WO2023051398A1 - Procédé et appareil de compensation de sécurité, et support de stockage et dispositif électronique - Google Patents

Procédé et appareil de compensation de sécurité, et support de stockage et dispositif électronique Download PDF

Info

Publication number
WO2023051398A1
WO2023051398A1 PCT/CN2022/120838 CN2022120838W WO2023051398A1 WO 2023051398 A1 WO2023051398 A1 WO 2023051398A1 CN 2022120838 W CN2022120838 W CN 2022120838W WO 2023051398 A1 WO2023051398 A1 WO 2023051398A1
Authority
WO
WIPO (PCT)
Prior art keywords
decision
target
trajectory
compensation
making
Prior art date
Application number
PCT/CN2022/120838
Other languages
English (en)
Chinese (zh)
Inventor
崔茂源
王超
吕颖
吕铮
高延熹
Original Assignee
中国第一汽车股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中国第一汽车股份有限公司 filed Critical 中国第一汽车股份有限公司
Publication of WO2023051398A1 publication Critical patent/WO2023051398A1/fr

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0015—Planning or execution of driving tasks specially adapted for safety
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences

Definitions

  • the embodiments of the present application relate to the technical field of automatic driving, for example, to a safety compensation method, device, storage medium and electronic equipment.
  • the safety model of the automatic driving system can make simple compensation responses, such as slowing down, changing lanes and other avoidance behaviors.
  • the avoidance behavior causes the vehicle to enter into a new conflict with other targets, the compensatory response will not be executed.
  • a stationary vehicle poses a danger, it is often expected that the vehicle will still perform a compensatory response to protect human safety, but related technologies will not perform this compensatory response, which does not meet the ethical requirements of the society for autonomous driving systems.
  • Embodiments of the present application provide a security compensation method, device, storage medium, and electronic equipment.
  • the embodiment of the present application provides a security compensation method, including:
  • Screening is performed on the multi-objective decision set based on multi-objective decision-making to determine a target trajectory, wherein the multi-objective decision-making includes at least a casualty target decision, and the casualty target decision is set to determine a trajectory with the least casualties.
  • the embodiment of the present application also provides a safety compensation device, including:
  • a collection acquisition module configured to obtain a compensation response collection and a system decision collection
  • a multi-objective decision determination module configured to determine a multi-objective decision set based on the compensation response set and the system decision set;
  • the target trajectory determination module is configured to perform screening in the multi-objective decision set based on the multi-objective decision-making, and determine the target trajectory, wherein the multi-objective decision-making includes at least the casualty target decision, and the casualty target decision is set to determine the casualty Minimal track.
  • the embodiment of the present application further provides an electronic device, the electronic device comprising:
  • processors one or more processors
  • storage means configured to store one or more programs
  • the one or more processors are made to implement the security compensation method described in any one of the embodiments of the present application.
  • the embodiments of the present application also provide a storage medium containing computer-executable instructions, and the computer-executable instructions are used to perform the security compensation described in any one of the embodiments of the present application when executed by a computer processor. method.
  • FIG. 1 is a schematic flowchart of a safety compensation method provided in Embodiment 1 of the present application;
  • Fig. 2 is a schematic flow chart of a safety compensation method provided in Embodiment 2 of the present application.
  • Fig. 3 is a schematic flow chart of a safety compensation method provided in Embodiment 3 of the present application.
  • Fig. 4 is a schematic diagram of generating a compensation reaction set provided in Example 3 of the present application.
  • Fig. 5 is a schematic structural diagram of a safety compensation device provided in Embodiment 4 of the present application.
  • FIG. 6 is a schematic structural diagram of an electronic device provided in Embodiment 5 of the present application.
  • Figure 1 is a flow chart of a safety compensation method provided in Embodiment 1 of the present application. This embodiment is applicable to automatic safety compensation in automatic driving, and the method can be executed by the safety compensation device provided in the embodiment of the present application.
  • the device may be implemented by software and/or hardware, and the device may be configured on an electronic device, for example, a vehicle-mounted terminal. Including the following steps:
  • the compensation response set refers to a set containing one or more compensation decisions.
  • the compensation decision can be a motion trajectory based on the basic actions of the vehicle such as speed change and direction change.
  • the motion trajectory includes a starting point, a path, and an end point.
  • the compensation decision can be to keep the autonomous vehicle away from the trajectory of obstacle targets, which can be people, surrounding vehicles, road facilities, etc.
  • obstacle targets which can be people, surrounding vehicles, road facilities, etc.
  • compensation decisions can bring the autonomous vehicle back to a safe state.
  • the system decision set may be a decision set generated by the automatic driving system.
  • the decision in the system decision set is a decision not to execute the compensation response, but the system decision set and the compensation response set may have the same motion track or different motion tracks.
  • the compensation response set can be used as the compensation decision of the system decision set, providing more optional decision-making schemes for the automatic driving system and ensuring vehicle safety.
  • the set of compensation responses may be randomly generated based on the real-time information of the self-driving vehicle.
  • the real-time information may include but not limited to the basic motion of the vehicle and the current position of the vehicle.
  • the route planning of the vehicle may also be performed by a graph search method, so as to obtain the compensation response set, and the method for obtaining the compensation response set is not limited in this embodiment of the present application.
  • the multi-objective decision set may be a set of motion trajectories corresponding to multiple decisions.
  • the compensation response set and the system decision set can be combined to obtain a multi-objective decision set, and the different motion trajectories in the two sets can be retained, or the same motion trajectory can be retained , to provide more motion trajectories for selection, that is, more driving decisions can be selected to ensure driving safety, and only one part of the same motion trajectory is reserved to avoid overlapping motion trajectories in multi-objective decision sets.
