DE102024204701A1 - SYSTEM FOR CONTROLLING LATERAL MOVEMENT OF AN AUTONOMOUS MOTOR VEHICLE - Google Patents

Abstract

Disclosed is a system for controlling lateral movement of an autonomous vehicle (101), comprising: a trajectory planner (102) configured to generate a target trajectory for the vehicle (101); and a trajectory controller (104) configured to receive the target trajectory from the trajectory planner (102) and generate as an output a steering control signal for controlling lateral movement of the vehicle (101). The trajectory controller (104) comprises a control circuit (104a), the control circuit (104) comprising an integrated adaptive PID neural network controller (124). The integrated adaptive PID neural network controller (124) comprises: a PID controller (116) receiving an input signal dependent on a target lane position parameter of the target trajectory and configured to minimize an error value indicative of the difference between the actual trajectory of the vehicle (101) and the input signal dependent on the target lane position parameter, the PID controller (116) further configured to receive an input signal dependent on a target heading angle parameter of the target trajectory and configured to minimize an error value indicative of the difference between the actual trajectory of the vehicle (101) and the input signal dependent on the target heading angle parameter; and a neural network (118) configured to determine the P-gain, I-gain, and D-gain terms used by the PID controller (116). The integrated adaptive PID neural network control (124) is so configured to use the P and I gain terms provided by the neural network (118) to control the lane position of the vehicle (101) and the D gain term provided by the neural network (118) to control the heading angle of the vehicle (101), whereby the P, I and D gain terms used by the PID controller (116) are provided by the same neural network (118).

Description

The present application relates to a system for controlling lateral movement of an autonomous motor vehicle and an autonomous vehicle comprising the system for controlling lateral movement.

To control an autonomous vehicle so that it can drive with reduced or no user input, a target trajectory is determined. The target trajectory may be determined by a planner function that processes images of the vehicle's location and environment along with other sensor information available to the vehicle to calculate a target trajectory. The target trajectory is the desired trajectory of the vehicle so that it follows the road or performs a desired maneuver, such as changing lanes, turning onto another road, or taking evasive action to avoid a collision.

Once a target trajectory is determined for the vehicle, the steering of the vehicle, along with the other vehicle devices, must be controlled to maintain the trajectory. Therefore, a lateral movement control system is provided that can implement a feedback loop in which the current trajectory of the vehicle is compared with the target trajectory. A control signal is provided to the vehicle steering system to minimize the difference between them in the vehicle's lateral movement maneuvers.

Known motion control systems may use feedback loops based on fixed parameters that may become suboptimal for controlling the vehicle over time. This may result in the target trajectory being inaccurately followed or it may take longer to reach the target trajectory. Adjusting the vehicle's steering angle to achieve the desired lateral trajectory or the actual steering path of the vehicle is challenging as it is subject to a number of variable or unknown influences such as road contact, vehicle load, vehicle tires, etc.

The present application relates to a lateral motion control system for autonomous motor vehicles, which aims to improve the limitations of the known control systems described above.

• einen Trajektorieplaner, der so konfiguriert ist, dass er eine Zieltrajektorie für das Fahrzeug erzeugt; und
• eine Trajektoriesteuerung, die so konfiguriert ist, dass sie die Zieltrajektorie vom Trajektorieplaner empfängt und als Ausgabe ein Lenksteuersignal zur Steuerung der Seitenbewegung des Fahrzeugs erzeugt,
• wobei die Trajektoriesteuerung eine Steuerschaltung umfasst, wobei die Steuerschaltung eine oder mehrere adaptive Neuronalnetzsteuerungen umfasst, die jeweils umfassen:
  • eine Rückkopplungsschleifensteuerung (z.B. vom PID-Typ), die ein Eingabesignal empfängt, das von einem Parameter der Zieltrajektorie abhängt, und die so konfiguriert ist, dass sie einen Fehlerwert, der die Differenz zwischen der tatsächlichen Trajektorie des Fahrzeugs und dem Eingabesignal angibt, auf Grundlage eines P-Verstärkungs- und/oder I-Verstärkungs- und/oder D-Verstärkungsterms minimiert; und
  • ein neuronales Netz, das so konfiguriert ist, dass es einen P-Verstärkungs- und/oder I-Verstärkungs- und/oder D-Verstärkungsterm bestimmt, die von der Rückkopplungsschleifensteuerung verwendet werden.

In a first aspect, the present application provides a system for controlling the lateral movement of an autonomous vehicle, comprising:

• a trajectory planner configured to generate a target trajectory for the vehicle; and
• a trajectory controller configured to receive the target trajectory from the trajectory planner and to generate as an output a steering control signal for controlling the lateral movement of the vehicle,
• wherein the trajectory controller comprises a control circuit, the control circuit comprising one or more adaptive neural network controllers each comprising:
  • a feedback loop controller (eg, PID type) receiving an input signal dependent on a parameter of the target trajectory and configured to minimize an error value indicative of the difference between the actual trajectory of the vehicle and the input signal based on a P-gain and/or I-gain and/or D-gain term; and
  • a neural network configured to determine a P-gain and/or I-gain and/or D-gain term used by the feedback loop controller.

