Method and device for vehicle escape

Abstract

According to the embodiment of the invention, the invention provides a method and a device for vehicle escape. The method comprises the following steps: in response to the condition that state information of a vehicle meets a preset condition, providing a group of feature representations associated with the vehicle for a target model; determining whether the vehicle is in a trapped state based on the set of feature representations in response to the target model, and determining whether the vehicle can autonomously get rid of the trapped state; and in response to determining that the vehicle cannot autonomously get rid of the trapped state, sending an assistance request to the remote device. Therefore, according to the embodiment of the invention, whether the vehicle is in the trapped state or not can be autonomously judged, and the remote assistance request is correspondingly triggered.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, devices, apparatuses, computer-readable storage media, and computer program products for vehicle escape. Background Art

[0002] Autonomous driving is a technology that uses computers to replace human drivers or assist human drivers to perceive the vehicle's surroundings, plan the vehicle's movement trajectory, and control the vehicle to a designated destination.

[0003] During the autonomous driving process, the vehicle will follow the planned path. Due to perception problems or some unexpected factors, the vehicle may stop or be unable to continue driving. Summary of the invention

[0004] In a first aspect of the present disclosure, a method for escaping a vehicle is provided. The method comprises: in response to the state information of the vehicle satisfying a preset condition, providing a set of feature representations associated with the vehicle to a target model; in response to the target model determining that the vehicle is in a trapped state based on the set of feature representations, determining whether the vehicle can autonomously escape the trapped state; and in response to determining that the vehicle cannot autonomously escape the trapped state, sending an assistance request to a remote device.

[0005] In a second aspect of the present disclosure, a device for escaping a vehicle is provided. The device includes: a providing module configured to provide a set of feature representations associated with the vehicle to a target model in response to the state information of the vehicle satisfying a preset condition; a determining module configured to determine whether the vehicle can autonomously escape from the trapped state in response to the target model determining that the vehicle is in a trapped state based on the set of feature representations; and a sending module configured to send an assistance request to a remote device in response to determining that the vehicle cannot autonomously escape from the trapped state.

[0006] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the device executes the method of the first aspect or the second aspect.

[0007] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0008] In a fifth aspect of the present disclosure, a computer program product is provided, which includes computer executable instructions, and when the computer executable instructions are executed by a processor, the method of the first aspect is implemented.

[0009] It should be understood that the contents described in the summary of the present invention are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0011] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0012] Figure 2 A flowchart showing an example process for vehicle extrication according to some embodiments of the present disclosure is shown;

[0013] Figure 3 A schematic structural block diagram of a device for escaping a vehicle according to certain embodiments of the present disclosure is shown; and

[0014] Figure 4 A block diagram of a device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0015] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0016] It should be noted that the titles of any sections / subsections provided herein are not restrictive. Various embodiments are described throughout this article, and any type of embodiment may be included under any section / subsection. In addition, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0017] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0018] The embodiments of the present disclosure may involve user data, data acquisition and / or use, etc. These aspects are subject to the corresponding laws, regulations and relevant provisions. In the embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user knows and confirms. Accordingly, when implementing each embodiment of the present disclosure, the type, scope of use, usage scenario, etc. of the data or information that may be involved should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with the relevant laws and regulations. The specific notification and / or authorization method can vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this respect.

[0019] In this specification and the embodiments, if personal information processing is involved, it will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or it is necessary to perform a contract, etc.), and will only be processed within the scope of regulations or agreements. If a user refuses to process personal information other than the necessary information for basic functions, it will not affect the user's use of basic functions.

[0020] As used herein, the term "model" can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multiple layers of processing units. In this article, "model" may also be referred to as "machine learning model", "machine learning network" or "network", and these terms are used interchangeably in this article.

[0021] As briefly mentioned above, due to the ever-changing environment or errors in the vehicle's environmental perception system, obstacles that the autonomous vehicle cannot accurately identify may appear on the planned path, causing the autonomous vehicle to stagnate or be unable to continue driving.

[0022] One of the modes of vehicle failure is called "stuck", which means that the autonomous vehicle is unable to continue driving the current route through autonomous driving and stops, which may cause the autonomous vehicle to be unable to continue to complete subsequent trips and may cause adverse effects on traffic.

[0023] Traditional solutions have difficulty autonomously determining whether a vehicle is in distress and rely on a safety officer or driver to initiate a remote assistance request, which makes it impossible for autonomous vehicles to operate effectively without a human in the vehicle.