  • the compensation reaction set and the system decision set may be intersected, and the same motion trajectory in both sets may be retained. Decisions corresponding to the same motion trajectory can be identified as optimal decisions, and the optimal decisions can be regarded as a multi-objective decision set.
  • multi-objective decision-making refers to the decision-making that has multiple decision-making objectives and needs to use multiple criteria to evaluate and select the motion trajectory.
  • the target trajectory is the final movement trajectory of the automatic driving system, which can be obtained by screening in the multi-objective decision-making set through multi-objective decision-making.
  • the target trajectory can be the one with the fewest casualties.
  • Multi-objective decision-making can include but not limited to casualty target decision-making, which is used to determine the trajectory with the least casualties, so that the planned target trajectory is more in line with social and ethical requirements.
  • the specific implementation method of casualty target decision-making can be to use the camera on the vehicle to detect the situation of people on the movement trajectory, and then select the trajectory with the least casualties among the various movement trajectories.
  • a trajectory set including multiple motion trajectories can be obtained.
  • any motion trajectory can be directly selected as a target trajectory in a plurality of motion-trajectory sets.
  • Select The method of the target trajectory is simple and can increase the speed of determining the target trajectory.
  • new multi-objective decision-making can be obtained to continue screening until there is one motion trajectory remaining in the trajectory set, and the remaining one motion trajectory in the trajectory set is used as the target trajectory, so that the obtained target trajectory conforms to multiple multi-objective decision-making
  • the evaluation standard can realize the selection of the optimal target trajectory.
  • the embodiment of this application provides a safety compensation method, by obtaining the compensation response set and the system decision set; determining the multi-objective decision set based on the compensation response set and the system decision set; The trajectory, wherein the multi-objective decision-making at least includes the casualty goal decision, and the casualty goal decision is used to determine the trajectory with the least casualties.
  • the compensation response set By obtaining the compensation response set, the number of decisions in the multi-objective decision set can be enriched, and more abundant strategy choices can be provided for users.
  • the target trajectory with minimum casualties is obtained, which makes the planned target trajectory more in line with social and ethical requirements.
  • Fig. 2 is a schematic flowchart of a safety compensation method provided in Embodiment 2 of the present application.
  • screening in the multi-objective decision-making set based on multi-objective decision-making to determine the target trajectory is described.
  • the method of the embodiment of the present application includes the following steps:
  • S220 Determine a multi-objective decision set based on the compensation response set and the system decision set.
  • the multi-objective decision-making also includes environmental damage target decision-making and economic loss target decision-making
  • the environmental damage target decision-making can be used to determine the trajectory set with the minimum environmental damage
  • the economic loss target decision-making can be used to determine the trajectory set with the minimum economic loss
  • the trajectory A collection can contain one or more motion profiles.
  • the trajectory set with the least environmental damage can be selected from the trajectory set with the smallest casualties, and then the trajectory set with the smallest environmental damage can be re-screened. After screening the trajectory set with the least economic loss, the priorities of the decision-making for the target of casualties, the decision-making of environmental damage and the decision-making of economic loss are lowered in turn. On the premise of ensuring the minimum of casualties, the screening of the least environmental damage and the least economic loss is carried out, so that the final The obtained target trajectory is more in line with the requirements of social ethics.
  • the decision-making based on the target of casualty, the target decision of environmental damage and the target decision of economic loss is sequentially screened in a multi-target decision set, and the target trajectory is determined based on the screening results, including: The casualty target decision is screened in the multi-objective decision set to determine the first trajectory set with the smallest casualties; based on the environmental damage target decision, the first trajectory set is screened to determine the second trajectory with the smallest environmental damage set; based on the economic loss target decision, perform screening in the second set of trajectories to determine a third set of trajectories with the smallest economic loss; determine the target trajectory in the third set of trajectories.
  • the first set of trajectories can be the set of motion trajectories with the least casualties
  • the second set of trajectories can be the set of motion trajectories that continue to filter the least damage to the environment in the first set of trajectories
  • the third set of trajectories can be the set of motion trajectories in the second set of trajectories. Continue to filter the set of motion trajectories with the least economic loss, and then determine the target trajectory in the third set of trajectories.
  • the multi-objective decision-making set is successively screened, so that the environmental damage and economic loss can be considered while ensuring the minimum casualties. And so on, so that the target trajectory is more in line with the requirements of social ethics.
  • the target trajectory is determined based on the screening results, including:
  • the target decision set is input into the multi-objective decision-making algorithm model to obtain the target trajectory;
  • the multi-objective decision-making algorithm model includes a sequentially connected casualty assessment module, environmental damage assessment module and economic loss assessment module, and the casualty assessment module uses
  • the environmental damage assessment module is used to determine the second trajectory set with the smallest environmental damage in the first trajectory set
  • the economic loss assessment module is used for A third trajectory set with the smallest economic loss is determined in the second trajectory set, and the third trajectory set is output.