By providing gain terms calculated by a neural network, the operation of the feedback loop control can be adjusted or tuned online and in real time while the motion control system is operating. This is advantageous compared to many existing control systems that use fixed gain terms and can improve the accuracy and effectiveness of vehicle control.

The feedback loop controller can use all three gain terms P, I and D and thus be a PID controller. Alternatively, the feedback loop controller can use only one or two of the gain terms and thus be a P, I, D, PD or PI controller.

The target trajectory may include one or more target trajectory parameters and/or variables. The target trajectory parameters and/or variables may include one or more target curves, a target lane position, and a target heading angle.

The trajectory controller may receive as input one or more of the target trajectory parameters or signals dependent thereon. The trajectory controller may also receive one or more signals related to the current trajectory of the vehicle.

The one or more adaptive neural network controllers for lateral trajectory control may include an adaptive neural network controller for lane position configured to perform P and/or I and/or D control for the lane position of the trajectory of the vehicle.

The one or more adaptive neural network controllers may include an adaptive neural network heading angle controller configured to perform P and/or I and/or D control of the heading angle of the trajectory of the vehicle.

The lane position adaptive neural network controller may be configured to receive as input a target lane position parameter and generate an output control signal. The heading angle adaptive neural network controller may be configured to receive as input a sum of the lane position adaptive neural network controller output control signal and a target heading angle parameter. This allows the lane position and heading angle controllers to be connected in series.

The trajectory controller may further comprise a trajectory PID controller configured to provide P and/or I and/or D control of the trajectory of the vehicle. The trajectory controller may use P, I and/or D gain terms that are predetermined and/or dependent on the vehicle motion variable(s). The trajectory PID controller may use P, I and D gain terms that are designed to be dependent on the vehicle motion variable(s), such as vehicle speed and trajectory measurements. The trajectory controller may use gain terms derived from a lookup table of predetermined values or use a fixed functional relationship between gain values and vehicle motion variables. The gain values are therefore predetermined in the sense that there is a fixed relationship between a current vehicle motion variable and the P, I and D gain term(s). Therefore, the curve shape control may not use a neural network to provide the gain terms.

Alternatively, the waveform controller may be an adaptive neural network controller configured to provide the required P-gain, I-gain, and D-gain terms.

The curve control may be configured to receive a target curve parameter as input and produce a curve control signal as output. The trajectory control may be configured to determine the sum of the curve control signal and the output of the adaptive neural network heading angle control (when connected in series with the lane position control) to provide the steering control signal output of the trajectory control. This allows the curve control to be placed in parallel with the other two controllers. This allows the curve control to be included earlier in the steering calculation and improves the accuracy of the steering control signal.

Each of the neural networks in the trajectory controller may include an input layer of neurons, at least one hidden layer of neurons, and an output layer having at least one output neuron. Each neural network may receive an input neural neuron, the error value associated with a respective trajectory parameter, and the control signal output by the respective controller, and output the gain values at respective node values within the hidden layer of the neural network.

Each of the neural networks may be further configured to receive at least one environmental variable as a feedforward term.

• - die Geschwindigkeit des Fahrzeugs für den größten Teil der Fahrzeugbewegungssteuerung,
• - Straßen-/Verkehrsmessungen wie Kurvenverlauf, Fahrtrichtung, Geschwindigkeitsbegrenzung usw.
• - Fahrzeugbeschleunigung/Reaktionskraft
• - Motordrehzahl/Drehwinkel für die Strom-/Drehmomentregelung
• - Lenkmoment oder -winkel
• - Fahrzeugblinkerzustand, z.B. Abbiegen angezeigt oder Abbiegen nicht angezeigt

The environmental variable may include at least one of the following variables commonly found in a vehicle motion control system:

• - the speed of the vehicle for most of the vehicle movement control,
• - Road/traffic measurements such as curves, direction of travel, speed limits, etc.
• - Vehicle acceleration/reaction force
• - Motor speed/angle of rotation for current/torque control
• - steering torque or angle
• - Vehicle indicator status, e.g. turning indicated or turning not indicated

During use of the control system, the weights of the neural network(s) may be updated by a gradient descent backpropagation method each time a new set of input values is fed to the neural network, and the updated Weights are used together with the input values to update the neurons.

In a second aspect, the present application provides a vehicle comprising the motion control system of the first aspect.

