WO2025218891A1

WO2025218891A1 - Determining capabilities of vehicle combinations

Info

Publication number: WO2025218891A1
Application number: PCT/EP2024/060432
Authority: WO
Inventors: Johan Lindberg; Leo Laine; Esteban GELSO; Maliheh SADEGHI KATI
Original assignee: Volvo Truck Corp
Current assignee: Volvo Truck Corp
Priority date: 2024-04-17
Filing date: 2024-04-17
Publication date: 2025-10-23
Anticipated expiration: 2026-10-17

Abstract

A computer system for determining a set of capabilities for an autonomously or semi- autonomously controllable vehicle combination, the computer system comprising processing circuitry configured to acquire an initial trajectory for the vehicle combination, acquire a reference probability distribution, RPD, for a control parameter for the vehicle combination based on a candidate set of capabilities for the vehicle combination, acquire a projected probability distribution, PPD, for the control parameter based on the initial trajectory and the candidate set of capabilities, and determine a set of capabilities for the vehicle combination based on a comparison between the RPD and the PPD.

Description

DETERMINING CAPABILITIES OF VEHICLE COMBINATIONS

TECHNICAL FIELD

[0001] The disclosure relates generally to vehicle control. In particular aspects, the disclosure relates to determining capabilities of vehicle combinations. The disclosure can be applied in heavy-duty vehicles, such as trucks, buses, and construction equipment. In particular, the disclosure can be applied in multi-unit vehicle combinations with distributed propulsion and energy storage. Although the disclosure may be described with respect to a particular vehicle, the disclosure is not restricted to any particular vehicle.

BACKGROUND

[0002] Vehicle motion management, such as automated driving, for multi-unit vehicle combinations is typically performed based on capabilities of different components of the vehicle combination. The capability of a sub-system or a component typically refers to the operational limits, such as power limits for batteries or torque limits related to engine, transmission, or electric motor drive systems. These capabilities are typically treated as fixed values. However, capabilities can change over time dependent on different factors, such as internal states, intended usage, optimization objectives, and durability.

[0003] It is therefore desired to develop a solution for vehicle motion management that addresses or at least mitigates some of these issues.

SUMMARY

[0004] This disclosure provides systems, methods and other approaches for determining a set of capabilities for an autonomously or semi-autonomously controllable vehicle combination. A reference probability distribution (RPD) for a control parameter for the vehicle combination is acquired that is based on a candidate set of capabilities for the vehicle combination. A projected probability distribution (PPD) for the control parameter is also acquired based on an initial trajectory for the vehicle combination and the candidate sets of capabilities. Based on a comparison between the RPD and PPD, a set of capabilities can be determined for use in trajectory planning or motion control for the vehicle combination. [0005] According to a first aspect of the disclosure, there is provided a computer system for determining a set of capabilities for an autonomously or semi-autonomously controllable vehicle combination, the computer system comprising processing circuitry configured to acquire an initial trajectory for the vehicle combination; acquire a reference probability distribution, RPD, for a control parameter for the vehicle combination based on a candidate set of capabilities for the vehicle combination, acquire a projected probability distribution, PPD, for the control parameter based on the initial trajectory and the candidate set of capabilities, and determine a set of capabilities for the vehicle combination based on a comparison between the RPD and the PPD.

[0006] The first aspect of the disclosure may seek to provide a computer system for determining capabilities for use in vehicle motion management in a manner that takes into account that these capabilities can change over time, often dependent on factors such as intended usage of vehicle components and sub-systems and optimisation objectives. A technical benefit may include that improved vehicle motion management is achieved as appropriate capabilities can be set for motion control. For example, the capabilities that match the expected or intended usage of the vehicle combination can be selected.

[0007] Optionally in some examples, including in at least one preferred example, the processing circuitry is configured to acquire a PPD for each of a plurality of candidate sets of capabilities, and determine a set of capabilities having the best fit to the RPD for the control parameter for the vehicle combination. A technical benefit may include that the set of capabilities that best fulfills the requirements can be identified, which may then be in vehicle motion management.

[0008] Optionally in some examples, including in at least one preferred example, the plurality of candidate sets of capabilities correspond to a plurality of reference temperatures for an operational objective. A technical benefit may include that the control of the vehicle combination may be optimized for different objectives such as performance, energy efficiency, and durability, by setting a reference temperature according to the objective.

[0009] Optionally in some examples, including in at least one preferred example, the processing circuitry is configured to determine a difference between the RPD and the PPD, and update the candidate set of capabilities to reduce the difference. A technical benefit may include that the actual or future usage of a sub-system or component, represented by the PPD, may be actively correlated the expected usage, represented by the RPD, making it possible to mitigate excessive usage and sustain durability of the sub-system or component.

[0010] Optionally in some examples, including in at least one preferred example, the processing circuitry is configured to acquire the RPD and/or the PPD using a kernel density estimation. A technical benefit may include that a Kernel Density Estimation method is nonparametric and can take any distribution, and that data analysis may be facilitated and data patterns may be visualized.

[0011] Optionally in some examples, including in at least one preferred example, the control parameter comprises a power, power stress range, power cycle range, power cycle average, speed and/or torque of the vehicle combination. A technical benefit may include that different possible usage and/or optimisation objectives relating to power and corresponding patterns of stress range are taken into account.

[0012] Optionally in some examples, including in at least one preferred example, the initial trajectory is determined based on hard constraints for the vehicle combination. A technical benefit may include increased safety as the instantaneous physical limits beyond which subsystems or components will endure stress and fail as well as legal limits such as a maximum velocity of the vehicle combination are taken into consideration.

[0013] Optionally in some examples, including in at least one preferred example, each set of capabilities comprises capabilities relating to one or more of a battery, electrical machine, service brakes, or transmission of the vehicle combination. A technical benefit may include that capabilities relating to the propulsion system and braking system are determined whereby improved vehicle motion management may be achieved.

[0014] Optionally in some examples, including in at least one preferred example, the processing circuitry is further configured to provide the determined set of capabilities to a control system configured to determine an updated trajectory for the vehicle combination. A technical benefit may include that an optimized trajectory based on different possible usage and/or optimisation objectives and appropriate capabilities is achieved for use by the control system to manage vehicle motion.

[0015] Optionally in some examples, including in at least one preferred example, the processing circuitry is further configured to provide the determined set of capabilities to a control system configured to determine one or more control inputs for the vehicle combination. A technical benefit may include improved vehicle motion management of an autonomously or semi-autonomously controllable vehicle combination based on appropriate capabilities. [0016] According to a second aspect of the disclosure, there is provided a vehicle comprising the computer system of any preceding claim. The second aspect of the disclosure may seek to provide a vehicle capable of determining capabilities for use in vehicle motion management, in a manner that takes into account that the capabilities can change over time in dependence of factors such as internal states, intended usage and different optimization objectives.

[0017] According to a third aspect of the disclosure, there is provided a battery electric vehicle combination comprising the computer system of any preceding claim. The third aspect of the disclosure may seek to provide a battery electric vehicle capable of determining capabilities for use in vehicle motion management, in a manner that takes into account that the capabilities can change over time in dependence of factors such as internal states, intended usage and different optimization objectives.

[0018] According to a fourth aspect of the disclosure, there is provided a computer- implemented method for determining a set of capabilities for an autonomously or semi- autonomously controllable vehicle combination, the method comprising acquiring, by processing circuitry of a computer system, an initial trajectory for the vehicle combination, acquiring, by the processing circuitry, a reference probability distribution, RPD, for a control parameter for the vehicle combination based on a candidate set of capabilities for the vehicle combination, acquiring, by the processing circuitry, a projected probability distribution, PPD, for the control parameter based on the initial trajectory and the candidate set of capabilities, and determining, by the processing circuitry, a set of capabilities for the vehicle combination based on a comparison between the RPD and the PPD.