  • the multi-objective decision-making algorithm model can be a preset objective function, and the personnel casualty assessment module, the environmental damage assessment module and the economic loss assessment module can be sub-functions in the objective function, and in some embodiments, the multi-objective decision-making algorithm model can also It can be a machine learning model, and the casualty assessment module, environmental damage assessment module and economic loss assessment module can be functional modules in the machine learning model. This embodiment does not limit the form of the multi-objective decision-making algorithm model.
  • the first trajectory set with the minimum casualty is determined in the multi-objective decision set, and then the environmental damage assessment module is used to determine the second trajectory set with the minimum environmental damage in the first trajectory set, and then Through the economic loss assessment module, the third track set with the smallest economic loss is determined in the second track set, and finally the current user set is determined in the third track set.
  • screening is performed in the multi-target decision set in turn, and the target trajectory is determined based on the screening results, including: for the multiple target decisions
  • Each trajectory in the target decision set determines the number of casualties, environmental damage and economic loss of each trajectory based on the casualty target decision, the environmental damage target decision and the economic loss target decision respectively;
  • Quantity, environmental damage and economic loss respectively determine the corresponding weight of the trajectory, determine the recommendation index of the trajectory based on each weight of the trajectory; determine the target trajectory based on the recommendation index of each trajectory.
  • the specific implementation of the decision-making of personal casualties, the decision-making of environmental damage and the decision-making of economic loss may be to obtain the picture of the movement trajectory through the camera, and then use the image recognition technology to identify the people and environmental objects in the picture of the movement trajectory, wherein, Personnel may include but not limited to pedestrians and cyclists; environmental objects may include but not limited to utility poles, trees, green belts, etc. Further, the number of casualties, environmental damage, and economic loss of the movement track are respectively determined according to the identified personnel and environmental objects.
  • the environmental object can be a green belt, and the environmental damage degree can be 3 (the environmental damage degree ranges from 0 to 10, the higher the environmental damage, the higher the environmental damage degree), the vehicle damage can be predicted according to the recognized environmental objects, and then according to the vehicle damage Calculate vehicle damage.
  • determining the corresponding weight of the trajectory is divided into the following situations: if the number of casualties is zero, the corresponding weight of the number of casualties on the trajectory can be a lower ratio, such as 0 or 0.1; When the number of casualties is not zero, the weight of environmental damage and economic loss can be directly reset to a lower ratio, such as 0 or 0.1, and the corresponding weight of the number of casualties on the trajectory can be reset to a higher ratio , such as 1 or 0.9.
  • the recommendation index of the track is determined according to each weight of the track; the target track is determined based on the recommendation index of each track, for example, the weights of the track are added to obtain the recommendation index, and then the recommendation index of each track is sorted, The trajectory with the largest recommendation index is determined as the target trajectory. If there are trajectories with the same recommendation index, one of the trajectories with the same recommendation index is selected as the target trajectory.
  • the embodiment of the present application provides a safety compensation method.
  • the trajectory set with the smallest environmental damage can be selected from the trajectory set with the smallest casualties, and then the environmental damage
  • the trajectory set with the smallest economic loss is selected from the smallest trajectory set, and the priority of the decision-making of the target of casualties, environmental damage and economic loss is lowered in turn.
  • the minimum screening makes the final target trajectory more in line with social and ethical requirements.
  • FIG. 3 is a schematic flow chart of a security compensation method provided in Embodiment 3 of the present application, and the embodiment of the present application may be combined with any of the foregoing embodiments.
  • the method before acquiring the compensation response set and the system decision set, the method further includes: creating an original compensation set, a storage set, and a queue; updating the original compensation set, the The storage set and queue described above determine the set of compensation responses.
  • the method of the embodiment of the present application includes the following steps:
  • the original compensation set can be an empty set, which is the initial state of the compensation response set, and the original compensation set can use the motion trajectory of the autonomous vehicle as a set element.
  • the storage set can be an empty set, which can be used to store the location information of the self-driving vehicle; the initial state of the queue can be an empty queue, and the queue can be used to store and pop up the location information of the self-driving vehicle.
  • the current position of the vehicle can be the real-time position of the self-driving vehicle.
  • the real-time positioning of the self-driving vehicle can be carried out by laser radar to obtain the current position of the vehicle; in some embodiments, the global satellite navigation system and The positioning method of inertial sensor fusion performs real-time positioning of the self-driving vehicle to obtain the current position of the vehicle. This embodiment does not limit the method for obtaining the current position of the vehicle.
  • Basic vehicle actions may include, but are not limited to, actions such as speed changes and direction changes.
  • the current position of the vehicle can be determined as the starting point of the trajectory, and then the trajectory of the vehicle can be automatically driven by predicting the trajectory of the vehicle through speed transformation or direction change. It can be understood that the predicted trajectory can be one or more.
  • the predicted motion trajectories can be directly added to the original compensation set as the compensation response set.
  • each motion trajectory is added to the original compensation set to update the elements in the original compensation set, and the updated original The compensation set is used as a compensation response set, which adds the current position of the vehicle to the storage set and queue, and realizes the updating of elements in the storage set and queue.