• einen Trajektorieplaner, der so konfiguriert ist, dass er eine Zieltrajektorie für das Fahrzeug erzeugt; und
• eine Trajektoriesteuerung, die so konfiguriert ist, dass sie die Zieltrajektorie vom Trajektorieplaner empfängt und als Ausgabe ein Lenksteuersignal zur Steuerung der Seitenbewegung des Fahrzeugs erzeugt;
• wobei die Trajektoriesteuerung eine Steuerschaltung umfasst, wobei die Steuerschaltung eine integrierte adaptive PID-Neuronalnetzsteuerung umfasst, die Folgendes umfasst:
  • eine PID-Steuerung, die ein von einem Zielfahrspurpositionsparameter der Zieltrajektorie abhängiges Eingabesignal empfängt und so eingerichtet ist, dass sie einen Fehlerwert minimiert, der die Differenz zwischen der tatsächlichen Trajektorie des Fahrzeugs und dem vom Zielfahrspurpositionsparameter abhängigen Eingabesignal angibt, wobei die PID-Steuerung ferner so eingerichtet ist, dass sie ein von einem Zielkurswinkelparameter der Zieltrajektorie abhängiges Eingabesignal empfängt, und so eingerichtet ist, dass sie einen Fehlerwert minimiert, der die Differenz zwischen der tatsächlichen Trajektorie des Fahrzeugs und dem vom Zielkurswinkelparameter abhängigen Eingabesignal angibt; und
  • ein neuronales Netz, das so konfiguriert ist, dass es die P-Verstärkungs-, I-Verstärkungs- und D-Verstärkungsterme bestimmt, die von der PID-Steuerung verwendet werden,
  • wobei die integrierte adaptive PID-Neuronalnetzsteuerung so konfiguriert ist, dass sie die von dem neuronalen Netz bereitgestellten P- und I-Verstärkungsterme verwendet, um die Fahrspurposition des Fahrzeugs zu steuern, und den von dem neuronalen Netz bereitgestellten D-Verstärkungsterm, um den Kurswinkel des Fahrzeugs zu steuern, wodurch die von der PID-Steuerung verwendeten P-, I- und D-Verstärkungsterme von demselben neuronalen Netz bereitgestellt werden.

According to a third aspect, there is provided a system for controlling lateral movement of an autonomous vehicle, comprising:

• a trajectory planner configured to generate a target trajectory for the vehicle; and
• a trajectory controller configured to receive the target trajectory from the trajectory planner and to produce as an output a steering control signal for controlling lateral movement of the vehicle;
• wherein the trajectory controller comprises a control circuit, the control circuit comprising an integrated adaptive PID neural network controller comprising:
  • a PID controller receiving an input signal dependent on a target lane position parameter of the target trajectory and configured to minimize an error value indicative of the difference between the actual trajectory of the vehicle and the input signal dependent on the target lane position parameter, the PID controller further configured to receive an input signal dependent on a target heading angle parameter of the target trajectory and configured to minimize an error value indicative of the difference between the actual trajectory of the vehicle and the input signal dependent on the target heading angle parameter; and
  • a neural network configured to determine the P-gain, I-gain and D-gain terms used by the PID controller,
  • wherein the integrated adaptive PID neural network controller is configured to use the P and I gain terms provided by the neural network to control the lane position of the vehicle and the D gain term provided by the neural network to control the heading angle of the vehicle, whereby the P, I and D gain terms used by the PID controller are provided by the same neural network.

By using a single PID controller and a single neural network to control both lane position and heading angle, the efficiency of the control system can be improved. This also allows the number of control steps and the number of components required to be reduced compared to using separate dedicated PID controllers and/or neural networks.

The trajectory controller may further comprise a curve control configured to perform P and/or I and/or D control of the curve of the trajectory of the vehicle.

The curve control may use P, I and/or D gain terms that are predetermined and/or dependent on the vehicle motion variable(s). The curve control may therefore not use a neural network to provide its gain terms. The curve PID control may use P, I and D gain terms that are designed to be dependent on the vehicle motion variable(s), such as vehicle speed and heading curve measurements. The curve control may use gain terms derived from a lookup table of predetermined values or use a fixed functional relationship between gain values and vehicle motion variables. The gain values are therefore predetermined in the sense that there is a fixed relationship between a current vehicle motion variable and the P, I and D gain term(s).

Alternatively, the waveform controller may be an adaptive PID neural network controller configured to provide its required P-gain, I-gain, and D-gain terms.

The trajectory controller may be configured to receive a target trajectory parameter as input and produce a trajectory control signal as output. The trajectory controller may be configured to determine the sum of the trajectory control signal and the output of the integrated adaptive PID neural network controller to provide the steering control signal output of the trajectory controller. This allows the trajectory controller and the integrated controller to be connected in parallel. This allows the trajectory controller to be included earlier in the control calculation.

The neural network(s) may have an input layer of neurons, at least one hidden layer of neurons and an output layer with at least one output neuron. The neural network or networks may comprise a feedforward neural network which outputs the error value associated with the input trajectory parameter in the input layer of the input neurons and the gain values at respective node values within the hidden layer of the neural network from the integrated adaptive neural network.

The neural network(s) may further be configured to receive at least one environmental variable as a feedforward term.

• - die Geschwindigkeit des Fahrzeugs für den größten Teil der Fahrzeugbewegungssteuerung,
• - Straßen-/Verkehrsmessungen wie Kurvenverlauf, Fahrtrichtung, Geschwindigkeitsbegrenzung usw.
• - Fahrzeugbeschleunigung/Reaktionskraft
• - Motordrehzahl/Drehwinkel für die Strom-/Drehmomentregelung
• - Lenkmoment oder -winkel
• - Fahrzeugblinkerzustand, z.B. Abbiegen angezeigt oder Abbiegen nicht angezeigt

The environmental variable may include at least one of the following variables commonly found in a vehicle motion control system:

• - the speed of the vehicle for most of the vehicle movement control,
• - Road/traffic measurements such as curves, direction of travel, speed limits, etc.
• - Vehicle acceleration/reaction force
• - Motor speed/angle of rotation for current/torque control
• - steering torque or angle
• - Vehicle indicator status, e.g. turning indicated or turning not indicated

During use of the control system, the weights of the neural network(s) may be updated by a gradient descent backpropagation method each time a new set of input values is fed to the neural network, and the updated weights are used together with the input values to update the neurons.