[0019] The fourth aspect of the disclosure may seek to provide a computer-implemented method for determining capabilities for use in vehicle motion management in a manner that reflect the internal states and intended usage of vehicle components and sub-systems as well as different optimization objectives, whereby improved vehicle motion management is achieved. [0020] According to a fifth aspect of the disclosure, there is provided a computer program product comprising program code for performing, when executed by processing circuitry, the computer-implemented method. The fifth aspect of the disclosure may seek to enable new vehicles and/or legacy vehicles to be conveniently configured, by software installation/update, to determine capabilities for use in vehicle motion management in a manner that takes into account that the capabilities can change over time in dependence of factors such as internal states, intended usage and different optimization objectives. [0021] According to a sixth aspect of the disclosure, there is provided a non-transitory computer-readable storage medium comprising instructions, which when executed by processing circuitry, cause the processing circuitry to perform the computer-implemented method. The sixth aspect of the disclosure may seek to enable new vehicles and/or legacy vehicles to be conveniently configured, by software installation/update, to determine capabilities for use in vehicle motion management in a manner that takes into account that the capabilities can change over time in dependence of factors such as internal states, intended usage and different optimization objectives.

[0022] The disclosed aspects, examples (including any preferred examples), and/or accompanying claims may be suitably combined with each other as would be apparent to anyone of ordinary skill in the art. Additional features and advantages are disclosed in the following description, claims, and drawings, and in part will be readily apparent therefrom to those skilled in the art or recognized by practicing the disclosure as described herein.

[0023] There are also disclosed herein computer systems, control units, code modules, computer-implemented methods, computer readable media, and computer program products associated with the above-discussed technical benefits.

BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Examples are described in more detail below with reference to the appended drawings.

[0025] FIG. 1A schematically shows a side view of a vehicle combination according to an example of the disclosure.

[0026] FIG. IB schematically shows a top view of a vehicle combination according to an example of the disclosure.

[0027] FIG. 2 schematically shows, in terms of functional blocks, a control system for a vehicle according to an example of the disclosure.

[0028] FIG. 3 is a flow chart of a computer-implemented method according to an example. [0029] FIG. 4 is a plot of probability distributions according to an example of the disclosure.

[0030] FIG. 5 is a plot of probability distributions according to an example of the disclosure.

[0031] FIG. 6 is a schematic diagram of a computer system for implementing examples disclosed herein. [0032] Like reference numerals refer to like elements throughout the description.

DETAILED DESCRIPTION

[0033] The detailed description set forth below provides information and examples of the disclosed technology with sufficient detail to enable those skilled in the art to practice the disclosure.

[0034] Vehicle motion management, such as automated driving, for multi-unit vehicle combinations is typically performed based on capabilities of different components of the vehicle combination. The capability of a sub-system or a component typically refers to the operational limits, such as power limits for batteries or torque limits related to engine, transmission, or electric motor drive systems. These capabilities are typically treated as fixed values. However, capabilities can change over time dependent on different factors, such as internal states, intended usage, optimization objectives, and durability.

[0035] To remedy this, systems and methods are proposed for determining a set of capabilities for an autonomously or semi-autonomously controllable vehicle combination. A reference probability distribution (RPD) for a control parameter for the vehicle combination is acquired that is based on a candidate set of capabilities for the vehicle combination. A projected probability distribution (PPD) for the control parameter is also acquired based on an initial trajectory for the vehicle combination and the candidate sets of capabilities. Based on a comparison between the RPD and projected PPD, a set of capabilities can be determined for use in trajectory planning or motion control for the vehicle combination.

[0036] FIG. 1A schematically shows a side view of an example vehicle combination 100 of the type considered in this disclosure. The vehicle combination 100 comprises a number of units 110, including a tractor unit and at least one trailing unit. Each unit 110 may be given an index z, and the total number of units 110 in a vehicle combination 100 is designated n. Whilst two trailing units are shown, it will be appreciated that the vehicle combination 100 may comprise more or fewer trailing units connected to each other. This gives rise to different types and designations of vehicle combinations.

[0037] A tractor unit, such as the tractor unit 110-1, is generally the foremost unit in a vehicle combination 100, and may comprise the cabin for the driver, including steering controls, dashboard displays and the like. Generally, the tractor unit 110-1 is used to provide propulsion power for the vehicle combination 100. In the example of FIG. 1A, the tractor unit 110-1 may also be used to store goods that are being transported by the vehicle combination 100

[0038] A trailing unit, such as the trailing units 110-i, 110-n, is generally used to store goods that are being transported by the vehicle combination 100. A trailing unit may be a truck, trailer, dolly and the like. A trailing unit may also provide propulsion to the vehicle combination 100. A trailing unit without a front axle, such as the trailing units 110-i, 110-n, is known as a semi-trailer. In vehicle combinations such as that shown in FIG. 1 A, vehicle motion management is available on a unit level to receive requests from a manual or virtual driver to coordinate the propulsion, braking and steering.

[0039] Whilst three tractor axles and two axles per trailer are shown, it will be appreciated that any suitable number of axles may be provide on the respective units 110. It will also be appreciated that any number of the tractor axles and/or trailer axles may be driven axles, including zero (i.e. one of the units may include at least one driven axle while the other does not).

[0040] The vehicle combination 100 may comprise one or more sources or propulsion. For example, on or more of the units 110 may comprise one or more electrical machines 120 such as electric motors. Each unit 110 may comprise one or more batteries 130 configured to provide power to the electrical machines 120. A vehicle combination 100 that uses only battery power is a BEV. In some examples, for example in the case of an HEV, a unit 110, most often a tractor unit 110-1, may also include another source of propulsion, for example an internal combustion engine (ICE). The vehicle combination 100 also comprises a drivetrain (not shown) to deliver mechanical power from the propulsion source (the electrical machines 120 or the ICE) to the wheels 140. All units 110 may provide propulsion to the vehicle combination 100. In the examples discussed herein, the vehicle combination 100 may be a BEV or an HEV.

[0041] The electrical machines 120 are configured to drive, e.g. provide torque and/or steering to, one or more axles or individual wheels 140 of the unit 110. The electrical machines 120 of a unit 110 can supply either a positive (propulsion) or negative (braking) force. In some examples, electric motors may also be operated as generators, in order for the electric motors to generate braking force when required. The use of electrical machines 120 to supply a negative force is known as regenerative braking. The energy recovered from regenerative braking can be stored in the batteries 130, and so regenerative braking is generally preferred over using service brakes 150.

[0042] Furthermore, each unit 110 may comprise one or more sets of service brakes 150. The service brakes 150 of a unit 110 can supply a negative (braking) force. The service brakes 150 may be, for example, frictional brakes such as pneumatic brakes. Pneumatic brakes use a compressor to fill the brake with air, which may be powered by the batteries 130. In some examples, the brakes may be electro-mechanical brakes or hydraulic brakes.

[0043] The vehicle combination 100 may also comprise one or more auxiliary systems (not shown). The auxiliary systems may include auxiliary mechanical systems, such as alternators, power take-off (PTO) systems, and an air compressors, and auxiliary electrical systems, such as steering pumps, headlights, other light systems, ignition systems, audio systems, and air conditioning systems.

[0044] The ICE, electrical machines 120 and service brakes 150 are considered as actuators of the vehicle combination 100. Other actuators may also be present. For example, steering actuators 150, such as steering servo arrangements, may be provided, and may be implemented as electro-hydraulic actuators. Each actuator in a given unit 110 may be given an index k, and the total number of actuators in a given unit 110 is designated m. It will be appreciated that each axle and/or wheel 140 may have an associated electrical machine 130, set of service brakes 150, and/or set of steering actuators 150.

[0045] The vehicle combination 100, or indeed one or more (e.g. each) units 110, can be considered to comprise two systems: a propulsion system comprising the components that are involved in propulsion of the vehicle combination 100, and a braking system comprising the components that are involved in braking of the vehicle combination 100. As such, the propulsion system can be considered to comprise one or more of the ICE, electrical machines 120, the drivetrain, and batteries 130 of the vehicle combination 100, while the braking system can be considered to comprise the ICE, the electrical machines 120, the drivetrain, the batteries 130, and the service brakes 150. As such, there is some overlap between the propulsion system and the braking system.