  • updating the original compensation set, the storage set and the queue based on the current vehicle position and the basic actions of the vehicle, and determining the compensation reaction set include: storing the current vehicle position in the storage set and The queue is determined as the starting position based on the top element in the queue; the path set is determined based on the starting position and the basic vehicle action; the original compensation set is updated based on the storage set and the path set, and a compensation response set is obtained.
  • the starting position may be the vehicle position at the current moment, or the vehicle position at the previous moment.
  • a collection of paths may be a collection of path segments starting from a starting location.
  • the current position of the vehicle is stored in the storage set and the queue, the current position of the vehicle can be represented by Xinit , and it is judged whether the queue is empty, if the queue is empty, the original compensation set is determined To compensate for the response set, if the queue is not empty, pop the top element in the queue and assign it to a custom variable, where the custom variable can be used as the starting position of the vehicle, which can be represented by the letter X.
  • the path set starting from the starting position is determined according to the basic actions of the vehicle such as speed change and direction change, and the path set can be denoted by M.
  • the path set may be a set of motion trajectories of the autonomous vehicle when the basic motion of the vehicle is a certain speed and a certain steering wheel angle.
  • the paths in the path set are traversed, and if the traversal ends, the step of judging whether the queue is empty is continued.
  • a type of traversal process is: if the path in the path set satisfies the preset distance from the obstacle target, that is, when it is far away from the target obstacle, then store the starting position, path, and end position of the motion trajectory in the original compensation set, where, The original compensation set can be represented by E, the storage set can be represented by V, the path can be represented by ⁇ , and the end position of the motion trajectory can be represented by ⁇ (1). If the end position of the motion track belongs to the storage set, then end the processing of the current track element; if the end position of the motion track does not belong to the storage set, then add the end position of the motion track to the queue and the storage set.
  • S350 Screen the multi-objective decision set based on multi-objective decision-making to determine a target trajectory, wherein the multi-objective decision-making includes at least a casualty target decision, and the casualty target decision is used to determine a trajectory with the least casualties.
  • the embodiment of the present application provides a safety compensation method, by creating the original compensation set, storage set and queue, updating the original compensation set, storage set and queue based on the current position of the vehicle and the basic actions of the vehicle, and determining the compensation response set, the vehicle
  • the motion trajectory far away from the dangerous target is added to the original compensation set to update the elements in the original compensation set, and the updated original compensation set is used as the compensation response set to provide users with richer strategy choices.
  • Fig. 5 is a schematic structural diagram of a safety compensation device provided in Embodiment 4 of the present application.
  • the safety compensation device provided in this embodiment can be realized by software and/or hardware, and can be configured in a terminal and/or server to realize the present invention. Apply the safety compensation method in the embodiment.
  • the device may include: a set acquisition module 410 , a multi-object decision determination module 420 and a target trajectory determination module 430 .
  • the set acquisition module 410 is configured to acquire a compensation response set and a system decision set;
  • the multi-objective decision determination module 420 is configured to determine a multi-objective decision set based on the compensation response set and the system decision set;
  • the target trajectory determination module 430 set to perform screening in the multi-objective decision-making set based on multi-objective decision-making, and determine the target trajectory, wherein the multi-objective decision-making includes at least the casualty target decision-making, and the casualty target decision-making is set to determine the trajectory with the least casualties.
  • the embodiment of the present application provides a safety compensation device, by obtaining the compensation response set and the system decision set; determining the multi-objective decision set based on the compensation response set and the system decision set; The trajectory, wherein the multi-objective decision-making at least includes the casualty goal decision, and the casualty goal decision-making is set to determine the trajectory with the least casualties.
  • the compensation response set By obtaining the compensation response set, the number of decisions in the multi-objective decision set can be enriched, and more abundant strategy choices can be provided for users.
  • the target trajectory with minimum casualties is obtained, which makes the planned target trajectory more in line with social and ethical requirements.
  • the multi-objective decision-making also includes environmental damage target decision-making and economic loss target decision-making;
  • the target trajectory determination module 430 may also include:
  • the trajectory determination unit is configured to sequentially perform screening in the multi-objective decision set based on the personal casualty target decision, the environmental damage target decision and the economic loss target decision, and determine the target trajectory based on the screening results.
  • the trajectory determination unit further includes:
  • the first trajectory set determination subunit is configured to perform screening in the multi-objective decision set based on the casualty target decision, and determine the first trajectory set with the smallest casualties;
  • the second trajectory set determination subunit is configured to filter in the first trajectory set based on the environmental damage target decision, and determine the second trajectory set with the smallest degree of environmental damage;
  • the third trajectory set determination subunit is configured to filter in the second trajectory set based on the economic loss target decision, and determine the third trajectory set with the smallest economic loss;
  • the target trajectory determining subunit is configured to determine the target trajectory in the third trajectory set.
  • the trajectory determination unit may also be set to:
  • the multi-objective decision-making algorithm model includes a sequentially connected casualty assessment module, an environmental damage assessment module, and an economic loss assessment module
