Collaborative management of remote updates to an autonomous driving feature provided by a driver assistance system in a motor vehicle

A computer system with a monitoring device and remote server, using a deep learning module, updates driving assistance systems to handle diverse dangerous scenarios, enhancing safety by determining preferred operations and improving the system's response to unpredictable driving conditions.

FR3148313A1Inactive Publication Date: 2024-11-01STELLANTIS AUTO SAS
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
FR2023004197
Authority / Receiving Office
FR · FR
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-04-26
Publication Date
2024-11-01
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing driving assistance systems for autonomous vehicles struggle to manage a wide variety of dangerous driving situations due to a lack of comprehensive decision-making rules, limiting their ability to ensure safety in diverse and unpredictable driving scenarios.

Method used

A computer system comprising a monitoring device on board a vehicle and a remote server, utilizing a deep learning module to analyze data from dangerous driving situations, determines preferred operations for the driving assistance equipment, and remotely updates the system to enhance its ability to handle such scenarios.

Benefits of technology

Enhances the driving assistance system's capacity to manage a broader range of dangerous situations, improving safety and reducing the risk of accidents without requiring user intervention.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

The invention relates to a method for managing, by means of a computer system (100), the updating of an autonomous driving feature provided by a driver assistance system (10) of a first motor vehicle (1), said system comprising a monitoring device (200) installed in a second motor vehicle (2) and a server (300) located remotely from both the first and second vehicles. The invention also relates to a computer system (100) implementing such a method. Figure for the abstract: 1
Need to check novelty before this filing date? Find Prior Art

Description

Title of the invention: Collaborative management of remote updates to an autonomous driving feature provided by a driver assistance system in a motor vehicle Technical field of the invention

[0001] The present invention relates to the field of driver assistance systems for motor vehicles. The invention relates in particular to a method for managing, by means of a computer system, the update of an autonomous driving function provided by a driver assistance system in a first motor vehicle, said system comprising an on-board monitoring device in a second motor vehicle and a remote server for both the first and second vehicles. The invention further relates to a computer system implementing such a method. The invention is applicable to motor vehicles, in particular motor vehicles such as cars. Prior art

[0002] It is known that some modern motor vehicles are equipped with driver assistance systems that provide autonomous driving functionality, that is, they allow the vehicle to be guided automatically. To enable this, these systems generally operate by determining a perception of the driving environment using detection devices (e.g., radar, lidar, camera, etc.), a perception that is used in conjunction with a number of pre-established decision rules that determine the driving behavior of the driver assistance system. Among such rules, efforts have been made to improve the safety of such autonomous driving functionalities by defining dangerous driving situations in order to allow the driver assistance system to react appropriately when it encounters such situations during driving.Unfortunately, it is difficult to determine all the dangerous driving situations a motor vehicle might encounter, particularly all those that could lead to an accident. Therefore, known driver assistance systems are limited in their ability to manage certain dangerous driving situations because they lack the decision-making rules that would allow them to handle them. Summary of the invention.

[0003] The invention aims to address this problem. In particular, the invention aims to provide a solution to enable an autonomous driving functionality provided by a driver assistance system in a motor vehicle to manage a A wider variety of hazardous driving situations. The invention aims, in particular, to provide a method and system that enable the handling of hazardous driving situations by a driver assistance system in a motor vehicle to be enhanced over time, without imposing any organizational constraints on vehicle users. In this way, the invention seeks to contribute to the provision of safer autonomous driving functionalities.

[0004] In order to achieve these goals, the invention relates, according to a first aspect, to a method for managing, by means of a computer system, the updating of an autonomous driving functionality provided by a driver assistance system of a first motor vehicle, said system comprising an on-board monitoring device in a second motor vehicle and a remote server for the first and second vehicles, the method comprising the steps of: i. determine, by the monitoring device, whether the second vehicle encountered a dangerous driving situation; ii. trigger, by the monitoring device, a transmission, to the server, of data characterizing said situation and an inventory of its consequences in relation to data characterizing the operation of a driving assistance device of the second vehicle at the time when said situation occurred; iii. to feed, via the server, a deep learning module with data characterizing said situation and an inventory of its consequences, and data characterizing the operation of a driver assistance system in the second vehicle at the time said situation occurred, in order to obtain data characterizing at least one preferred operation of a driver assistance system in a motor vehicle in relation to at least one specific dangerous driving situation; and iv. to remotely update, via the server, said functionality so that it uses data characterizing at least one privileged operation of a motor vehicle driving assistance device in connection with at least one particular dangerous driving situation.