[0046] FIG. IB schematically shows a top view of an example vehicle combination 100 of the type considered in this disclosure. Similarly to the example of FIG. 1A, the vehicle combination 100 comprises a number of units 110, including a tractor unit and a plurality of trailing units. FIG. IB also shows the requested global forces of the vehicle combination 100 as a whole. Examples of requested global forces of the vehicle combination 100 as a whole may e.g. include a total longitudinal/axial force Fx.tot a total lateral/radial force F_y, tot, and/or one or more yaw moments M_z,t for the respective vehicle units 110. In order to control motion of a vehicle combination 100, the requested global forces of the vehicle combination 100 must be determined and resolved. This may be achieved by a control system 200 (shown in FIG. 2) of the vehicle combination 100 that determines control signals based on a requested reference input and certain operating conditions of the vehicle combination 100.

[0047] In the example of FIG. IB, the vehicle combination 100 includes a combination control allocator 210 and a plurality of unit control allocators 212. The combination control allocator 210 and the various unit specific control allocators 212 together form a distributed control allocation system for the vehicle combination 100. In this system, the control allocation may be performed on multiple levels, i.e. first on a level of the vehicle combination 100 as a whole, and then on a level of each vehicle unit 110 individually. The combination control allocator 210 may be provided (as shown) as part of the tractor unit 110-1, while the unit control allocators 212 are provided as part of each individual unit 110. It will be appreciated that the combination control allocator 210 may be provided as part of any unit 110 of the vehicle combination 100.

[0048] FIG. 2 schematically shows, in terms of functional blocks, an example control system 200 for a vehicle, such as the vehicle combination 100. The control system 200 serves to perform various functions of the vehicle combination 100, such as power management and motion coordination. The control system 200 comprises a tactical layer 202, a target generator 204, a state estimator 206, an energy manager 208, a combination control allocator 210 and a plurality of unit control allocators 212. The combination of the target generator 204, the state estimator 206, and the energy manager 208, may be referred to as a vehicle motion controller (VMC) of the vehicle combination 100. The various modules may e.g. be implemented as code running on a processing circuitry, or similar. The various modules may comprise processing circuitry configured to implement various operations disclosed below. The various modules may include a memory storing instructions that, when executed by the processing circuitry, cause the processing circuitry to perform the various operations. The various modules may be communicatively connected or connectable to each other, for example as known in the art.

[0049] The tactical layer 202 is responsible for ensuring that the trajectory for the whole combination 100 is obstacle free and collision free. The tactical layer 202 may also be referred to as an automated driving system (ADS) of the vehicle combination 100. For example, the tactical layer 202 may determine a trajectory for the vehicle combination 100 that ensures that a swept path of the vehicle combination 100 and the individual units 110 is safe and achievable. To this end, the tactical layer 202 may provide an input r_ads relating to a manoeuvre in an autonomous driving case. The input r_ads may include requests such as target distance, velocity, acceleration, and curvature (steering) for the vehicle combination 100. These may be scalar values or vectors with evolutions for a given prediction horizon. The trajectory may be determined by the tactical layer 202 based on hard constraints for the vehicle combination 100, as will be discussed below. The tactical layer 202 may also send determined future performance limits for the vehicle combination 100.

[0050] The tactical layer 202 may also send requests for power and energy management to optimize range and mission performance. For example, the tactical layer 202 may also include predictive energy management, including battery targets, capabilities and statuses that determine how the energy sources of the vehicle combination 100 should be used for a whole mission.

[0051] In some examples, the tactical layer 202 comprises a vehicle model 203. The vehicle model 203 is a model of the vehicle combination 100 intended to plan trajectories of the vehicle combination 100. As such, the vehicle model 203 can be used to determine the input r_ads. The vehicle model 203 may include different parameters of the vehicle combination 100 such as capabilities, structural parameters, and dynamic parameters of the vehicle combination 100, and be capable of determining the forces acting on the vehicle combination 100. The vehicle model 203 can be any suitable model, for example a model known in the art. The vehicle model 203 can be based on real tests, computer model simulations, a machine-learning model, or other suitable means known in the art. The vehicle model 203 may be, for example, a single-track model (i.e., left and right wheels on a given axle are considered together), such as a bicycle model. The vehicle model 203 may alternatively be a more complex model such as a dual track model (i.e., left and right wheels on a given axle are considered separately). The real units can have axle groups with several axles, but in the model they may be considered together. A tyre model can be used in combination with the vehicle model 203. The tyre model may take into account the cornering stiffness of the tyres of the vehicle combination 100. The vehicle model 203 may be configured to operate within an agreed operational design domain (ODD) and a specified safe operating envelope (SOE) for the vehicle combination 100. The vehicle model 203 may therefore include vehicle motion management logic that includes capabilities of the vehicle combination 100 and the SOE to avoid instabilities such as rollover, jack-knife, and/or an unsafe swept path width.

[0052] The vehicle model 203 may be time-invariant or time variant, based on certain parameters of the vehicle combination 100. To this end, the tactical layer 202 may receive parameters yi of the vehicle combination 100 from the vehicle combination 100 and/or the individual units 110. The parameters yi may include capabilities, structural parameters, and/or dynamic parameters of the vehicle combination 100. [0053] The vehicle capabilities comprise at least one of a maximum range capability, a maximum operational time capability, a longitudinal acceleration minimum, a longitudinal acceleration maximum, a longitudinal acceleration rate minimum, a longitudinal acceleration rate maximum, a longitudinal velocity minimum, a longitudinal velocity maximum, a longitudinal distance minimum, a longitudinal distance maximum, a yaw rate minimum, a yaw rate maximum, a yaw acceleration minimum, a yaw acceleration maximum, a longitudinal velocity maximum for uphill slopes, and a longitudinal velocity maximum values for downhill slopes. While the maximum range capability relates to total distance that the vehicle can travel, the longitudinal distance minimum/maximum refers to a relatively short distance, for example for shunting in a logistic context for moving a vehicle in a yard, or for a safe stop.

[0054] In some examples, the capabilities are functions of capability parameters. For example, the longitudinal acceleration minimum and/or the longitudinal acceleration maximum may be a function of one or more of a longitudinal velocity of the vehicle combination 100, a mass of the vehicle combination 100, a lateral acceleration of the vehicle combination 100, a turning radius of the vehicle combination 100, a longitudinal force provided by the electrical machines 120, and/or a thermal property of one or more batteries 130. In some examples, the longitudinal force provided by the electrical machines 120 is a function of thermal properties of the electrical machines 120, as the power capabilities of the the electrical machines 120, and consequently the longitudinal force capabilities, will be a function of motor temperature. Similarly, the capability of the batteries 130 depends on thermal properties of the batteries 130. Furthermore, the thermal properties of the batteries 130 may limit performance of the electrical machines 120 in the case that the battery power limits the electrical machine power and the electrical machines 120 can only provide a certain torque. The vehicle capabilities may also be influenced by a thermal mode requested by the tactical layer 202, as discussed further below.

[0055] The structural parameters of the vehicle combination 100 comprise at least one of a type of the vehicle combination 100, a number of units 110 of the vehicle combination 100, a number of axles in each unit 110, a tyre type in each axle group, a distance of each axle of each unit 110 to the first axle and coupling points of the unit 110, the number of steered axles in each unit 110, the number of propelled axles in each unit 110, the number of liftable axles in each unit 110, nominal diameters of the wheels 140, a track of each axle, a mass of the unladen vehicle combination 100, and a centre of gravity of the unladen vehicle combination 100. The type of the vehicle combination 100 may be defined by different types of coupling used in the vehicle combination 100. The tyre type may be defined by a tyre stiffnesses, a peak friction/ slip parameter of the tyre, and/or other parameters used in known tyre models such as the Pacejka Magic Formula or a brush model.

[0056] The dynamic parameters of the vehicle combination 100 comprise at least one of a mass of each unit 110, a load on each axle, an inertia of each unit 110, a lumped cornering stiffness of each axle, a rolling resistance of each axle, a distance of a dynamic centre of gravity from the first axle of each unit 110, and an air drag property. The inertia may be expressed in three directions, although the vertical direction is most relevant for trajectory planning as it represents the yaw moment of inertia, which is relevant for the yaw-plane motion of the vehicle combination 100. The air drag property may include am effective surface of the vehicle combination 100 for different wind directions.