  • the casualty assessment module is set to determine the first trajectory with the smallest casualties in the multi-objective decision-making set set
  • the environmental damage assessment module is set to determine the second set of trajectories with the smallest degree of environmental damage in the first set of trajectories
  • the economic loss target decision is set to determine the third set of trajectories with the smallest economic loss in the second set of trajectories , and output the third set of trajectories.
  • the trajectory determination unit may also be set to:
  • For each trajectory in the multi-objective decision set determine the number of casualties, environmental damage and economic loss of each trajectory based on the casualty target decision, the environmental damage target decision and the economic loss target decision respectively;
  • the target trajectory is determined based on the recommendation index of each trajectory.
  • the device further includes:
  • a data creation module configured to create an original compensation set, a storage set, and a queue before obtaining the compensation response set and the system decision set;
  • the compensation response set generation module is configured to update the original compensation set, the storage set and the queue based on the current position of the vehicle and the basic motion of the vehicle, and determine a compensation response set.
  • the compensation response set generation module can also be set to:
  • the original compensation set is updated based on the storage set and the path set to obtain a compensation response set.
  • the safety compensation device provided in the embodiment of the present application can execute the safety compensation method provided in any embodiment of the present application, and has corresponding functional modules and beneficial effects for executing the method.
  • FIG. 6 is a schematic structural diagram of an electronic device provided in Embodiment 5 of the present application.
  • FIG. 6 shows a block diagram of an exemplary electronic device 12 suitable for implementing embodiments of the present application.
  • the electronic device 12 shown in FIG. 6 is only an example, and should not limit the functions and scope of use of the embodiment of the present application.
  • electronic device 12 takes the form of a general-purpose computing device.
  • Components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, bus 18 connecting various system components including system memory 28 and processor 16.
  • Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus structures.
  • these architectures include but are not limited to Industry Standard Architecture (ISA, Industry Standard Architecture) bus, Micro Channel Architecture (MCA, Micro Channel Architecture) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA, Video Electronics Standards Association) local bus and peripheral component interconnect (PCI, Peripheral Component Interconnect) bus.
  • Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12 and include both volatile and nonvolatile media, removable and non-removable media.
  • System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM, Random Access Memory) 30 and/or cache memory 32 .
  • the electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media.
  • storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 6, commonly referred to as a "hard drive”).
  • a disk drive for reading and writing to a removable nonvolatile disk such as a "floppy disk”
  • a removable nonvolatile disk such as a CD-ROM (Compact Disc Read).
  • System memory 28 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of various embodiments of the present application.
  • a program/utility tool 36 having a set (at least one) of program modules 26 may be stored, for example, in system memory 28, such program modules 26 including but not limited to an operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include the implementation of the network environment.
  • Program modules 26 generally perform functions and/or methods in the embodiments described herein.
  • the electronic device 12 may also communicate with one or more external devices 14 (e.g., a keyboard, pointing device, display 24, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 12, and/or communicate with Any device (eg, network card, modem, etc.) that enables the electronic device 12 to communicate with one or more other computing devices. This communication can take place via an input/output (I/O, Input/Output) interface 22 .
  • the electronic device 12 can also communicate with one or more networks (such as a local area network (LAN, Local Area Network), a wide area network (WAN, Wide Area Network) and/or a public network, such as the Internet) through the network adapter 20. As shown in FIG.
  • network adapter 20 communicates with other modules of electronic device 12 via bus 18 .
  • other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID (Redundant Arrays of Independent Disks, disk array) systems, tape drives, and data backup storage systems.
  • the processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28 , for example, implementing a security compensation method provided in the embodiment of the present application.
  • Embodiment 6 of the present application also provides a storage medium containing computer-executable instructions, the computer-executable instructions are used to execute a security compensation method when executed by a computer processor, and the method includes:
  • Screening is performed on the multi-objective decision set based on multi-objective decision-making to determine a target trajectory, wherein the multi-objective decision-making includes at least a casualty target decision, and the casualty target decision is set to determine a trajectory with the least casualties.
  • the computer storage medium in the embodiments of the present application may use any combination of one or more computer-readable media.
  • the computer readable medium may be a computer readable signal medium or a computer readable storage medium.
  • a computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • the storage medium may be a non-transitory storage medium.
  • a computer readable signal medium may include a data signal carrying computer readable program code in baseband or as part of a carrier wave. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. .
  • the program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to wireless, wire, optical cable, RF (Radio Frequency, radio frequency), etc., or any suitable combination of the above.
  • Computer program codes for performing the operations of the embodiments of the present application may be written in one or more programming languages or combinations thereof, the programming languages including object-oriented programming languages—such as Java, Smalltalk, C++, including A conventional procedural programming language - such as "C" or a similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as through an Internet service provider). Internet connection).