[0005] According to one variant, the data characterizing said situation and an inventory of its consequences and the data characterizing the operation of a driving assistance device of the second vehicle at the time when said situation occurred can be transmitted by means of collaborative perception messages.

[0006] According to another variant, step i) can be carried out by interacting with a shock sensor arranged on board the second vehicle.

[0007] According to yet another variant, the data characterizing said situation and an in- The effects of its consequences can be generated by interacting with said sensor.

[0008] According to yet another variant, step i) may include a step consisting of establishing whether a sudden change in the speed of the second vehicle has occurred, whether the second vehicle has swerved, whether the hazard lights of the second vehicle have been turned on or whether a horn of the second vehicle has been activated.

[0009] According to yet another variant, the data characterizing said situation and an inventory of its consequences can be generated by interacting with a device for determining a physiological parameter of an occupant arranged on board the second vehicle.

[0010] According to a second aspect, the invention relates to a system for managing the update of an autonomous driving functionality provided by a driver assistance device of a first motor vehicle, said system comprising a monitoring device, which is on board a second motor vehicle, and a remote server of the first and second vehicles which jointly implement a method as described above.

[0011] According to one variant, the server can be hosted within a cloud computing infrastructure or on equipment of a fifth generation mobile communication network.

[0012] According to another embodiment, said system may include a deep learning module configured to determine data characterizing at least one preferred operation of a driver assistance device for a motor vehicle in relation to at least one particular dangerous driving situation. Brief description of the figures

[0013] Other features and advantages of the invention will become apparent from an examination of the detailed description below, and the accompanying drawings, in which:

[0014] [Fig-1] is a diagram illustrating the context of the invention; and

[0015] [Fig.2] is a diagram illustrating the steps of a process according to the invention. Detailed description of the invention

[0016] Figure 1 schematically illustrates a system 100 for managing the update of an autonomous driving feature provided by a driver assistance system 10 of a first motor vehicle 1 according to the invention. It is fundamentally a computer system, which includes, firstly, a monitoring device 200 installed in a second motor vehicle 2, which includes at least one information processing unit 201, comprising one or more processors, a data storage medium 202, and an input / output interface 203 for receiving and transmitting data. Preferably, the monitoring device 200 is hosted on a computer and interacts via its input and output interface 203 and by means of a wired communication network of the vehicle 1 (e.g. CAN, Ethernet) with a driving assistance device 20, a shock sensor 21, a device for determining a physiological parameter of an occupant 22, which allows for example the determination of the heart rate of an occupant, and a radio frequency signal communication device 23, preferably by means of a fifth generation mobile communication network, which are carried on board the second vehicle 2.

[0017] Furthermore, the system 100 according to the invention comprises a server 300 remote from the first vehicle 1 and the second vehicle 2, which is preferably part of a cloud computing infrastructure or equipment of a fifth generation mobile communication network, and which integrates or interacts with a deep learning module 400. Advantageously, the deep learning module 400 is configured to be fed with data characterizing dangerous driving situations and their consequences in terms of material damage and / or personal injury and with data characterizing the operation of a driver assistance system at the times when these situations occurred.Based on this data, the 400 deep learning module deduces data characterizing preferred operating modes of a vehicle's driver assistance system in relation to specific dangerous driving situations, as will be seen later. In other words, the 400 deep learning module is advantageously capable of determining, in relation to a given dangerous driving situation, a driver assistance system operation that minimizes the consequences in terms of material damage and / or personal injury.

[0018] To obtain the data that feeds the deep learning module 400, the server 300 is conventionally connected to at least one wireless communication network, preferably a fifth-generation mobile communication network, through which it can exchange data with the first and second vehicles 1, 2 using conventional communication protocols. The server 300 can thus advantageously receive data transmitted by the second vehicle 2, preferably by means of collaborative perception messages, and it can remotely update the autonomous driving functionality provided by the driver assistance system 10 of the first vehicle 1, in particular using remote software update methods, commonly identified by the acronym OTA, which comes from the English term "Over-The-Air".