[0057] Based on these received parameters yi of the vehicle combination 100, the vehicle model 203 can be updated to reflect the current state of the vehicle combination 100. This can be advantageous in autonomous driving of multi-unit vehicle combinations, as it may enable safe and precise trajectory planning, which is not trivial due to the complexity in their dynamics and interactions between units 110. For instance, an updated vehicle model 203 can enable a swept path of both the vehicle combination 100 and individual units 110 to be maintained within a safe range. Other typical use cases for the vehicle model 203 include overtake situations on uphill for the vehicle combination 100, where the vehicle model 203 can determine whether the vehicle combination 100 has sufficient motion capabilities for a successful overtake. Additionally, the vehicle model 203 can be applied to assess rough timing, determining how long the vehicle combination 100 can be used.

[0058] In some examples, the tactical layer 202 can decide on state of charge (SoC) targets for the batteries 130 of the vehicle combination 100 as a function of distance, in some cases considering slope changes, etc. For example, the tactical layer 202 can request the battery 130 of a unit 110 having a higher SoC be drained for an uphill slope, as it can foresee that batteries 130 of all units 110 can be charged fully with regenerative braking at a following downhill slope. In some examples, an SoC controller (not shown) can calculate weighting factors for SoC targets. In some examples, the tactical layer 202 can send targets for the state of energy rate (SoE) directly to the combination control allocator 210.

[0059] Furthermore, the tactical layer 202 can request the transfer of energy from one unit 110 to another by means of propulsion in one unit 110 and regenerative braking in the other (as explained in WO 2021/180300 Al in the name of Volvo Truck Corporation). In another example, the tactical layer 202 requests the battery 130 of a unit 110 be drained faster than another based on the number of available chargers in a following charge station or due to equalizing the charging time of all units 110 or minimizing the total charging time at the charging station.

[0060] The tactical layer 202 can also be used to select an operating mode (otherwise known as a thermal management mode) for the vehicle combination 100. A vehicle combination 100 may be capable of operating in a number of different modes dependent on desired performance. It is advantageous to provide smart electric vehicle units that can provide different settings or automatically detect which operating mode is most suitable for durable and/or efficient driving. The tactical layer 202 can select an operating mode based on factors such as current traffic situation, road types, GPS signals, weather conditions, or a vehicle usage preference (a preferred driving scenario for example long distance, short distance usage, etc.). The tactical layer 202 can also select an operating mode based on real time data from the vehicle sensors, or vehicle-to-vehicle/infrastructure communication data. For example, if it is determined that a quick acceleration or high performance is needed based on this data (e.g. due to changes in traffic conditions), the tactical layer 202 can select an operating mode accordingly. The operating modes may include an “Eco” mode or “Range” mode, in which acceleration and top speed of the vehicle combination 100 can be limited to optimise energy efficiency and maximise range, an “Endurance” mode, intended to enable a vehicle combination 100 to operate for a long duration, a “Performance” mode, configured to provide maximum acceleration and top speed, and an “I-know” mode, in which pre-set configurations for the vehicle combination 100 can be adjusted appropriate to desired performance.

[0061] The tactical layer 202 can interface with vehicle motion management components of the control system 202, in particular the target generator 204. As discussed above, the tactical layer 202 may provide an input r_ads relating to a manoeuvre to the target generator 204. In some instances, the input r_ads may be determined by the vehicle model 203 based on the current parameters yi received from the vehicle combination 100. This interface ensures that motion in a reference coordinate system can be requested by the tactical layer 202 within the capabilities of the vehicle combination 100 to ensure safe and efficient motion control. This enables fully automated driving with redundancy and vehicle safety.

[0062] The purpose of the target generator 204 is to determine a requested reference input r_req and a requested combination control input Vcomb.req for the vehicle combination 100. The requested reference input r_req is determined based on an input related to a manoeuvre for the vehicle combination 100, for example the input rads from the vehicle model 203 of the tactical layer 202, and represents a requested movement of the vehicle combination 100. The requested combination control input Vcomb.req can be determined based on the requested reference input r_req and/or the input r_ads. The requested combination control input Vcomb.req can also be determined based on a motion capability Vcomb.cap for the vehicle combination 100. The target generator 204 comprises a path planner/controller 214 and a force generator 216.

[0063] In particular, the target generator 204 may receive an input related to a manoeuvre for the vehicle combination 100. The manoeuvre may be, for example, straight-line driving, cornering, braking and the like. The target generator 204 may receive data from, for example, a steering wheel and/or gas/brake pedal of the combination 100, indicating that the driver (or some other system of the vehicle combination 100) wants to change the direction and/or the speed of the vehicle combination 100 in a certain way. This may be the case in a semi- autonomous driving scenario. In some examples, the input may originate from elsewhere, for example any other system that may provide some indication of how the overall forces of the vehicle combination 100 are to be influenced (e.g. steered, propelled or braked). For example, the data may originate from a lane assist system, a lane following system, an emergency steering system, an emergency braking system, an automated or semi-automated drive system. In one particular example, the target generator 204 may receive the input r_ads from the vehicle model 203 of the tactical layer 202. This may be the case in a fully autonomous driving scenario. Based on this input, the target generator 204 may output a requested reference input r_req. In particular, the path planner/controller 214 determines the requested reference input rreq. The requested reference input r_req may comprise at least one of a longitudinal acceleration a_x of the vehicle combination 100 as a whole or of a unit 110 of the vehicle combination 100 (for example the unit 110 comprising the combination control allocator 210), a longitudinal velocity v_xi of a tractor unit 110-1, a lateral velocity v_yi of the tractor unit 110-1, a yaw rate cozt of at least one unit 110 of the vehicle combination 100, and a steering angle y _req of the tractor unit 110-1. In some examples, the target generator 204 may also receive determined future performance limits for the vehicle combination 100.

[0064] The requested combination control input Vcomb.req is determined by the force generator 216. The requested combination control input Vcomb.req can be determined based on the requested reference input r_req, or based on the input r_ads directly. In the latter case, the path planner/controller 214 can be used to determine a requested reference input r_req for shorter term motion, for example by up-sampling the requests r_ads from the tactical layer 202 that may be sent infrequently (e.g. every second or so). The requested combination control input V comb, req may include requested motion parameters for the vehicle combination 100. In particular, the forces Ftot.req and/or moments M_z, tot, req that need to be applied to the vehicle combination 100 as a whole in order to follow the requested reference input r_req are determined. The requested motion parameters included in the requested combination control input Vcomb.req of the vehicle combination 100 may comprise at least one of a requested longitudinal force F_x, tot, req of the vehicle combination 100, a requested lateral force F_y,tot,req of the vehicle combination 100, a requested longitudinal coupling force F ext, req between consecutive units 110, and a requested lateral coupling force Fcyt.req between consecutive units 110. These make up the total requested force to be applied Ftot,req for the vehicle combination 100. The motion parameters included in the requested combination control input Vcomb.req of the vehicle combination 100 may also comprise a requested yaw moment Mz,t,req for one or more units 110.

[0065] The requested combination control input Vcomb.req may also be determined based on state information j’2 from the different units 110 of the vehicle combination 100 and a motion capability Vcomb.cap for the vehicle combination 100. The state information y2 may include information from sensors of the vehicle combination 100 such as wheel speed sensors, inertial measurement units, articulation angle sensors and the like. The motion capability Vcomb.cap of the vehicle combination 100 may describe the limits of motion parameters for safe operation of the vehicle combination 100. The motion capability Vcomb.cap may comprise at least one of a longitudinal force capability F_x.tot,cap of the vehicle combination 100, a lateral force capability Fy. tot, cap of the vehicle combination 100, and a yaw moment capability Mz,t,cap for one or more units 110. The state information y2 may also include structural parameters of the vehicle combination 100 as discussed above in relation to parameters yi .

[0066] The requested combination control input Vcomb.req may be determined based on a vehicle model. The vehicle model can be any suitable model, for example a model known in the art. The model can be based on real tests, computer model simulations, a machine-learning model, or other suitable means known in the art. The vehicle model may provide motion prediction of the vehicle combination 100 by looking at previous steering input and acceleration input. The prediction may include instabilities such as understeer or rollover risk, for example within a one-second horizon. The model may be, for example, a single-track model, i.e., left and right wheels on a given axle are considered together. The real units can have axle groups with several axles, but in the model they are considered together. A tyre model can be used in combination with the vehicle model. The tyre model may take into account the cornering stiffness of the tyres of the vehicle combination 100.