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Traffic Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

L'invention concerne un procédé et un appareil de compensation de sécurité, ainsi qu'un support de stockage et un dispositif électronique. Le procédé de compensation de sécurité comprend les étapes suivantes : S110, acquisition d'un ensemble de réactions de compensation et d'un ensemble de décisions de système ; S120, détermination d'un ensemble de décisions à cibles multiples sur la base de l'ensemble de réactions de compensation et de l'ensemble de décisions de système ; et S130, réalisation d'un filtrage dans l'ensemble de décisions à cibles multiples sur la base d'une prise de décision à cibles multiples, de manière à déterminer une trajectoire de cible, la prise de décision à cibles multiples comprenant au moins la prise de décision de cible avec victime, et la prise de décision de cible avec victime est configurée pour déterminer une trajectoire avec un minimum de victimes. Dans le procédé, le filtrage est réalisé dans un ensemble de décision à cibles multiples sur la base d'une prise de décision à cibles multiples, de manière à obtenir une trajectoire de cible avec un minimum de victimes, de sorte que la trajectoire de cible planifiée soit plus cohérente avec les exigences sociales et éthiques.
PCT/CN2022/120838 2021-09-30 2022-09-23 Procédé et appareil de compensation de sécurité, et support de stockage et dispositif électronique WO2023051398A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111160105.XA CN113799799A (zh) 2021-09-30 2021-09-30 一种安全补偿方法、装置、存储介质及电子设备
CN202111160105.X 2021-09-30