According to a fourth aspect there is provided a vehicle comprising the motion control system according to any one of the preceding claims.

It will be understood by a person skilled in the art that a feature described in relation to one of the above aspects may also be applied to any other aspect, unless they are mutually exclusive.

• 1 zeigt eine schematische Darstellung eines Systems zur Steuerung seitlicher Bewegung, das in ein autonomes Fahrzeug
• 2 zeigt eine schematische Darstellung einer Trajektoriesteuerung des in 1 gezeigten Systems zur Steuerung seitlicher Bewegung;
• 3 veranschaulicht die Kurvenverlaufs-, Fahrspurpositions- und Kurswinkelparameter der Trajektorie des autonomen Fahrzeugs;
• 4 zeigt eine schematische Darstellung einer allgemeinen adaptiven PID-Neuronalnetzsteuerung, die in der Trajektoriesteuerung des Bewegungssteuersystems vorgesehen ist;
• 5 ist eine Darstellung der Neuronenverbindungen des neuronalen Netzes der adaptiven PID-Neuronalnetzsteuerung;
• 6 zeigt eine schematische Darstellung eines weiteren Beispiels einer Trajektoriesteuerung des Systems zur Steuerung seitlicher Bewegung aus 1, bei dem eine Kurvenverlaufssteuerung parallel zu einer Fahrspurpositionssteuerung und einer Kurswinkelsteuerung geschaltet ist;
• 7 zeigt eine schematische Darstellung eines weiteren Beispiels einer Trajektoriesteuerung des Systems zur Steuerung seitlicher Bewegung aus 1, bei dem die Kurvenverlaufssteuerung mit der Fahrspurpositionssteuerung und der Kurswinkelsteuerung in Reihe geschaltet ist;
• 8 zeigt eine schematische Darstellung eines weiteren Beispiels einer Trajektoriesteuerung des Systems zur Steuerung seitlicher Bewegung aus 1, bei dem eine Kurvenverlaufssteuerung parallel zu einer integrierten adaptiven Neuronalnetzsteuerung für die Fahrspurposition und den Kurswinkel geschaltet ist; und
• 9 zeigt eine schematische Darstellung eines weiteren Beispiels einer Trajektoriesteuerung des Systems zur Steuerung seitlicher Bewegung aus 1, bei dem eine Kurvenverlaufssteuerung mit der integrierten adaptiven Neuronalnetzsteuerung für die Fahrspurposition und den Kurswinkel in Reihe geschaltet ist.

Embodiments of the invention will now be described by way of example only and with reference to the accompanying drawings:

• 1 shows a schematic representation of a system for controlling lateral movement that can be integrated into an autonomous vehicle
• 2 shows a schematic representation of a trajectory control of the 1 shown system for controlling lateral movement;
• 3 illustrates the curve, lane position and heading angle parameters of the autonomous vehicle’s trajectory;
• 4 shows a schematic representation of a general adaptive PID neural network controller provided in the trajectory control of the motion control system;
• 5 is a representation of the neuron connections of the neural network of the adaptive PID neural network control;
• 6 shows a schematic representation of another example of a trajectory control of the system for controlling lateral movement from 1 , in which a curve control is connected in parallel to a lane position control and a heading angle control;
• 7 shows a schematic representation of another example of a trajectory control of the system for controlling lateral movement from 1 in which the curve control is connected in series with the lane position control and the heading angle control;
• 8 shows a schematic representation of another example of a trajectory control of the system for controlling lateral movement from 1 , in which a curve control is connected in parallel to an integrated adaptive neural network control for the lane position and the heading angle; and
• 9 shows a schematic representation of another example of a trajectory control of the system for controlling lateral movement from 1 , in which a curve control is connected in series with the integrated adaptive neural network control for the lane position and the course angle.

1 shows a schematic representation of a lateral movement control system 100 installed in an autonomous vehicle 101. The vehicle may be a motor vehicle such as a car, truck, van or the like. The vehicle 101 may be a fully autonomous vehicle that is controlled without any user input to control its movement, or the vehicle 101 may be a semi-autonomous vehicle in which at least the steering of the vehicle is controlled automatically.

The motion control system 100 generally includes a trajectory planner 102, a trajectory controller 104, and a steering system 106. The trajectory planner 102 is configured to generate a target trajectory for the vehicle 101. The target trajectory may represent a route or a portion of a route to a planned destination of a trip of the vehicle. The target trajectory may be determined by the trajectory planner 102 based on sensing information provided by one or more sensors 110. The sensors 110 may include a video camera configured to process images of the surroundings of the vehicle 101. Based on such images, the trajectory planner 102 may calculate an appropriate trajectory for the vehicle 101 so that it travels autonomously on a road and responds to other vehicles or road conditions. The sensors 110 may be any other suitable sensors configured to provide information from which the vehicle trajectory can be calculated, such as vehicle speed, acceleration, etc. The trajectory planner 102 may also have access to navigation information (e.g., from a satellite-based navigation system) to determine the target trajectory.