[0067] The state estimator 206 is responsible for processing state information y4 from the different units 110 of the vehicle combination 100. For example, the state estimator 206 may receive information from sensors of the vehicle combination 100 such as wheel speed sensors, inertial measurement units, articulation angle sensors and the like and use this information to determine states for the vehicle combination 100 and the various units. The state estimator 206 may then output unit-specific state information x_P to the energy manager 208 and unit-specific state information x_c to the combination control allocator 210.

[0068] The energy manager 208 determines a power split between the different units 110 of the vehicle combination 100. The energy manager 208 may also determine a power split within each unit 110, meaning how the power demand is divided between the actuators (for example, the ICE, the electrical machines 120, service brakes 150, and/or steering actuators) of the unit 110. Inputs to the energy manager 208 include the requested reference input r_req from the target generator 204 and the statuses SoX of the batteries 130 of the vehicle combination 100. The energy manager 208 determines a power allocation and an associated power allocation input Ucomb,des. The power split may be determined based on the state of energy rate (SoE) for each unit 110 and/or the longitudinal part of the requested force for the unit’s propulsion system Fxpi.req. The energy manager 208 may consider factors that affect long-term energy consumption, such as road slopes, SoC states, charger locations, and the like, and determine power behaviour as a function of the energy over time. The energy manager 208 may also be configured as a power manger. For example when a time horizon is considered, it may handle energy. When instantaneous values are considered, it may handle power.

[0069] Based on these values, the control allocators 210, 212 may determine control data that meets the requested global forces of the vehicle combination 100 to meet certain constraints, such as power management (optimising battery usage) and safety constraints (ensuring that the trajectory for the whole combination 100 is obstacle free and collision free). In particular, the control allocators 210, 212 determine how various actuators (for example, the ICE, the electrical machines 120, service brakes 150, and/or steering actuators) of the vehicle combination 100 are to be controlled in order to generate requested global forces of the vehicle combination 100 as a whole. The combination control allocator 210 and the various unit specific control allocators 212 together form a distributed control allocation system for the vehicle combination 100. In this system, the control allocation is performed on multiple levels, i.e. first on a level of the vehicle combination 100 as a whole, and then on a level of each vehicle unit 110 individually.

[0070] The combination control allocator 210 transforms the requested combination control input Vcomb.req from the target generator 204 into an allocated combination control input Ucomb for the vehicle combination 100, describing appropriate motion parameters for each unit 110. The allocated combination control input u_COmb of the vehicle combination 100 comprises the forces F and/or moments AT to be applied for the vehicle combination 100. The allocated combination control input Ucomb comprises allocated unit control inputs m describing the forces and/or moments that each respective unit 110 is to produce in order to provide the allocated combination control input Ucomb of the vehicle combination 100. The allocated unit control inputs ut may comprise a force control input for the unit’s propulsion system F_Pi, and a force control input for the unit’s braking system Fbt.

[0071] The unit control allocators 212 comprise a specific control allocator 212 for each unit 110 of the vehicle combination 100. The unit-specific allocated control inputs m that are output from the combination control allocator 210 are transformed into actuator-specific allocated control inputs Uk, describing actual actuator commands by the unit-specific control allocators 212. For example, the unit-specific control allocators 212 map the forces and moments of each unit 110 into the steering and drive/brake torques to be applied at the wheels of each unit 110. To do this, the unit control allocators 212 may determine a requested force control input for the unit’s propulsion system F_Pi and a requested force control input for the unit’s braking system Fbt. The unit control allocators 212 then determine the actuator-specific allocated control inputs Uk accordingly, which comprise allocated force control inputs for the individual actuators of the unit’s different systems: F_Pk for the actuators of the propulsion system, and Fbk for the actuators of the braking system.

[0072] In some examples, each unit 110 may be capable of estimating its own capabilities Ui,_cap, e.g. how much and/or how fast the unit 110 can move at a current time instant. The unit capabilities comprise a force capability for its propulsion system F_Pi,_cap and a force capability for its braking system Fbt,ca_P. This may be based on an actuator capability uk,ca_P for each actuator, e.g. how much and/or how fast the actuator can move at a current time instant. The actuator capabilities comprise a force capability for the actuators F_Pk,ca_P during propulsion and a force capability for the actuators Fbk,ca_P during braking. The actuators of each unit 110 may provide an actuator capability Uk,ca_P to the respective unit control allocator 212-i, which provides a unit capability Ui,_cap to the combination control allocator 210. The unit capabilities Ui,_cap may also comprise capabilities of the power input/output of the batteries 130.

[0073] Each unit 110 may also be capable of estimating its own power losses Pi, loss. The unit power losses Pi, loss comprise a power loss for its propulsion system P_Pi,i_oss and a power loss for its braking system Pbi.ioss. This may be based on an actuator power losses Pk,ioss,i for each actuator in the unit 110 as well as other power losses in the unit 110, such as power losses in the batteries and the drivetrain. The actuator power losses Pk,ioss,i comprise a power loss for propulsion actuators P_pk,ioss,i (e.g. electrical machines 120, ICE, and/or other propulsion sources) and a power loss for braking actuators Pbk,ioss,i (e.g. electrical machines 120 and/or service brakes 150) The actuators of each unit 110 may provide the actuator power losses Pk,ioss,i to the respective unit control allocator 212-i, which provides unit power losses Pi, loss to the combination control allocator 210.

[0074] The capability of a sub-system or a component typically refers to its operational limits, such as power limits for batteries or torque limits for electrical machines. A capability of a sub-system or a component may describe its limits in value, time and frequency domain. These limits can be divided into hard and soft limits. Hard limits are the instantaneous physical limits of the sub-system or component, beyond which it will endure stress and fail, or may be legal limits (such as a maximum velocity of the vehicle combination 100). Soft limits can be seen as constraints within the hard limits that can be exceeded intermittently, but not too often and not for a long period. The soft limits typically relate to mission objectives, such as performance, energy efficiency, or durability, and an intended usage of a component. These can be based on thermal conditions that may have an impact on the performance of the subsystem or component.

[0075] As discussed in relation to FIG. 2, various types of capabilities can be taken into account by the control system 200. These can include vehicle capabilities that are used in the vehicle model 203 of the tactical layer 202, the motion capability Vcomb.cap for the vehicle combination 100 used by the target generator 204, and the unit capabilities Ui,_cap that are determined based on the actuator capabilities uk,ca_P. These are typically used to determine hard constraints such as safety-related limits. Legal limits may be programmed manually or downloaded to the control system.

[0076] As mentioned above, the capability of a sub-system or component may not only depend on the current internal state of the system, but often also on its intended usage. However, the intended usage of a system or component may also depend on a specific capability. This creates a loop scenario, where the intended usage and the capabilities are dependent on each other. For example, an ADS (e.g. the tactical layer 202) may determine a motion and power trajectory for a vehicle combination 100 that is evaluated against the motion capability Vcomb.cap by the VMC (e.g. the target generator 204). The VMC then provides a response that may modify of the trajectory to comply with the motion capability Vcomb.cap. This modified trajectory should then be evaluated by the ADS, which may further modify it. Such looping should be avoided. Furthermore, capabilities may change dependent on an optimisation objective. For example, control of the vehicle combination 100 optimised for performance will require different functionality of sub-systems and components than control of the vehicle combination 100 optimised for energy efficiency or durability. Therefore, the capabilities for each sub-system or component may be different for different objectives. Yet further, the actual usage of a sub-system or component may differ from the expected usage, meaning that future usage may need to be changed to sustain durability. This will also be reflected in a change of capabilities for the sub-system or component. An improved approach for determining capabilities, in particular soft capabilities, for use in an ADS or VMC of a vehicle combination 100 is therefore required.

[0077] FIG. 3 is a flow chart of a computer-implemented method 300 according to an example. The method 300 is for determining a set of capabilities for an autonomously or semi- autonomously controllable vehicle combination, such as the vehicle combination 100. The method 300 enables a set of capabilities to be determined for use in controlling a vehicle combination, taking into account different possible usage and/or optimisation objectives. The method 300 may be implemented by processing circuitry of a computer system (e.g., the control system 200 described in relation to FIG. 2).