Publications (1)

Publication Number Publication Date
WO2023051398A1 true WO2023051398A1 (fr) 2023-04-06

Family

ID=78897181

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/120838 WO2023051398A1 (fr) 2021-09-30 2022-09-23 Procédé et appareil de compensation de sécurité, et support de stockage et dispositif électronique

Country Status (2)

Country Link
CN (1) CN113799799A (fr)
WO (1) WO2023051398A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113799799A (zh) * 2021-09-30 2021-12-17 中国第一汽车股份有限公司 一种安全补偿方法、装置、存储介质及电子设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170364083A1 (en) * 2016-06-21 2017-12-21 Baidu Online Network Technology (Beijing) Co., Ltd. Local trajectory planning method and apparatus for smart vehicles
CN109669461A (zh) * 2019-01-08 2019-04-23 南京航空航天大学 一种复杂工况下自动驾驶车辆决策系统及其轨迹规划方法
CN112512887A (zh) * 2020-07-21 2021-03-16 华为技术有限公司 一种行驶决策选择方法以及装置
CN112829742A (zh) * 2020-12-30 2021-05-25 清华大学 乘员安全决策方法和装置
US20210200212A1 (en) * 2019-12-31 2021-07-01 Uatc, Llc Jointly Learnable Behavior and Trajectory Planning for Autonomous Vehicles
CN113110489A (zh) * 2021-04-30 2021-07-13 清华大学 一种轨迹规划方法、装置、电子设备和存储介质
CN113799799A (zh) * 2021-09-30 2021-12-17 中国第一汽车股份有限公司 一种安全补偿方法、装置、存储介质及电子设备