The motion control system 100 further includes a trajectory controller 104 configured to receive the target trajectory from the trajectory planner 102 and that provides an output signal including a steering control signal (δ _{s_tgt} ). The steering control signal is generated by the trajectory controller 104 to control the lateral trajectory of the vehicle 101 to follow the target trajectory. The trajectory controller 104 outputs the steering control signal δ _{s_tgt} to the and may include a steering actuation system. The steering system may include, for example, electric power steering (EPS) or steer-by-wire (SbW) steering. The trajectory controller 104 may pass the steering control signal to the steering control system, which provides an output signal to actuate a motor controller of the vehicle steering system 106. The vehicle steering system may include an electric steering system in which an electric motor applies torque to a portion of the vehicle steering (e.g., a rack) to steer or adjust the angle of the wheels of the vehicle 101.

An embodiment of the trajectory control 104 for controlling lateral movement of the vehicle is shown in 2 The trajectory controller 104 is configured to receive a target trajectory consisting of three target trajectory parameters - a target curve path (CV), a target track position (LP), and a target heading angle (CA). These parameters are described with reference to 3 defined.

3 shows the vehicle while driving on a lane of a road or highway defined by a lane boundary labeled 111. The curve of the trajectory refers to the curve of the road that the vehicle follows, as shown in 3 shown. The curve shape can be defined as the reciprocal of the radius of a circle that best approximates the curve shape of the trajectory at every point along its length.

Lane position refers to the extent to which the vehicle is offset from the centerline of the lane or roadway on which it is traveling. As in 3 As can be seen, the lane position is determined by a lateral distance between the center line of the lane (in 3 marked with X) and the centre line of vehicle 101 (in 3 marked with Y).

The heading angle refers to the direction in which the vehicle is traveling on the road. The heading angle can be defined as the angle between the intended direction of travel of the vehicle and a reference direction, e.g. north.

As in 2 As shown, the trajectory controller 104 comprises three adaptive neural network (NN) controllers, each of which is connected to one of the 3 defined trajectory parameters. The trajectory controller 104 includes an adaptive curve NN controller 110, an adaptive lane position NN controller 112, and an adaptive heading angle NN controller 114. The curve controller 110 is configured to control the curve of the trajectory of the vehicle. It receives the target curve from the trajectory planner and provides as output a curve control signal (δ _{s_cv} ). The lane position controller 112 is configured to control the lane position of the trajectory of the vehicle. It receives the target lane position from the trajectory planner and provides as output a lane position control signal (δ _{s_po} ). The heading angle controller 114 is configured to control the heading angle of the trajectory of the vehicle. It receives the target heading angle from the trajectory planner and provides as output a heading angle control signal (δ _{s_ca} ). The trajectory controller 104 is configured to determine (through a summing unit 115) the sum of the control signals (δ _{s_cv} , δ _{s_po} , δ _{s_ca} ) to provide the steering control signal δ _{s_tgt} which is supplied to the steering system 106 as described above.

Each of the 2 The adaptive NN controls shown are configured to provide a Error value that indicates the difference between the actual trajectory of the vehicle and the input target trajectory parameter. By minimizing the error value, the vehicle is controlled to maintain a trajectory that corresponds to a minimum deviation from the target trajectory generated by the trajectory planner 102. Each of the 2 The adaptive NN controllers 110, 112, 114 shown (and any other adaptive or non-adaptive controller described herein) receive a general measurement input y. This reflects the current measurement of the trajectory parameter(s) used as input to the feedback loop implemented by the controller. The input y may include measurements of lane position, heading angle, and/or curve progression.

Each of the above adaptive NN controllers 110, 112, 114 is a PID controller configured to control its I and/or D gain term. Thus, "PID controller" may mean a P, I, D, PD, PI or PID controller. In the 2 In the embodiment shown, the turn control 110 and the heading angle control 114 are PD controllers that use the P and D gain terms. The lane position control is a PID controller that uses all three gain terms. In other embodiments, the lane position control 112 may not use the D gain term, but may use the P and I gain terms because the D gain term may be noisy in position measurement and processing. Each of the controllers 110, 112, 114 described herein may be a PID controller that uses a P and/or an I and/or a D gain term.

The adaptive NN controllers each comprise a control circuit 104a comprising a PID controller 116 connected to a corresponding neural network 118, as shown in 4 In the example described presently, the trajectory controller 104 includes a turn control configured to receive an input dependent on the target turn, the turn control coupled to a turn neural network configured to provide P, I, and D gain values as needed. The trajectory controller 104 further includes a lane position controller configured to receive an input dependent on the target lane position, the lane position controller coupled to a lane position neural network. The trajectory controller 104 further includes a heading angle controller configured to receive an input dependent on the target heading angle, the heading angle controller coupled to a lane position neural network.

Each of the PID controllers 116 generates an output signal u _c (e.g., the control signals δ _{s_cv} , δ _{s_po} , δ _{s_ca} ) as the sum of one or more different terms - a proportional term P, an integral term I, and a differential term D. Each of these terms is calculated by multiplying an error signal e _y by a corresponding gain term K _p , K _{i ,} and K _d . The error signal is the difference between a target value of a described target curve, target lane position, or target heading angle) and an actual (current) value of the respective trajectory parameter.