[0078] At 302, an initial trajectory for the vehicle combination 100 is acquired. For example, by an ADS of the vehicle combination 100 (e.g. the tactical layer 202) may determine a trajectory for the vehicle combination 100 and provide an input r_ads. The input r_ads may include requests such as target distance, velocity, acceleration, and curvature (steering) for the vehicle combination 100. In some examples, the tactical layer 202 may determine the trajectory based on hard constraints for the vehicle combination 100. The hard constraints may be physical limits of a sub-system or component or legal limits, as discussed above.

[0079] At 304, a reference probability distribution (RPD) for a control parameter for the vehicle combination 100 is acquired based on a candidate set of capabilities for the vehicle combination 100. This may be performed by an ADS of the vehicle combination 100 (e.g. the tactical layer 202). The RPD may be determined using a probability distribution function, which is a statistical function that provides the probabilities of different outcomes or events in a probabilistic system. It describes the likelihood of each possible value of a variable occurring. The probability distribution may be generated by any suitable function as known in that art, for example using kernel density estimation (KDE), which is a non-parametric method used to estimate the probability distribution of a random variable based on a set of observed data points, Rainflow counting, and the like. In some examples, the probability distribution function is a cumulative distribution function (CDF), which is a function that gives the probability that a variable will take on a value less than or equal to a given value. A CDF based on a KDE method is non parametric and can have any distribution, but can also be parametrized to some known probability distribution such as Normal, Exponential, Beta, and Poisson distributions and the like. In other examples, the probability distribution function is a probability density function, which is a function that describes the likelihood of a continuous random variable taking on a specific value within a given interval.

[0080] The control parameter that is modelled by the probability distribution function may be a power, power stress range, power cycle range, power cycle average, speed, and/or torque of the vehicle combination 100. The control parameter may be a setting then enables the probability distribution function to generate an appropriate distribution. In one example, a power cycle average may be determined using a Rainflow counting algorithm, which is a method used for counting and analysing fatigue cycles in a time series of stress or strain data.

[0081] In particular, the RPD is determined based on a first candidate set of capabilities for the vehicle combination 100. The first candidate set of capabilities may be used as an input to the function, which generates the probability distribution. The first candidate set of capabilities comprises capabilities relating to one or more of electrical machines 120, batteries 130, service brakes 150, or a transmission of the vehicle combination 100. The first candidate set of capabilities may be filter model representation, where a digital filter function represents timedependent capabilities. This is explained in detail in PCT patent application PCT/EP2023/068988, which was filed in the name of Volvo Truck Corporation on 10 July 2023.

[0082] FIG. 4 shows an example RPD 402 (solid line) for power for a first set of capabilities. In this example, the RPD 402 is generated using a CDF, and illustrates an increasing probability that the power will take on a value less than or equal to the power value as that value increases.

[0083] At 306, a projected probability distribution (PPD) for the control parameter is acquired based on the initial trajectory and the first candidate set of capabilities. The initial trajectory may be used as another input to the function, which generates the probability distribution accordingly. This may be performed by a VMC of the vehicle combination 100 (e.g. the target generator 204). The PPD is a version of the RPD that considers the initial trajectory when providing the probabilities of different outcomes. The PPD may also be a generated using a cumulative distribution function or a probability density function. In some examples, the RPD can be acquired using a kernel density estimation. FIG. 4 also shows an example PPD 404 (dashed line) for power for the first set of capabilities. In this example, the PPD 404 is generated using a CDF, and illustrates a lower chance of being below a higher power than the RPD 402. This means that there is more headroom for increased flexibility of the capabilities.

[0084] In some examples, a PPD may be acquired for each of a plurality of candidate sets of capabilities. In this way, a plurality of different PPDs are acquired. Each of the plurality of candidate sets of capabilities may be similar in content and form as the first set of capabilities used to determine the RPD at 304, but may differ in one or more aspects from the first set of capabilities. The different sets of capabilities may be generated in any suitable manner, for example incrementally, or based on an objective as will be discussed below. FIG. 4 also shows an example PPD 406 (dotted line) for power for a second set of capabilities. In this example, the PPD 406 is generated using a CDF, and illustrates a higher chance of being below a lower power than the RPD 402. This means that there is less flexibility for the capabilities.

[0085] In some examples, a candidate set of capabilities may be acquired for a plurality of reference temperatures for an operational objective. As discussed above, control of the vehicle combination 100 may be optimised for objectives such as performance, energy efficiency, and durability. Each objective may have an associated set of reference temperatures. The capabilities for each sub-system or component may be different to meet these different reference temperatures. For example, to optimise energy efficiency, a coolant inlet reference temperature may be set higher to reduce the power requirement for cooling. To optimise performance, a lower coolant inlet reference temperature may be used to provide a higher torque/power capability and therefore increased headroom for transient power/torque capability, with the expense of increased auxiliary cooling power need. To optimise durability, a lower coolant inlet reference temperature may be used to reduce the operational average temperature and reduce the power required for cooling. These different sets of capabilities can be used to determine a plurality of different PPDs. FIG. 5 shows an example RPD 502 (solid line) for power usage for a first set of capabilities. FIG. 5 shows example PPDs 504 and 506 (dotted lines), where the reference temperature for the PPD 504 is lower than the reference temperature for the PPD 506.

[0086] At 308, a set of capabilities for the vehicle combination 100 is determined based on a comparison between the RPD acquired at 304 and the PPD acquired at 306. This may be performed by a VMC of the vehicle combination 100 (e.g. the target generator 204). The comparison can be performed in a number of different ways in order to determine a set of capabilities to be used in control of the vehicle combination 100.

[0087] In some examples, a difference between the RPD for the first candidate set of capabilities and PPD for the first candidate set of capabilities is determined. For example, a difference between the RPD 402 and the PPD 404 of FIG. 4 may be determined. Based on this, the first candidate set of capabilities can be updated in order to reduce the difference. In this way, the actual or future usage of a sub-system or component (represented by the PPD) may be correlated the expected usage (represented by the RPD), making it possible to mitigate excessive usage and sustain durability of the sub-system or component. For example, by applying a comparison between the the RPD and the PPD or the first candidate set of capabilities, such as Kolmogorov-Smirnov test or Cramer-von-Mises test, the difference can be fed back as a status to the ADS. The ADS can then redistribute the effort between the subsystems where there is a certain degree of freedom to do so. For example, if the probability that the power from an electric machine 120 will be low for the initial trajectory, the reference temperature for the cooling system can be increased, and the cooling pump speed decreased, to save energy over the trajectory. This involves an inherent update of the first set of capabilities. The updated first set of capabilities can then be used in control of the vehicle combination 100.

[0088] In some examples, where PPDs are acquired for each of a plurality of candidate sets of capabilities, a set of capabilities having the best fit to the RPD may be identified. For example, a fit between the RPD 402 and the PPD 404 of FIG. 4 may be determined, as well as a fit between the RPD 402 and the PPD 406. It may then be determined that the PPD 404 has the best fit to the RPD 402, and the first set of capabilities may therefore be used in control of the vehicle combination 100. The best fit may be found, for example, using a Kolmogorov- Smirnov test or a Cramer-von-Mises test.

[0089] At 310, the determined set of capabilities may be provided to an ADS of the vehicle combination 100 (e.g. the tactical layer 202), which may determine an updated trajectory for the vehicle combination 100 and provide an updated input rads based on the new set of capabilities.

[0090] At 310, the determined set of capabilities may be provided to VMC of the vehicle combination 100 (e.g. the target generator 204), which may determine one or more control inputs for the vehicle combination, for example, a requested combination control input V comb, req based on the new set of capabilities.

[0091] The method 300 enables the provision of a set of capabilities for use in controlling a vehicle combination, taking into account different possible usage and/or optimisation objectives. For example, as probability distributions are projected based on an initial trajectory for one or more sets of capabilities, the capabilities that match the expected or intended usage of the vehicle combination can be selected. This can be done for different control parameters, such as power and corresponding patterns of stress range. Furthermore, by using sets of capabilities that correspond to different reference temperatures, different optimisation objectives can be met. This can be achieved by using the determined set of capabilities to update a trajectory for the vehicle combination or provide control inputs for the vehicle combination.