[0019] According to the invention, all the elements described above contribute to enabling the implementation of a method for managing the update of an autonomous driving functionality provided by a driver assistance system of a first vehicle automobile, as described below in connection with [Fig.2].

[0020] Figure 2 illustrates, by means of a flowchart, the steps of the method according to the invention. According to a first step 11 of the method according to the invention, the monitoring device 200 installed on board the second vehicle 2 determines whether the second vehicle 2 has encountered a dangerous driving situation. In other words, the implementation of the method according to the invention begins with the monitoring device 200, which is configured to determine when the second vehicle 2 encounters what are referred to in the present invention as dangerous driving situations. Such situations are obviously those that result in an accident, but also situations in which erratic driving occurs. To determine the existence of such situations, the monitoring device 200 interacts, for example, with the shock sensor 21, which conventionally generates an electrical signal when the second vehicle 2 is subjected to a shock.Alternatively or cumulatively, it interacts with the driver assistance system 20 of the second vehicle 2 in order to determine whether a sudden change in speed of the second vehicle 2 has occurred, whether the second vehicle 2 has swerved, whether its hazard lights have been activated, or whether its horn has been sounded. And when it thus determines that the second vehicle 2 has encountered a dangerous driving situation, the monitoring device 200 then proceeds by carrying out the next step of the method according to the invention described below.

[0021] According to a second step E2 of the method according to the invention, the monitoring device 200, by interacting with the radio frequency communication equipment 23 of the second vehicle 2, triggers a transmission to the server 300, preferably by means of collaborative perception messages, of data characterizing the dangerous driving situation and an inventory of its consequences in relation to data characterizing the operation of the driver assistance equipment 20 of the second vehicle 2 at the time the dangerous driving situation occurred. In other words, the monitoring device 200 ensures at this stage the transmission of data that will feed the deep learning module 400.

[0022] For example, when it has determined that a dangerous driving situation has occurred by establishing that the second vehicle 2 has been impacted, the monitoring device 200 determines data characterizing the dangerous driving situation, interacting for this purpose with the driver assistance system 20 of the second vehicle in order to obtain its perception of the dangerous driving situation. And to establish an inventory of the consequences of the dangerous driving situation, the monitoring device 200 interacts, for example, with the impact sensor 21 in order to determine the extent of any material damage sustained by the second vehicle 2. Alternatively or cumulatively, it interacts with the equipment for determining a physiological parameter of an occupant 22 in order to determine any bodily injuries sustained by one or more occupants (is an occupant's heart rate critical?). According to yet another possibility, the monitoring device 200 uses the radio frequency signal communication equipment 23 to interact with a remote communicating entity of an emergency service, which conventionally provides inventories of the consequences of accidents, particularly in terms of material damage and / or bodily injury.

[0023] Furthermore, in connection with this data characterizing the dangerous driving situation and an inventory of its consequences, the monitoring device 200 also advantageously triggers the transmission of data characterizing the operation of the driver assistance system 20 of the second vehicle 2 at the time the dangerous driving situation occurred. Thus, at the end of this second step, the monitoring device 200 has advantageously enabled the server 300 to obtain data that fully characterize a dangerous driving situation and, in connection with this data, data that establishes how the driver assistance system 20 of the second vehicle functioned at the time this situation occurred.

[0024] According to a third step E3 of the method according to the invention, the server 300 feeds the deep learning module 400 with data characterizing the dangerous driving situation and an inventory of its consequences, as well as data characterizing the operation of the driver assistance system of the second vehicle at the time said situation occurred, in order to obtain data characterizing at least one preferred operation of a driver assistance system of a motor vehicle in relation to at least one particular dangerous driving situation. In other words, the deep learning module 400 advantageously makes it possible to establish, thanks to the data it receives, a preferred operation of a driver assistance system, in particular an operation that minimizes the consequences of the dangerous driving situation in terms of material damage and / or personal injury.And, as mentioned in the introduction, it is precisely such data that can be used by driver assistance systems, particularly those installed in the first vehicle 1, to enable an appropriate response from the driver assistance system when such a situation arises, thereby improving its operational safety. Thus, at the end of this third step, the server 300 has successfully obtained data that enables safer autonomous driving functionality for a driver assistance system in a motor vehicle.

[0025] Finally, according to a fourth step E4 of the process according to the invention, the server 300 triggers a remote update of the autonomous driving functionality provided by the driver assistance system 10 of the first vehicle 1, such that it uses data characterizing at least one preferred operation of a driver assistance system in a motor vehicle related to at least one specific dangerous driving situation. This data was generated by the deep learning module 400 during the previous step of the process. Preferably, this fourth step includes a preliminary step in which the server 300 determines, based on the data generated by the deep learning module 400, a set of decision rules that can be understood and used by the driver assistance system 10 of the first vehicle 1.These decision rules are then used to create a campaign of remote updates to the autonomous driving functionality provided by the driver assistance system 10 of the first vehicle 1. Thus, at the end of this final step of the process according to the invention, the autonomous driving functionality provided by the driver assistance system 10 of the first vehicle 1 is advantageously updated with data that allows it to react more safely to a wider variety of dangerous driving situations.

[0026] Thus, thanks to the method and system according to the invention described above, a solution is provided to enable an autonomous driving functionality provided by a driver assistance system in a motor vehicle to handle a wider variety of dangerous driving situations. In particular, thanks to the method and system according to the invention described above, the capacity of a driver assistance system in a motor vehicle to handle dangerous driving situations can advantageously be increased over time without imposing any organizational constraints on vehicle users. It is through these means that the invention contributes to the provision of more efficient, more comfortable, more ergonomic, and safer motor vehicles.

Claims

Claims

1. Method for managing, by means of a computer system (100), the updating of an autonomous driving functionality provided by a driving assistance device (10) of a first motor vehicle (1), said system comprising a monitoring device (200) on board a second motor vehicle (2) and a server (300) remote from the first and second vehicles, characterized in that the method comprises the steps of: i. determine, by the monitoring device, whether the second vehicle has encountered a dangerous driving situation; ii. cause, by the monitoring device, a transmission, to the server, of data characterizing said situation and an inventory of its consequences in relation to data characterizing the operation of a driving assistance device (20) of the second vehicle at the time when said situation occurred; iii. supplying, by the server, a deep learning module (400) with the data characterizing said situation and an inventory of its consequences and the data characterizing the operation of a driving assistance device of the second vehicle at the time when said situation occurred in order to obtain data characterizing at least one preferred operation of a driving assistance device of a motor vehicle in relation to at least one particular dangerous driving situation; and iv. remotely update, by the server, said functionality so that it uses the data characterizing at least one preferred operation of a driving assistance device of a motor vehicle in connection with at least one particular dangerous driving situation.

2. Method according to claim 1, characterized in that the data characterizing said situation and an inventory of its consequences and the data characterizing the operation of a driving assistance device of the second vehicle at the time when said situation occurred are transmitted by means of collaborative perception messages. borative.

3. Method according to one of the preceding claims, characterized in that step i) is carried out by interacting with a shock sensor (21) arranged on board the second vehicle.

4. Method according to claim 3, characterized in that the data characterizing said situation and an inventory of its consequences are generated by interacting with said sensor.

5. Method according to one of the preceding claims, characterized in that step i) comprises a step of establishing whether a sudden change in the speed of the second vehicle has occurred, whether the second vehicle has swerved, whether the hazard lights of the second vehicle have been switched on or whether a horn of the second vehicle has been activated.

6. Method according to one of the preceding claims, characterized in that the data characterizing said situation and an inventory of its consequences are generated by interacting with an apparatus for determining a physiological parameter of an occupant (22) arranged on board the second vehicle.

7. System (100) for managing the update of an autonomous driving functionality provided by a driving assistance device (10) of a first motor vehicle (1), characterized in that said system comprises a monitoring device (200), which is on board a second motor vehicle (2), and a server (300) remote from the first and second vehicles which jointly implement a method according to one of the preceding claims.

8. System according to claim 7, characterized in that the server is hosted within a cloud computing infrastructure or equipment of a fifth generation mobile communication network.

9. System according to one of claims 7 or 8, characterized in that said system comprises a deep learning module (400) configured to determine data characterizing at least one preferred operation of a driving assistance device of a motor vehicle in relation to at least one particular dangerous driving situation.

Citation Information

Patent Citations

  • Transport dangerous driving reporting

    US20210174684A1

  • Autonomous vehicle system

    US20220126864A1

  • Vulnerable road user safety technologies based on responsibility sensitive safety

    US20220388505A1