The gain terms of the PID controller 116 are each calculated by the neural network 118. In the present example, each of the P, I and D gain terms required for the respective controller is calculated by the neural network, but in other embodiments one or more of them may be calculated in this way. The gain terms may be determined and updated by the neural network during use of the control system 100 and stored in a memory of the control circuit 115 so that they are available to the controller 116. The P, I and D gain terms are therefore recalculated and updated at regular intervals during operation of the motion controller and can therefore be continuously adjusted over time to optimize the performance of the PID controller. This is an advantage over using fixed, predetermined values for the PID gain terms, which cannot adjust in the same way.

The neural network 118 receives as inputs the error signal e _y (in 5 denoted by "e" as described later), the control signal output u _{c ,} and one or more environment variables U. Each of these variables is provided as a function of the time step k of the optimization processing of the neural network. The signals input to the neural network may be updated at regular intervals, and between each update, the neuron values may be updated in response before updated values are input to the neural network.

• - die Geschwindigkeit des Fahrzeugs,
• - den Fahrspurkurvenverlauf
• - Straßen-/Verkehrsmessungen wie Fahrspurkurvenverlauf und Geschwindigkeitsbegrenzung usw.
• - Fahrzeugbeschleunigung/Reaktionskraft
• - Motordrehzahl/Drehwinkel für die Strom-/Drehmomentregelung
• - Lenkmoment oder -winkel
• - Fahrzeugblinkerzustand, z.B. Abbiegen angezeigt oder Abbiegen nicht angezeigt.

The environmental variable provided as input to the neural network may be a variable that specifies a parameter that is not used in the PID controller control loop. The environmental variable may be at least one of the following commonly used in a vehicle motion Variables occurring in the supply control system include:

• - the speed of the vehicle,
• - the lane curve
• - Road/traffic measurements such as lane curve and speed limit etc.
• - Vehicle acceleration/reaction force
• - Motor speed/angle of rotation for current/torque control
• - steering torque or angle
• - Vehicle indicator status, e.g. turn indicated or turn not indicated.

Each of the environmental variables will change during operation of the vehicle and the provision of the at least one additional variable at the input point of the neural network allows further adaptation to the control of the lateral movement so that the error value can be better minimized according to the environmental conditions changing during operation. It will be understood by one skilled in the art that this list is not exhaustive and that other variables may also be used within the scope of the invention. In other embodiments, the environmental parameter may not be used at all.

The neural network 118 comprises a set of neurons 120 as in 5 . The neurons include an input layer of neurons 120a, a hidden layer of neurons 120b, and an output layer of neurons 120c. The neurons 120 are arranged in a network of connections, with each connection providing the output of one neuron as input to another neuron. Each connection is assigned a weight representing its relative importance. The propagation function calculates the input to a neuron (activation function) from the outputs of its predecessor neurons and their connections as a weighted sum.

The neural network of 5 is a feedforward network with one hidden layer. The neural network is configured to perform gradient descent backpropagation learning to provide the P-gain, I-gain, and D-gain terms used by the respective PID controller. The neural network in this example is a single hidden layer neural network, where the hidden layer has three neurons and each defines a controller. In the input layer 120a, the neural network receives a vector X consisting of the error signal e at the time steps k, k-1, k-2... at which the neural network operates, the environmental parameter U, and the PID output control signal u _c . The number of previous time steps the neural network uses may depend on the type of neural network used. The output of the neural network is the required PID gains K _p , K _i , K _d and the control signal u _c . In some embodiments, the output of the neural network may not include the control signal u _c . The control signal u _c may be provided as an output of the neural network in the embodiment described herein so that it can be used directly as a PID control output. For example, the lateral motion control system 100 of the present application may be part of a larger general motion control system whose other components may utilize the output of the neural network with or without u _c .

• - Aktualisieren der Werte des Eingabevektors X;
• - Aktualisieren der Werte der PID-Verstärkungen K_p, K_i, K_d und des Steuersignals u_c auf Grundlage einer Neuronenpunktberechnung aus der Eingabe X und den Gewichtungsverstärkungen W;
• - Aktualisieren der Lernrate für das GDBP-Schema; und
• - Aktualisieren der Werte der Gewichtungen W mit dem GDBP-Schema durch Kombinieren des Eingabevektors X und der PID-Verstärkungszustände.

The neural network of the present example is configured to perform a gradient descent backpropagation (GDBP) scheme to determine the linear combination weights between neurons. At each time step (k), the controller is configured to perform the following steps:

• - Updating the values of the input vector X;
• - updating the values of the PID gains K _p , K _i , K _d and the control signal u _c based on a neuron point calculation from the input X and the weighting gains W;
• - Updating the learning rate for the GDBP scheme; and
• - Updating the values of the weights W with the GDBP scheme by combining the input vector X and the PID gain states.

It will be understood by one skilled in the art that the type of neural network described in the present application is only a preferred example. In other embodiments, other types of neural networks or neural network optimization or processing algorithms may be used.

In the 2 In the example of the trajectory control 104 shown, an adaptive NN control is provided for each of the respective parameters of the target trajectory. In other embodiments, however, this may not be the case, so that an adaptive NN control is only provided for one or more of the target trajectory parameter feedback In such examples, a PID control similar to that in 4 shown without the presence of a neural network. Instead, the values of the gain terms used by such a PID controller are predetermined and stored in memory so that they are accessible to the controller. The gain terms in this case remain constant during operation of the motion control system 100. The gain terms may additionally or alternatively be dependent on one or more vehicle motion variables. For example, the gain terms may be obtained from a lookup table with predetermined values based on a vehicle motion variable (e.g., vehicle speed) or based on a predetermined functional relationship between the gain terms and vehicle speed.

6 shows an embodiment of the trajectory control 104 in which only the lane position and the course angle are provided with an adaptive NN control, while the curve control is carried out with a non-adaptive control without a neural network, which provides periodically updated gain values.

In the 6 In the example shown, the trajectory control 104 comprises an adaptive lane position NN control 112, which operates similarly to 2 described. The lane position controller 112 performs an adaptive control with an error signal determined by the difference between the target lane position P _LAC provided by the trajectory planner 102 and the current or actual lane position value y. The gain terms used by the lane position controller 112 are provided by a lane position neural network as described above. The lane position controller provides an output δ _{fb_p} (ie, a The trajectory controller 104 from 6 further comprises an adaptive heading angle NN controller 114. The heading angle controller 114 is configured to receive as input a sum of the output of the lane position controller 112 (δ _{fb_p} ) and a target heading angle parameter CA _LAC . The sum is calculated by a first computing unit 115a. The heading angle controller 114 then performs adaptive control with an error signal determined by the difference between the target heading angle provided by the trajectory planner 102 and a corresponding current or actual value y of the heading angle parameter. The gain terms used by the heading angle controller 114 are similarly provided by a heading angle neural network as described above. The heading angle controller 114 then provides an output signal δ _fb (i.e., a lane position control signal).

The adaptive NN lane position and heading angle controllers 112, 114 therefore operate in series with each other, with the output of the lane position controller 112 being summed with the target heading angle and then provided as input to the heading angle controller 114.

The trajectory control 104 of the 6 The embodiment shown further includes a curve controller 110'. The curve controller is not equipped with a neural network, but operates with constant values for the required P, I and D gains that do not change during use of the motion control system. The P, I and D gain values may be preset before the first use of the motion control system, but otherwise remain constant during subsequent use. The P, I and D terms may also be dependent on one or more vehicle motion variables as described above. For example, they may be determined from a fixed relationship between one or more motion variables and the gain values defined by a look-up table or a fixed functional relationship. The curve controller receives as input a target curve CV _tgt of the trajectory and performs control using an error signal input by the difference between the target curve and curve controller 110' (in 7 indicated by the parameter y). The waveform controller 110' is configured to generate an output signal δ _ff (ie, an output waveform control signal).

To generate a final steering control signal, the trajectory controller includes a second summing unit 115b configured to determine the sum of the output of the curve control 110' δ _ff and the output of the heading angle control 114 δ _fb to provide the output steering control signal δ _{f_tgt} as shown in 6 The output steering control signal δ _{f_tgt} can then be provided to the steering system 106 as described above.

The curve control 110' in the 6 The embodiment shown operates in parallel with the lane position control 112 and the heading angle control 114. This may be preferred because it allows the curve control to be included earlier in the calculation of the control signal output by the trajectory control 104. In an alternative embodiment shown in 7 As shown, the controls for the lane position, the course angle and the curve course are each connected in series. In the embodiment of 7 the lane position control 112 and the course angle control 114 remain opposite 7 unchanged and output a control signal CV _{tgt_fb} . In this embodiment, however, the output of the curve controller 114 is summed with the target curve CV _tgt by a second summing unit 115b, the result being provided to the curve controller 110'. The curve controller 110' is again a non-adaptive PID controller without a neural network, similar to the embodiment in 7 . The output system of the curve control 110' provides the final steering control signal δ _{f_tgt} from the trajectory control 104.

The 8 and 9 show further embodiments of a trajectory control 104, which is part of the 1 shown motion control system 100. In the embodiments of the 8 and 9 is an integrated adaptive PID neural network (NN) controller 124 for the controller 124 is used instead of the 6 and 7 The integrated adaptive PID NN controller 124 comprises an integrated PID controller which is similar to the one shown in 4 shown control 116, as well as a neural network corresponding to the one shown in 4 to provide the gain terms P, I and D. In both embodiments of the 8 and 9 the trajectory controller 104 further comprises a non-adaptive curve controller 110' which does not have a neural network for providing the gain terms P, I and D, which are instead fixed and/or dependent on one or more vehicle motion variables, as described above. The curve controller 110' may be operated in a similar manner as described above in connection with the 7 and 8 described.

The integrated controller 124 is configured to receive as input the target lane position parameter P _LAC from the trajectory planner 102. The integrated controller 124 is configured to perform adaptive control with the lane position error (ΔP) and the heading angle error (ΔCA). The integrated PID controller 124 is configured to receive an input signal dependent on a target lane position parameter of the target trajectory and is configured to minimize an error value indicative of the difference between the actual trajectory of the vehicle and the input signal. The integrated PID controller 124 is further configured to receive an input signal dependent on a target heading angle parameter of the target trajectory and is configured to minimize an error value indicative of the difference between the actual trajectory of the vehicle and the input signal.

The integrated controller 124 is configured similarly to the adaptive PID NN lane position controller 112 and associated neural network 118, except that the D gain term provided by the neural network is used to control heading angle, while the P and I gain terms provided by the neural network are used to control lane position. The gain terms provided by the integrated PID controller 124 are used to control lane position. This is possible because heading angle can be associated with the derivative of a vehicle's lane position while driving. Controlling heading angle is equivalent to controlling the derivative of lane position, so they can share a PID controller.

In this way, by using an integrated adaptive PID-NN controller, a single controller can be used to control both trajectory parameters. This can improve the efficiency of trajectory control and mean that only a few components are required.

In the 8 In the embodiment shown, the output signal δ _{f_fb} of the integrated controller 124 is summed with the output signal δ _{f_ff} of the curve control 110' in a summing unit 115c. The output of the summing unit provides the total control signal δ _{f_tgt} of the trajectory controller 104, which is provided to the steering system 106 as described above. In this embodiment, the integrated controller 124 and the curve control 110' therefore operate in parallel with each other, with their resulting output signals being summed to provide the output of the trajectory controller 104. This is similar to the trajectory controller in and enables curve control to be included in the calculation at an early stage.

9 shows an alternative embodiment in which the integrated controller 124 and the curve controller 112' are connected in series. In this embodiment, the output signal CV _{tgt_fb} is summed with the target curve parameter CV _tgt by a summing unit 115d. The resulting signal is provided as an input signal to the curve controller 110', with the output of the curve controller 110' providing the overall control signal δ _{f_tgt} of the trajectory controller 104.

In the in the 6 to 9 In the embodiments shown, the curve control fixed P, I and/or D gain terms (e.g. determined using a fixed relationship between one or more motion variables and the gain values, where the fixed relationship is through a). In other embodiments, the waveform controller of these embodiments may be an adaptive PID neural network controller in which a neural network provides the gain terms.

Various modifications will be apparent to one skilled in the art without departing from the scope of the claims. The embodiments described above are intended as examples only. Any feature of any aspect or embodiment of the disclosure may be used separately or in combination with any other feature of the same or any other aspect or embodiment of the disclosure, and the disclosure includes any feature or combination of features disclosed herein.

Claims (10)

A system for controlling lateral movement of an autonomous vehicle, comprising: a trajectory planner configured to generate a target trajectory for the vehicle; and a trajectory controller configured to receive the target trajectory from the trajectory planner and generate as an output a steering control signal for controlling lateral movement of the vehicle; wherein the trajectory controller comprises a control circuit, the control circuit comprising an integrated adaptive PID neural network controller comprising: a PID controller receiving an input signal dependent on a target lane position parameter of the target trajectory and configured to minimize an error value indicative of the difference between the actual trajectory of the vehicle and the input signal dependent on the target lane position parameter, the PID controller further configured to receive an input signal dependent on a target heading angle parameter of the target trajectory and configured to minimize an error value indicative of the difference between the actual trajectory of the vehicle and the input signal dependent on the target heading angle parameter; and a neural network configured to determine the P-gain, I-gain, and D-gain terms used by the PID controller, wherein the integrated adaptive PID neural network controller is configured to use the P and I-gain terms provided by the neural network to control the lane position of the vehicle and the D-gain term provided by the neural network to control the heading angle of the vehicle, whereby the P, I, and D-gain terms used by the PID controller are provided by the same neural network. motion control system according to claim 1 wherein the trajectory controller further comprises a curve control configured to perform P and/or I and/or D control of the curve of the trajectory of the vehicle. motion control system according to claim 2 wherein the cornering control uses predetermined and/or vehicle motion variable dependent P-gain, I-gain and/or D-gain terms that do not change during use of the motion control system. motion control system according to claim 2 , where the waveform controller is an adaptive neural network controller whose neural network is configured to provide P-gain, I-gain and/or D-gain terms. motion control system according to claim 2 or claim 3 or claim 4 , wherein: the curve controller is configured to receive as input a target curve parameter and to produce as output a curve control signal; the trajectory controller is configured to determine the sum of the curve control signal and the output of the integrated adaptive PID neural network controller to provide the steering control signal output for the trajectory controller. A motion control system according to any preceding claim, wherein the neural network comprises an input layer of neurons, at least one hidden layer of neurons, and an output layer having at least one output neuron, the neural network comprising a feedforward neural network receiving in the input layer of input neurons the error value associated with the input trajectory parameter and the control signal output by the integrated adaptive PID neural network controller and outputting the gain values at corresponding node values within the hidden layer of the neural network. motion control system according to claim 6 , wherein the neural network is further configured that it receives at least one environmental variable as a feedforward term. motion control system according to claim 7 , wherein the environmental variable comprises at least one of the following variables commonly found in a vehicle motion control system: - the speed of the vehicle for most of the vehicle motion control, - road/traffic measurements such as curve shape, direction of travel, speed limit, etc. - vehicle acceleration/reaction force - engine speed/angle of rotation for current/torque control - steering torque or angle - vehicle indicator state, e.g. turn indicated or turn not indicated Motion control system according to one of the Claims 6 until 8 , wherein during use of the control system, the weights of the neural network are updated by a gradient descent backpropagation scheme each time a new set of input values is fed to the neural network, and the updated weights are used together with the input values to update the neurons. An autonomous motor vehicle comprising the motion control system according to any preceding claim.

Images