[0092] FIG. 6 is a schematic diagram of a computer system 600 for implementing examples disclosed herein. The computer system 600 is adapted to execute instructions from a computer-readable medium to perform these and/or any of the functions or processing described herein. The computer system 600 may be connected (e.g., networked) to other machines in a LAN, an intranet, an extranet, or the Internet. While only a single device is illustrated, the computer system 600 may include any collection of devices that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein. Accordingly, any reference in the disclosure and/or claims to a computer system, computing system, computer device, computing device, control system, control unit, electronic control unit (ECU), processor device, processing circuitry, etc., includes reference to one or more such devices to individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein. For example, control system may include a single control unit or a plurality of control units connected or otherwise communicatively coupled to each other, such that any performed function may be distributed between the control units as desired. Further, such devices may communicate with each other or other devices by various system architectures, such as directly or via a Controller Area Network (CAN) bus, etc.

[0093] The computer system 600 may comprise at least one computing device or electronic device capable of including firmware, hardware, and/or executing software instructions to implement the functionality described herein. The computer system 600 may include processing circuitry 602 (e.g., processing circuitry including one or more processor devices or control units), a memory 604, and a system bus 606. The computer system 600 may include at least one computing device having the processing circuitry 602. The system bus 606 provides an interface for system components including, but not limited to, the memory 604 and the processing circuitry 602. The processing circuitry 602 may include any number of hardware components for conducting data or signal processing or for executing computer code stored in memory 604. The processing circuitry 602 may, for example, include a general-purpose processor, an application specific processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a circuit containing processing components, a group of distributed processing components, a group of distributed computers configured for processing, or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. The processing circuitry 602 may further include computer executable code that controls operation of the programmable device.

[0094] The system bus 606 may be any of several types of bus structures that may further interconnect to a memory bus (with or without a memory controller), a peripheral bus, and/or a local bus using any of a variety of bus architectures. The memory 604 may be one or more devices for storing data and/or computer code for completing or facilitating methods described herein. The memory 604 may include database components, object code components, script components, or other types of information structure for supporting the various activities herein. Any distributed or local memory device may be utilized with the systems and methods of this description. The memory 604 may be communicably connected to the processing circuitry 602 (e.g., via a circuit or any other wired, wireless, or network connection) and may include computer code for executing one or more processes described herein. The memory 604 may include non-volatile memory 608 (e.g., read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.), and volatile memory 610 (e.g., random-access memory (RAM)), or any other medium which can be used to carry or store desired program code in the form of machineexecutable instructions or data structures and which can be accessed by a computer or other machine with processing circuitry 602. A basic input/output system (BIOS) 612 may be stored in the non-volatile memory 608 and can include the basic routines that help to transfer information between elements within the computer system 600.

[0095] The computer system 600 may further include or be coupled to a non-transitory computer-readable storage medium such as the storage device 614, which may comprise, for example, an internal or external hard disk drive (HDD) (e.g., enhanced integrated drive electronics (EIDE) or serial advanced technology attachment (SATA)), HDD (e.g., EIDE or SATA) for storage, flash memory, or the like. The storage device 614 and other drives associated with computer-readable media and computer-usable media may provide nonvolatile storage of data, data structures, computer-executable instructions, and the like.

[0096] Computer-code which is hard or soft coded may be provided in the form of one or more modules. The module(s) can be implemented as software and/or hard-coded in circuitry to implement the functionality described herein in whole or in part. The modules may be stored in the storage device 614 and/or in the volatile memory 610, which may include an operating system 616 and/or one or more program modules 618. All or a portion of the examples disclosed herein may be implemented as a computer program 620 stored on a transitory or non- transitory computer-usable or computer-readable storage medium (e.g., single medium or multiple media), such as the storage device 614, which includes complex programming instructions (e.g., complex computer-readable program code) to cause the processing circuitry 602 to carry out actions described herein. Thus, the computer-readable program code of the computer program 620 can comprise software instructions for implementing the functionality of the examples described herein when executed by the processing circuitry 602. In some examples, the storage device 614 may be a computer program product (e.g., readable storage medium) storing the computer program 620 thereon, where at least a portion of a computer program 620 may be loadable (e.g., into a processor) for implementing the functionality of the examples described herein when executed by the processing circuitry 602. The processing circuitry 602 may serve as a controller or control system for the computer system 600 that is to implement the functionality described herein.

[0097] The computer system 600 may include an input device interface 622 configured to receive input and selections to be communicated to the computer system 600 when executing instructions, such as from a keyboard, mouse, touch-sensitive surface, etc. Such input devices may be connected to the processing circuitry 602 through the input device interface 622 coupled to the system bus 606 but can be connected through other interfaces, such as a parallel port, an Institute of Electrical and Electronic Engineers (IEEE) 1394 serial port, a Universal Serial Bus (USB) port, an IR interface, and the like. The computer system 600 may include an output device interface 624 configured to forward output, such as to a display, a video display unit (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)). The computer system 600 may include a communications interface 626 suitable for communicating with a network as appropriate or desired.

[0098] The operational actions described in any of the exemplary aspects herein are described to provide examples and discussion. The actions may be performed by hardware components, may be embodied in machine-executable instructions to cause a processor to perform the actions, or may be performed by a combination of hardware and software. Although a specific order of method actions may be shown or described, the order of the actions may differ. In addition, two or more actions may be performed concurrently or with partial concurrence.

[0099] According to certain examples, there is also disclosed: [00100] Example 1 : A computer system (200, 600) for determining a set of capabilities for an autonomously or semi-autonomously controllable vehicle combination (100), the computer system (200, 600) comprising processing circuitry (602) configured to: acquire an initial trajectory for the vehicle combination (100); acquire a reference probability distribution, RPD, (402, 502) for a control parameter for the vehicle combination (100) based on a candidate set of capabilities for the vehicle combination (100); acquire a projected probability distribution, PPD, (404) for the control parameter based on the initial trajectory and the candidate set of capabilities; and determine a set of capabilities for the vehicle combination (100) based on a comparison between the RPD (402, 502) and the PPD (404, 406, 504, 506).

[00101] Example 2: The computer system (200, 600) of example 1, wherein the processing circuitry (602) is configured to acquire a PPD (404, 406, 504, 506) for each of a plurality of candidate sets of capabilities, and determine a set of capabilities having the best fit to the RPD (402, 502) for the control parameter for the vehicle combination (100).

[00102] Example 3: The computer system (200, 600) of example 2, wherein the plurality of candidate sets of capabilities correspond to a plurality of reference temperatures for an operational objective.

[00103] Example 4: The computer system (200, 600) of example 1, wherein the processing circuitry (602) is configured to determine a difference between the RPD (402, 502) and the PPD (404, 406, 504, 506), and update the candidate set of capabilities to reduce the difference. [00104] Example 5: The computer system (200, 600) of any preceding example, wherein the processing circuitry (602) is configured to acquire the RPD (402, 502) and/or the PPD (404, 406, 504, 506) using a kernel density estimation.

[00105] Example 6: The computer system (200, 600) of any preceding example, wherein the control parameter comprises a power, power stress range, power cycle range, power cycle average, speed and/or torque of the vehicle combination (100).

[00106] Example 7: The computer system (200, 600) of any preceding example, wherein the initial trajectory is determined based on hard constraints for the vehicle combination.

[00107] Example 8: The computer system (200, 600) of any preceding example, wherein each set of capabilities comprises capabilities relating to one or more of an electrical machine (120), a battery (130), a set of service brakes (150), or transmission of the vehicle combination (100).

[00108] Example 9: The computer system (200, 600) of any preceding example, wherein the processing circuitry (602) is further configured to provide the determined set of capabilities to a control system (202) configured to determine an updated trajectory for the vehicle combination (100).

[00109] Example 10: The computer system (200, 600) of any preceding example, wherein the processing circuitry (602) is further configured to provide the determined set of capabilities to a control system (204) configured to determine one or more control inputs for the vehicle combination.

[00110] Example 11 : A vehicle (100) comprising the computer system (200, 600) of any preceding example.

[00111] Example 12: A battery electric vehicle combination (100) comprising the computer system (200, 600) of any preceding example.

[00112] Example 13: A computer-implemented method (300) for determining a set of capabilities for an autonomously or semi-autonomously controllable vehicle combination (100), the method (300) comprising: acquiring (302), by processing circuitry (602) of a computer system (200, 600), an initial trajectory for the vehicle combination (100); acquiring (304), by the processing circuitry (602), a reference probability distribution, RPD, (402, 504) for a control parameter for the vehicle combination (100) based on a candidate set of capabilities for the vehicle combination (100) acquiring (306), by the processing circuitry (602), a projected probability distribution, PPD, (404, 406, 504, 506) for the control parameter based on the initial trajectory and the candidate set of capabilities; and determining (308), by the processing circuitry (602), a set of capabilities for the vehicle combination (100) based on a comparison between the RPD (402, 502) and the PPD (404, 406, 504, 506).

[00113] Example 14: The computer-implemented method (300) of example 13, comprising acquiring, by the processing circuitry (602), a PPD (404, 406, 504, 506) for each of a plurality of candidate sets of capabilities, and determining, by the processing circuitry (602), a set of capabilities having the best fit to the RPD (402, 502) for the control parameter for the vehicle combination (100).

[00114] Example 15: The computer-implemented method (300) of example 14, wherein the plurality of candidate sets of capabilities correspond to a plurality of reference temperatures for an operational objective.

[00115] Example 16: The computer-implemented method (300) of example 13, comprising determining, by the processing circuitry (602), a difference between the RPD (402, 502) and the PPD (404, 406, 504, 506), and updating, by the processing circuitry (602), the candidate set of capabilities to reduce the difference. [00116] Example 17: The computer-implemented method (300) of example 13 to 16, comprising acquiring, by the processing circuitry (602), the RPD (402, 502) and/or the PPD (404, 406, 504, 506) using a kernel density estimation.

[00117] Example 18: The computer-implemented method (300) of example 13 to 17, wherein the control parameter comprises a power, power stress range, power cycle range, power cycle average, speed and/or torque of the vehicle combination (100).

[00118] Example 19: The computer-implemented method (300) of example 13 to 18, wherein the initial trajectory is determined based on hard constraints for the vehicle combination (100).

[00119] Example 20: The computer-implemented method (300) of example 13 to 19, wherein each set of capabilities comprises capabilities relating to one or more of an electrical machine (120), a battery (130), a set of service brakes (150), or transmission of the vehicle combination (100).

[00120] Example 21 : The computer-implemented method (300) of example 13 to 20, further comprising providing (310), by the processing circuitry (602), the determined set of capabilities to a control system (202) configured to determine an updated trajectory for the vehicle combination (100).

[00121] Example 22: The computer-implemented method (300) of example 13 to 21, further comprising providing (312), by the processing circuitry (602), the determined set of capabilities to a control system (204) configured to determine one or more control inputs for the vehicle combination (100).

[00122] Example 23: A computer program product comprising program code for performing, when executed by processing circuitry (602), the computer-implemented method (300) of any of examples 13 to 22.

[00123] Example 24: A non-transitory computer-readable storage medium comprising instructions, which when executed by processing circuitry (602), cause the processing circuitry to perform the computer-implemented method (300) of any of examples 13 to 23.

[00124] The terminology used herein is for the purpose of describing particular aspects only and is not intended to be limiting of the disclosure. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items. It will be further understood that the terms "comprises," "comprising," "includes," and/or "including" when used herein specify the presence of stated features, integers, actions, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, actions, steps, operations, elements, components, and/or groups thereof.

[00125] It will be understood that, although the terms first, second, etc., may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element without departing from the scope of the present disclosure.

[00126] Relative terms such as "below" or "above" or "upper" or "lower" or "horizontal" or "vertical" may be used herein to describe a relationship of one element to another element as illustrated in the Figures. It will be understood that these terms and those discussed above are intended to encompass different orientations of the device in addition to the orientation depicted in the Figures. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element, or intervening elements may be present. In contrast, when an element is referred to as being "directly connected" or "directly coupled" to another element, there are no intervening elements present.

[00127] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms used herein should be interpreted as having a meaning consistent with their meaning in the context of this specification and the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

It is to be understood that the present disclosure is not limited to the aspects described above and illustrated in the drawings; rather, the skilled person will recognize that many changes and modifications may be made within the scope of the present disclosure and appended claims. In the drawings and specification, there have been disclosed aspects for purposes of illustration only and not for purposes of limitation, the scope of the disclosure being set forth in the following claims.

Claims

CLAIMS What is claimed is:

1. A computer system (200, 600) for determining a set of capabilities for an autonomously or semi-autonomously controllable vehicle combination (100), the computer system (200, 600) comprising processing circuitry (602) configured to: acquire an initial trajectory for the vehicle combination (100); acquire a reference probability distribution, RPD, (402, 502) for a control parameter for the vehicle combination (100) based on a candidate set of capabilities for the vehicle combination (100); acquire a projected probability distribution, PPD, (404, 406, 504, 506) for the control parameter based on the initial trajectory and the candidate set of capabilities; and determine a set of capabilities for the vehicle combination (100) based on a comparison between the RPD (402, 502) and the PPD (404, 406, 504, 506).

2. The computer system (200, 600) of claim 1, wherein the processing circuitry (602) is configured to acquire a PPD (404, 406, 504, 506) for each of a plurality of candidate sets of capabilities, and determine a set of capabilities having the best fit to the RPD (402, 502) for the control parameter for the vehicle combination (100).

3. The computer system (200, 600) of claim 2, wherein the plurality of candidate sets of capabilities correspond to a plurality of reference temperatures for an operational objective.

4. The computer system (200, 600) of claim 1, wherein the processing circuitry (602) is configured to determine a difference between the RPD (402, 502) and the PPD (404, 406, 504, 506), and update the candidate set of capabilities to reduce the difference.

5. The computer system (200, 600) of any preceding claim, wherein the processing circuitry (602) is configured to acquire the RPD (402, 502) and/or the PPD (404, 406, 504, 506) using a kernel density estimation.

6. The computer system (200, 600) of any preceding claim, wherein the control parameter comprises a power, power stress range, power cycle range, power cycle average, speed and/or torque of the vehicle combination (100).

7. The computer system (200, 600) of any preceding claim, wherein the initial trajectory is determined based on hard constraints for the vehicle combination.

8. The computer system (200, 600) of any preceding claim, wherein each set of capabilities comprises capabilities relating to one or more of an electrical machine (120), a battery (130), a set of service brakes (150), or a transmission of the vehicle combination (100).

9. The computer system (200, 600) of any preceding claim, wherein the processing circuitry (602) is further configured to provide the determined set of capabilities to a control system (202) configured to determine an updated trajectory for the vehicle combination (100).

10. The computer system (200, 600) of any preceding claim, wherein the processing circuitry (602) is further configured to provide the determined set of capabilities to a control system (204) configured to determine one or more control inputs for the vehicle combination (100).

11. A vehicle (100) comprising the computer system (200, 600) of any preceding claim.

12. A battery electric vehicle combination (100) comprising the computer system (200, 600) of any preceding claim.

13. A computer-implemented method (300) for determining a set of capabilities for an autonomously or semi-autonomously controllable vehicle combination (100), the method (300) comprising: acquiring (302), by processing circuitry (602) of a computer system (200, 600), an initial trajectory for the vehicle combination (100); acquiring (304), by the processing circuitry (602), a reference probability distribution, RPD, (402, 502) for a control parameter for the vehicle combination (100) based on a candidate set of capabilities for the vehicle combination (100) acquiring (306), by the processing circuitry (602), a projected probability distribution, PPD, (404, 406, 504, 506) for the control parameter based on the initial trajectory and the candidate set of capabilities; and determining (308), by the processing circuitry (602), a set of capabilities for the vehicle combination (100) based on a comparison between the RPD (402, 502) and the PPD (404, 406, 504, 506).

14. A computer program product comprising program code for performing, when executed by processing circuitry (602), the computer-implemented method (300) of claim 13.

15. A non-transitory computer-readable storage medium comprising instructions, which when executed by processing circuitry (602), cause the processing circuitry to perform the computer-implemented method (300) of claim 13.