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11430071B2 (en) * 2017-08-16 2022-08-30 Mobileye Vision Technologies Ltd. Navigation based on liability constraints
DE102017216061A1 (de) * 2017-09-12 2019-03-14 Zf Friedrichshafen Ag Situationsabhängige Entscheidungsfindung für Fahrzeuge
CN109375632B (zh) * 2018-12-17 2020-03-20 清华大学 自动驾驶车辆实时轨迹规划方法
US11364936B2 (en) * 2019-02-28 2022-06-21 Huawei Technologies Co., Ltd. Method and system for controlling safety of ego and social objects
CN113031583B (zh) * 2020-03-13 2022-11-25 青岛慧拓智能机器有限公司 一种结构化道路避障方法
US11334081B2 (en) * 2020-03-20 2022-05-17 Ford Global Technologies, Llc Vehicle anomalous-condition response during autonomous driving

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170364083A1 (en) * 2016-06-21 2017-12-21 Baidu Online Network Technology (Beijing) Co., Ltd. Local trajectory planning method and apparatus for smart vehicles
CN109669461A (zh) * 2019-01-08 2019-04-23 南京航空航天大学 一种复杂工况下自动驾驶车辆决策系统及其轨迹规划方法
US20210200212A1 (en) * 2019-12-31 2021-07-01 Uatc, Llc Jointly Learnable Behavior and Trajectory Planning for Autonomous Vehicles
CN112512887A (zh) * 2020-07-21 2021-03-16 华为技术有限公司 一种行驶决策选择方法以及装置
CN112829742A (zh) * 2020-12-30 2021-05-25 清华大学 乘员安全决策方法和装置
CN113110489A (zh) * 2021-04-30 2021-07-13 清华大学 一种轨迹规划方法、装置、电子设备和存储介质
CN113799799A (zh) * 2021-09-30 2021-12-17 中国第一汽车股份有限公司 一种安全补偿方法、装置、存储介质及电子设备

Also Published As

Publication number Publication date
CN113799799A (zh) 2021-12-17

Similar Documents

Publication Publication Date Title
CN109598066B (zh) 预测模块的效果评估方法、装置、设备和存储介质
CN111860155B (zh) 一种车道线的检测方法及相关设备
US20200050894A1 (en) Artificial intelligence apparatus and method for providing location information of vehicle
KR102301631B1 (ko) 협업 주행을 수행하는 자동차들로부터 획득된 주행 이미지들을 통합하는 방법 및 이를 이용한 주행 이미지 통합 장치
CN113537445B (zh) 一种轨迹预测方法、装置、设备和存储介质
CN109635861B (zh) 一种数据融合方法、装置、电子设备及存储介质
CN113950611B (zh) 用于预测道路属性的方法和数据处理系统
JP2022023910A (ja) 通行状態取得方法及び装置、路側装置、並びに、クラウド制御プラットフォーム
WO2023051398A1 (fr) Procédé et appareil de compensation de sécurité, et support de stockage et dispositif électronique
CN116194351A (zh) 使用目标位置的代理轨迹预测
CN115861884A (zh) 复杂场景下视频多目标跟踪方法、系统、设备及介质
CN109635868B (zh) 障碍物类别的确定方法、装置、电子设备及存储介质
US11211045B2 (en) Artificial intelligence apparatus and method for predicting performance of voice recognition model in user environment
WO2023010827A1 (fr) Procédé et appareil d'apprentissage de modèle de prédiction de trajectoire basée sur une scène de migration
US20210334542A1 (en) Explainable multi-entity event recognition
US11615327B2 (en) Artificial intelligence device for providing search service and method thereof
CN116088537B (zh) 车辆避障方法、装置、电子设备和计算机可读介质
CN116343169A (zh) 路径规划方法、目标对象运动控制方法、装置及电子设备
JP2023036795A (ja) 画像処理方法、モデル訓練方法、装置、電子機器、記憶媒体、コンピュータプログラム及び自動運転車両
US11211079B2 (en) Artificial intelligence device with a voice recognition
Priya et al. Vehicle Detection in Autonomous Vehicles Using Computer Vision Check for updates
CN108944945B (zh) 用于辅助驾驶的状态预测方法、装置、电子设备和车辆
Naresh et al. Real Time Vehicle Tracking using YOLO Algorithm
Lim et al. Object Detection in Autonomous Vehicles: A Performance Analysis
CN115761815B (zh) 人体检测模型的训练方法及人体检测方法、设备、介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22874784

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE