GB2641805A

GB2641805A - Method for collecting extreme data and collecting system

Info

Publication number: GB2641805A
Application number: GB2408527.6A
Authority: GB
Inventors: Even Stephanie
Original assignee: Mercedes Benz Group AG
Current assignee: Mercedes Benz Group AG
Priority date: 2024-06-14
Filing date: 2024-06-14
Publication date: 2025-12-17
Also published as: DE102024135408A1; GB202408527D0

Abstract

Disclosed is a method for collecting environmental data by an autonomous driving vehicle 10. The method starts by collecting the environmental data 14 from the surroundings of the vehicle using sensing devices 12 and then sending the data from an on-board electronic computing device 16 to an off-board electronic computing device 17 via wireless communication. The off-board electronic device initializes an associative memory array, each piece of environmental data is positioned in different row of the associative memory array. Then extreme values of the data are determined by examining each number to check whether it contains a bit with an extreme value in the row of the memory. Information about the data with the extreme values is transmitted back to the on-board device and an adapted control is executed by the on-board device based on the data with the extreme values.

Description

[0001] Method for collecting extreme data and collecting system

[0002] FIELD OF THE INVENTION

[0003] The present invention relates to the field of automobiles. More specifically, the present invention relates to a method for collecting extreme data especially in the context of an autonomous driving system for a at least partially autonomous vehicle according to claim 1. Furthermore, the present invention relates to a corresponding computer program product, to a corresponding non-transitory computer-readable storage medium, as well as to a corresponding data collection system.

[0004] BACKGROUND INFORMATION

[0005] The US10929751 B2 discloses a method that involves identifying a set of extreme values from a data set of elements in a constant time, regardless of the data set's size. This method creates a set of indicators, with each indicator associated with a multi bit binary number in a large data set of multi bit binary numbers. The method includes organizing these multi bit binary numbers so that each bit of each multi bit binary number is positioned in a different row of an associative memory array. This arrangement starts from a row that stores the most significant NSB. An indicator is added to the set of each multi bit binary number that contains a bit with an extreme value in the respective row, and this addition continues until the set contains indicators.

[0006] SUMMARY OF THE INVENTION

[0007] The object of the invention is to provide means to enable efficient detection of extreme values during the autonomous operation of a vehicle, while avoiding overloading the computational capacity of the electronic computing device used for the autonomous driving.

[0008] This objective is achieved by a method as described in claim 1 and by a computer program product, a non-transitory computer-readable storage medium, and a data collection system according to the invention. Advantageous embodiments and further developments may be found in the dependent claims.

[0009] The invention relates to a method for collecting extreme data by at least one autonomous driving vehicle, especially for passenger vehicles, furthermore, the method can also be adapted and applied to semi-autonomous vehicles.

[0010] In a first step, environmental data of the vehicle's surroundings is collected using at least one sensing device and transmitted to an on-board electronic computing device coupled with the sensing device(s), with the environmental data represented by binary numbers with multiple bits. Such sensing devices are normally already installed in the vehicle and can include cameras or sensors, which transmit all data to the on-board electronic computing device. As a result, they are electronically coupled and at least partially controllable. Communication can be bidirectional, allowing targeted data to be collected as requested by the on-board electronic computing device. Alternatively, a data stream or other data transfer methods may be provided, transferring data from the sensing device to the on-board electronic computing device, enabling continuous data collection and processing of the environment, thereby facilitating continuous targeted overloading avoidance.

[0011] In a second step, the environmental data is sent from the on-board electronic device to an off-board electronic computing device of a data collection system via wireless communication. For this purpose, both the on-board and off-board electronic computing devices may have respective communication modules capable of exchanging data, for example, via the internet. Additionally, the off-board electronic computing device could be part of a cloud with a corresponding server or backend, serving as a central hub for collecting data from a multitude of vehicles. This off-board device is thus a component of the data collection system, capable of providing much higher computational power compared to the on-board electronic device, allowing for the capture of extreme values, processing of information, and subsequent forwarding or return to the respective vehicles. As a result, the computation of data is outsourced, enabling an overloading avoidance of the on-board computer. Additionally, this offers the capability to collect and merge data from many vehicles and increase the relevance of the statistical evaluation.

[0012] In a third step, an associative memory array is initialized by the off-board electronic device, wherein each binary number with multiple bits of the environmental data is positioned in a different row of the associative memory array. This means that the data is captured by the off-board electronic device and the memory array is accordingly generated. Overall, communication occurs, for example, via a data stream of binary numbers, which requires lower data transmission overhead. Simultaneously, the off-board electronic computing device captures all the multiple bits from the received binary numbers and inserts them into the memory array for comparison, allowing for subsequent evaluation of the data.

[0013] In a fourth step, extreme values in the binary numbers are determined by examining each binary number comprising multiple Bits to verify whether it contains at least one bit with an extreme value in the row of the associative memory array. This allows for the data to be outsourced and utilized for capturing the extreme values.

[0014] In a fifth step, information regarding the environmental data with the extreme values is transmitted to the on-board electronic computing device. Here also, it is intended to transmit the data via wireless communication, thereby avoiding the computation of extreme values in the vehicle. Furthermore, outsourcing has the advantage of not only applying the data of one vehicle to that vehicle alone but also making it available for other vehicles of a fleet through the data collection system. Particularly, the values from an environment are applicable to other vehicles in that environment, allowing for better statistical values and faster results for the vehicles in that environment.

[0015] In a sixth step, at least one adapted control is executed by the on-board electronic device based on the environmental data with the extreme values. This step involves utilizing the extreme values to inform decision-making processes within the vehicle's control system. These adapted controls may include adjustments to steering, acceleration, braking, or other vehicle functions to enhance safety and performance in response to the detected extreme conditions, as some examples [0012] Therefore, this method enables the collecting and analysis of extreme data in the vehicle's environment, ensuring the safety and performance of the autonomous driving system.

[0016] In an advantageous embodiment of the invention, it is provided that the initialization of the associative memory array begins with the most significant bit. This means that the process of organizing multi bit binary numbers with the memory array starts with the highest bits as an example, ensuring efficient data management.

[0017] In another advantageous embodiment of the invention, it is provided that the addition of indicators to a group of extreme values for each binary number, which has at least one bit with an extreme value in one row N, continues until the group contains the desired number K of extreme values. This method allows for the effective identification and collection of the required number of extreme values, optimizing the process.

[0018] In another advantageous embodiment of the invention, it is provided that a statistical model based on the collected extreme values is used, through which a threshold value is determined to establish the compile-time defined capacity for observed objects in an autonomous driving system. Statistical models, as required here, would necessitate a vast amount of data and computational capacity to adapt to the entirety of extreme values collected from a fleet of vehicles. By employing this statistical model and the threshold value, the system can dynamically adjust and allocate resources based on the observed extreme values, thereby enhancing the overall performance and safety of the autonomous driving system without causing overloads.

[0019] Another aspect of the invention relates to a computer program product comprising program code means for performing a method for collecting extreme data by the at least one autonomous driving vehicle.

[0020] Another aspect of the invention relates to a non-transitory computer-readable storage medium comprising at least the computer program product.

[0021] Another aspect of the invention relates to a data collection system implemented for collecting extreme data from a fleet of autonomous vehicles. This data collection system includes an off-board electronic computing device, to which multiple on-board electronic computing devices from each autonomous vehicle in the fleet can wirelessly transmit environmental data represented as binary numbers with multiple bits. Within this collection data system, an associative memory array can be initialized by the off-board electronic device, where each binary number with multiple bits of the environmental data is positioned in a separate row of the associative memory array. The data collection system is capable of determining extremes in the binary numbers by examining each binary number with multiple bits to verify whether it contains at least one bit with an extreme value in the row of the associative memory array. Moreover, information regarding the environmental data with the extremes can be transmitted to the on-board electronic computing devices of every vehicle in the fleet, ensuring the safety and performance of the autonomous driving systems of each vehicle.

[0022] Further advantages, features, and details of the invention derive from the following description of preferred embodiments as well as from the figures. The features and feature combinations previously mentioned in the description as well as the features and feature combinations mentioned in the following description of the figures and/or shown in the figures alone may be employed not only in the respectively indicated combination but also in any other combination or taken alone without leaving the scope of the invention.

[0023] BRIEF DESCRIPTION OF THE FIGURES

[0024] The novel features and characteristic of the disclosure are set forth in the appended claims. The accompanying figures, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and together with the description, serve to explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components. Some embodiments of system and/or methods in accordance with embodiments of the present subject matter are now described below, by way of example only, and with reference to the accompanying figures.

[0025] The figures show in: [0022] Fig. 1 represents a data collection system for autonomous driving.

[0026] In the figures the same elements or elements having the same function are indicated by the same reference signs.

[0027] DETAILED DESCRIPTION

[0028] In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration". Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0029] While the disclosure is susceptible to various modifications and alternative forms, specific embodiments thereof have been shown by way of example in the figure and will be described in detail below. It should be understood, however, that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternatives falling within the scope of the disclosure.

[0030] The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion so that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus preceded by "comprises" or "comprise" does not or do not, without more constraints, preclude the existence of other elements or additional elements in the system or method.

[0031] In the following detailed description of the embodiment of the disclosure, reference is made to the accompanying figure that forms part hereof, and in which is shown by way of illustration a specific embodiment in which the disclosure may be practiced. This embodiment is described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.

[0032] Fig. 1 shows a schematic representation of a Data Collection System 20 designed for collecting extreme data from a fleet of autonomous vehicles 10, 11 to illustrate an inventive method for collecting extreme data by at least one autonomous driving vehicle.

[0033] An Off-Board Electronic Computing Device 17 of the data collection system 20, depicted as a central hub, to which multiple On-Board Electronic Computing Devices 16 from each autonomous vehicle in the fleet can wirelessly transmit environmental data.

[0034] It is envisioned that environmental data of the vehicle's 10, 11 surroundings 14 will be collected using at least one sensing device 12 of the vehicles 10, 11 and transmitted to the on-board electronic computing device 16 coupled with the sensing devices 12. This data will be represented by binary numbers with multiple bits.

[0035] Following that, the environmental data collected by the on-board electronic device 16 will be transmitted to an off-board electronic computing device 17 of a data collection system 20. This communication occurs via wireless communication channels, facilitating seamless data transfer.

[0036] The environmental data transmitted from the On-Board Electronic Computing Devices 16 is represented as binary numbers with multiple bits. Upon reception, the Off-Board Electronic Computing Device 17 can initialize an Associative Memory Array. Each binary number with multiple bits of the environmental data is then positioned in a distinct row of the associative memory array, allowing for efficient organization and storage of the data.

[0037] Moreover, the Off-Board Electronic Computing Device 17 is equipped with algorithms capable of determining extreme values within the binary numbers. This involves examining each binary number with multiple bits to ascertain whether it contains at least one bit with an extreme value. Such extreme values are highlighted and stored within the associative memory array for further analysis.

[0038] For instance, the off-board electronic computing device 17 can initialize the associative memory array, starting with the most significant bit, and add indicators to a group of extreme values for each binary number that contains at least one bit with an extreme value in a row, continuing the addition until the group contains the desired number of extreme values. Additionally, the utilization of a statistical model based on the collected extreme values is possible. This statistical model is employed to determine a threshold value, which is utilized to establish the compile-time defined capacity for observed objects in an autonomous driving system.

[0039] Finally, the Fig.1 illustrates the transmission of information regarding the environmental data with the extremes back to the On-Board Electronic Computing Devices 16 of each vehicle 10, 11 in the fleet. This bidirectional communication enables the dissemination of crucial information to individual vehicles, enhancing their ability to respond effectively to extreme environmental conditions in real-time.

[0040] This Fig. 1 illustrates therefore the essential components and functionality of the data collection system 20 in the context of autonomous driving by vehicles 10, 11 highlighting its role in detecting extreme data for improved vehicles 10, 11 operation and safety.

[0041] Reference signs vehicle 11 vehicle (fleet) 12 sensing device 14 surrounding 16 on-board electronic computing device 17 off-board electronic computing device data collecting system

Claims

1. CLAIMS1. Method for collecting extreme data by at least one autonomous driving vehicle (10), comprising the following steps - collecting environmental data of a surrounding (14) of the vehicle (10) using at least one sensing device (12) and transmitting the environmental data to an onboard electronic computing device (16) coupled with the at least one sensing device (12), with the environmental data represented by binary numbers with multiple Bits; - sending the environmental data from the on-board electronic device (16) to an off-board electronic computing device (17) of a data collection system (20) via wireless communication; - initializing an associative memory array by the off-board electronic device (17), wherein each binary number with multiple Bits of the environmental data is positioned in a different row of the associative memory array; - determining extreme values in the binary numbers by examining each binary number comprising multiple bits to verify whether it contains at least one bit with an extreme value in the row of the associative memory array, - transmitting information of the environmental data with the extreme values to the on-board electronic computing device (16); - executing at least one adapted control depending on the environmental data with the extreme values by the on-board electronic device (16).

2. Method according to claim 1, characterized in that the initialization of the associative memory array begins with the most significant bit.

3. Method according to claim 1 or 2, characterized in that the addition of indicators to a group of extreme values for each binary number that has at least one bit with an extreme value in a row and continuing the addition until the group contains the desired number of extreme values is subsequently performed.

4. Method according to claim 1 or 2, characterized in that a statistical model based on the collected extreme values is used, through which a threshold value is determined to establish the compile-time defined capacity for observed objects in an autonomous driving system.

5. A computer program product comprising program code means for performing a method according to claims 1 to 4.

6. A non-transitory computer-readable storage medium comprising at least the computer program product according to claim 5.

7. Data collection system (20) for collecting extreme data by a fleet of autonomous vehicles (11), with an off-board electronic computing device (17) to which a plurality of on-board electronic computing devices (16) of the respective autonomous vehicles (11) of the fleet can transmit environmental data represented as binary numbers with multiple bits via wireless communication, wherein an associative memory array can be initialized by the off-board electronic device (17), and each binary number with multiple bits of the environmental data can be positioned in a different row of the associative memory array and extremes in the binary numbers can be determined by examining each binary number with multiple bits to verify whether it contains at least one bit with an extreme value in the row of the associative memory array, wherein information of the environmental data with the extremes can be transmitted to the on-board electronic computing devices (16) of each vehicle (11) of the fleet.