[0024] The embodiments of the present disclosure propose a solution for vehicle escape. According to various embodiments of the present disclosure, in response to the state information of the vehicle satisfying a preset condition, a set of feature representations associated with the vehicle is provided to a target model; in response to the target model determining that the vehicle is in a trapped state based on the set of feature representations, it is determined whether the vehicle can escape the trapped state autonomously; and in response to determining that the vehicle cannot escape the trapped state autonomously, a request for assistance is sent to a remote device.

[0025] Thus, the embodiments of the present disclosure can autonomously determine whether the vehicle is in a trapped state and trigger a remote assistance request accordingly. Based on this approach, the embodiments of the present disclosure can help unmanned vehicles get rid of their dependence on drivers or safety officers, and further improve the reliability of unmanned vehicles.

[0026] Example Environment

[0027] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. In the environment 100, an assisting person 110 can interact with a remote device 120 directly or with an attached device via the remote device 120. The remote device 120 can present a user interface 140 to the assisting person 110 for the assisting person 110 to view vehicle information or perform route planning and other operations.

[0028] The remote device 120 may include, for example, a cloud device or an edge computing device. In some embodiments, such a remote device 120 may be configured to provide the vehicle 101 with supplementary perception information about the traffic environment, and / or provide escape guidance for the trapped vehicle 101.

[0029] Environment 100 may include vehicle 101. In some embodiments, vehicle 101 may be any type of vehicle that can carry people and / or objects and move through a power system such as an engine, including but not limited to cars, trucks, buses, electric vehicles, RVs, etc. Vehicle 101 may be an autonomous driving vehicle (also called an autonomous vehicle) that integrates functions such as environmental perception, planning and decision-making, and multi-level assisted driving.

[0030] like Figure 1 As shown, the vehicle 101 is equipped with an electronic device 150, which can be connected to the remote device 120. For example, the electronic device 150 can communicate with the remote device 120 via an appropriate wireless communication method. The electronic device 150 can be any device with computing capabilities, and can generate a driving route for escape or execute corresponding instructions according to the path planning information sent by the remote device 120.

[0031] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and does not imply any limitation on the scope of the present disclosure.

[0032] Example Process

[0033] Figure 2 1 shows a schematic diagram of a process 400 for assisting a vehicle to escape from distress according to some embodiments of the present disclosure. The process 200 may be implemented at an electronic device 150 associated with the vehicle 101. Figure 1 Process 200 is described.

[0034] like Figure 2 As shown, in box 210, the electronic device 150 determines whether the status information of the vehicle 101 meets a preset condition.

[0035] In some embodiments, the status information of the vehicle 101 may include the driving mode of the vehicle, for example, whether it is in the automatic driving mode. Alternatively or additionally, the status information of the vehicle 101 may also include the health status of a set of preset modules of the vehicle, that is, whether they are in a normal working state. Alternatively or additionally, the status information of the vehicle 101 may also include the speed information of the vehicle 101.

[0036] In some embodiments, such a preset condition may include that the vehicle 101 is in an automatic driving mode. Alternatively or additionally, the preset condition may also include that a set of preset modules of the vehicle 101 are in a normal working state. Alternatively or additionally, the preset condition may also include that the speed of the vehicle 101 is lower than a threshold.

[0037] In some embodiments, only when these preset conditions are met, the electronic device 150 can trigger the determination of whether the vehicle 101 is in a trapped state. Figure 2 As shown, process 200 may proceed to block 260, ie, electronic device 150 may not initiate remote assistance.

[0038] Further, if the preset condition is met, then in box 220, the electronic device 150 may provide the target model with a set of feature representations associated with the vehicle 101. In some embodiments, such a target model may be deployed locally on the electronic device 150, or may be deployed at other appropriate electronic devices, such as an edge device or a server.

[0039] In some embodiments, such a target model can be implemented based on an appropriate machine learning model to predict whether the vehicle is in a trapped state based on the feature representation of the vehicle. Exemplarily, such a target model can be a binary classification model to predict whether the vehicle is in a trapped state or a non-trapped state.

[0040] In some embodiments, the set of feature representations provided to the target model may include a first set of feature representations for indicating state information of the vehicle 101. Such a first feature representation may also be referred to as vehicle state-related features, for example.

[0041] Exemplarily, such status information may include one or more states such as those introduced above: whether the vehicle is in autonomous driving mode, the health status of a set of preset modules of the vehicle, the speed of the vehicle, etc.

[0042] In some embodiments, the set of feature representations provided to the target model may include, for example, a second set of feature representations for indicating the traffic environment of the vehicle 101. The second set of feature representations may also be referred to as traffic condition-related features.

[0043] In some embodiments, the second set of feature representations may, for example, indicate lane information associated with the vehicle 101. Exemplarily, the second set of feature representations may indicate a lane trajectory of the vehicle, i.e., one or more lanes involved in the planned trajectory of the vehicle. Alternatively, such lane information may include lane boundaries of such one or more lanes. For example, the lane boundaries may be determined based on map information.

[0044] In some embodiments, the second set of feature representations may indicate traffic light information associated with the vehicle 101. For example, the traffic light information may include information such as the light state of the traffic light, the distance from the vehicle 101 to the stop line corresponding to the traffic light, and the like.

[0045] In some embodiments, the second set of feature representations may also indicate obstacle information associated with the vehicle 101. Such obstacle information may, for example, be used to indicate static and dynamic obstacles in the traffic environment of the vehicle 101. Such obstacle information may, for example, include but is not limited to information such as the type, boundary, location, and speed of the obstacle.

[0046] In some embodiments, the set of feature representations includes a third set of feature representations for indicating the vehicle's traffic capability. The third set of feature representations may also be referred to as vehicle capability-related features.

[0047] In some embodiments, the third set of feature representations may indicate constraint information associated with the longitudinal constraint of the vehicle 101. Specifically, the electronic device 150 may, for example, determine the planned route of the vehicle 101, and may accordingly construct a spatiotemporal graph of the vehicle 101. Further, the electronic device 150 may determine the main obstacles that affect the vehicle 101 in the longitudinal direction of the vehicle 101 based on the spatiotemporal graph. Accordingly, the electronic device 150 may determine information such as the type, speed, relative speed, position, and distance to the vehicle 101 of the main obstacle as constraint information associated with the longitudinal constraint of the vehicle 101.

[0048] In some embodiments, the third set of feature representations may indicate a drivable area of ​​the vehicle 101. For example, the electronic device 150 may determine the boundary of the drivable area of ​​the vehicle 101 based on the perception information of the vehicle 101, and determine the third set of feature representations based on the boundary.

[0049] In some embodiments, the third set of feature representations may also indicate interaction information between the vehicle 101 and dynamic traffic objects.

[0050] Specifically, the electronic device 150 may determine at least one dynamic traffic object associated with the planned route of the vehicle. As an example, after determining the planned route of the vehicle 101, the electronic device 110 may project the position and speed of the dynamic traffic object in the traffic environment to the planned route for calculation in the SL coordinate system.

[0051] Further, the electronic device 150 may determine at least one dynamic traffic object that affects the planned route of the vehicle 101. Accordingly, the electronic device 150 may determine the interaction information between the vehicle 101 and the dynamic traffic object based on the position and / or speed of the at least one dynamic traffic object.

[0052] In some embodiments, dynamic traffic objects with different relative distances and / or relative speeds may have different weights, for example. Such weights may be set, for example, by means of hyperparameters to increase the speed of model convergence.

[0053] In some embodiments, considering that the trapped scene of the vehicle has a strong temporal nature, the target model may also consider temporal related features. Specifically, the set of features acquired by the target model represents that it is generated based on a first set of information associated with the current moment and a second set of information associated with at least one historical moment.

[0054] For example, the electronic device 150 may provide not only features related to the current frame of the vehicle 101 , but also features of a predetermined number of frames before, thereby improving the accuracy of the distress prediction.

[0055] Further, the electronic device 150 may obtain a prediction result determined by the target model based on the provided set of input features to indicate whether the vehicle 101 is in a trapped state.

[0056] Based on this approach, the embodiments of the present disclosure can support autonomous determination of whether the vehicle is in a trapped state, thereby further getting rid of dependence on the driver or safety officer, thereby improving the reliability of unmanned driving.

[0057] Continue to refer Figure 2 In block 230 , the electronic device 150 may obtain the prediction result of the target model to determine whether the vehicle 101 is in a trapped state. If the vehicle 101 is not in a trapped state, the electronic device 150 may not initiate remote assistance.

[0058] In contrast, if the target model determines that the vehicle 101 is in a trapped state, the process 200 may proceed to block 240. Specifically, the electronic device 150 further determines whether the vehicle 101 is able to autonomously escape from the trapped state.

[0059] In some embodiments, the vehicle 101 may be equipped with at least one autonomous escape module. Such an autonomous escape module may be capable of determining whether the vehicle 101 is in an trapped state based on corresponding judgment logic, and executing autonomous escape control of the vehicle according to corresponding strategies. For example, such an autonomous escape module may include a creeping module, a borrowing lane module, and the like.

[0060] Specifically, the electronic device 150 may first determine whether such at least one autonomous escape module detects the trapped state of the vehicle 101. If the at least one autonomous escape module fails to detect the trapped state of the vehicle 101 within the first period of time, the electronic device 150 may determine that the vehicle 101 cannot autonomously escape the trapped state.

[0061] In some embodiments, if at least one autonomous escape module detects the trapped state of the vehicle 101 within the first period, the electronic device 150 may further determine whether the vehicle can escape the trapped state by using the at least one autonomous escape module within the second period.

[0062] For example, the electronic device 150 may determine whether autonomous escape modules such as a creeping module and a borrowing lane module are able to plan an escape route within a predetermined period of time, and control the vehicle to perform an escape process.

[0063] In some embodiments, if the electronic device 150 determines that the vehicle 101 cannot escape the trapped state by using at least one autonomous escape module within the second period of time, the electronic device 150 may determine that the vehicle 101 cannot escape the trapped state.

[0064] Accordingly, process 200 may proceed to block 250. Electronic device 150 may send an assistance request to remote device 120. In contrast, if vehicle 101 is able to autonomously escape from the escape state, electronic device 150 may not initiate remote assistance, for example.

[0065] Based on this approach, the embodiments of the present disclosure can autonomously determine whether the vehicle needs to initiate remote assistance, thereby getting rid of dependence on drivers or safety officers and improving the degree of unmanned operation of the vehicle.

[0066] In some embodiments, the electronic device 150 may also receive an assistance message from the remote device 120 for guiding the vehicle 101 to escape from distress. Accordingly, the electronic device 150 may control the vehicle 101 to escape from distress based on the assistance message. The present disclosure is not intended to limit the specific process of generating the assistance message and escaping from distress.

[0067] As mentioned above, the electronic device 150 can use the target model to predict whether the vehicle 101 is in a trapped state. The training process of the target model will be further described below. It should be understood that the training of the target model can be performed using any appropriate training device.

[0068] In some embodiments, the training device constructs a training sample set for training the target model according to the simulation process of the autonomous driving, and uses the training sample set to train the model. Such a training sample set may include, for example, a set of positive samples marked as trapped scenes and a set of negative samples marked as non-trapped scenes. Such a positive sample may indicate, for example, that the vehicle can be manually judged to be autonomous, but the autonomous driving system controls the vehicle to stop.

[0069] In some embodiments, such a training sample set may, for example, cover a variety of traffic scenarios such as going straight, changing lanes, turning, U-turn, unprotected left turn, etc. Additionally, the number of negative samples may, for example, be greater than the number of positive samples.

[0070] In some embodiments, for the simulation process, the training device can preliminarily mark whether the vehicle is in a trapped state according to whether the autonomous driving system remains stationary for a predetermined period of time. Further, such machine-marked information can be optimized, for example, by using manual marking or other methods.

[0071] In some embodiments, the training device may also construct at least one negative sample based on a simulation process of a set of preset traffic scenarios. Such a set of preset traffic scenarios includes a parking scenario associated with a traffic stop signal, for example, a vehicle is stopped because it is waiting for a red light.

[0072] As another example, the preset traffic scene may include a parking scene associated with vehicle cruising, vehicle lane changing, or vehicle following. For example, the vehicle may also be in a parking state in a scene of looping, lane changing, or normal following.

[0073] As another example, the preset traffic scenario may include a parking scenario associated with an abnormal state of the vehicle. For example, in the case of an abnormality in the perception module, decision module, control module, etc. of the vehicle, the vehicle cannot continue to drive automatically and is in a parking state.

[0074] Based on this approach, the embodiments of the present disclosure can construct a training sample set based on the simulation process of the autonomous driving program, thereby reducing the training cost of the target model.

[0075] Example devices and equipment

[0076] Figure 3 A schematic structural block diagram of an apparatus 300 for vehicle escape according to certain embodiments of the present disclosure is shown. The apparatus 300 may be implemented as or included in an electronic device 120 associated with the vehicle 101. Each module / component in the apparatus 300 may be implemented by hardware, software, firmware, or any combination thereof.

[0077] As shown in the figure, the device 300 includes a providing module 310, which is configured to provide a set of feature representations associated with the vehicle to the target model in response to the vehicle's status information satisfying a preset condition; a determining module 320, which is configured to determine whether the vehicle can autonomously escape the trapped state in response to the target model determining that the vehicle is in a trapped state based on a set of feature representations; and a sending module 330, which is configured to send an assistance request to a remote device in response to determining that the vehicle cannot autonomously escape the trapped state.

[0078] In some embodiments, the preset conditions include at least one of the following: the vehicle is in automatic driving mode; a set of preset modules of the vehicle are in normal working condition; the speed of the vehicle is lower than a threshold.

[0079] In some embodiments, the set of feature representations includes a first set of feature representations for indicating status information of a vehicle.

[0080] In some embodiments, the set of feature representations includes a second set of feature representations indicating a traffic environment of the vehicle.

[0081] In some embodiments, the second set of feature representations indicates at least one of: lane information associated with the vehicle; traffic light information associated with the vehicle; obstacle information associated with the vehicle.

[0082] In some embodiments, the set of feature representations includes a third set of feature representations indicating a vehicle's traffic capabilities.

[0083] In some embodiments, the third set of feature representations indicates at least one of: constraint information associated with a longitudinal constraint of the vehicle; a drivable area of ​​the vehicle; and interaction information between the vehicle and a dynamic traffic object.

[0084] In some embodiments, the apparatus 300 further includes an information determination module configured to determine at least one dynamic traffic object associated with the planned route of the vehicle; and determine interaction information based on a position and / or speed of the at least one dynamic traffic object.

[0085] In some embodiments, a set of feature representations is generated based on a first set of information associated with a current moment and a second set of information associated with at least one historical moment.

[0086] In some embodiments, the target model is trained based on the following process: obtaining a training sample set generated based on a simulation process, the training sample set including a group of positive samples and a group of negative samples; and training the target model using the training samples.

[0087] In some embodiments, obtaining a training sample set generated based on a simulation process includes: constructing at least one negative sample based on a simulation process of a set of preset traffic scenarios, wherein the set of preset traffic scenarios includes at least one of the following: a parking scene associated with a traffic stop signal, a parking scene associated with vehicle cruising, vehicle lane changing or vehicle following, and a parking scene associated with an abnormal state of a vehicle.

[0088] In some embodiments, the determination module 320 is further configured to: determine whether at least one autonomous escape module of the vehicle detects the trapped state of the vehicle; and determine that the vehicle cannot escape the trapped state in response to at least one autonomous escape module not detecting the trapped state of the vehicle within a first time period.

[0089] In some embodiments, the determination module 320 is further configured to: determine whether the vehicle can use at least one autonomous escape module to escape the trapped state within a second time period in response to at least one autonomous escape module detecting the trapped state of the vehicle within a first time period; and determine that the vehicle cannot escape the trapped state in response to the vehicle being unable to use at least one autonomous escape module to escape the trapped state within the second time period.

[0090] In some embodiments, the apparatus 300 further includes a receiving module configured to receive an assistance message from a remote device for guiding the vehicle to escape from distress.

[0091] Figure 4 A block diagram illustrating a computing device 400 in which one or more embodiments of the present disclosure may be implemented is shown. It should be understood that Figure 4 The computing device 400 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 4 The computing device 400 shown may be used to implement Figure 1 remote device 120 or electronic device 150.

[0092] like Figure 4 As shown, computing device 400 is in the form of a general-purpose computing device. Components of computing device 400 may include, but are not limited to, one or more processors or processing units 410, memory 420, storage device 430, one or more communication units 440, one or more input devices 450, and one or more output devices 460. Processing unit 410 may be an actual or virtual processor and is capable of performing various processes according to a program stored in memory 420. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to increase the parallel processing capabilities of computing device 400.

[0093] The computing device 400 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the computing device 400, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 420 may be a volatile memory (e.g., a register, a cache, a random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 430 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data (e.g., training data for training) and may be accessed within the computing device 400.

[0094] The computing device 400 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 4As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 420 may include a computer program product 425 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0095] The communication unit 440 enables communication with other computing devices via a communication medium. Additionally, the functions of the components of the computing device 400 can be implemented in a single computing cluster or multiple computing machines that can communicate via a communication connection. Therefore, the computing device 400 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0096] Input device 450 may be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 460 may be one or more output devices, such as a display, speaker, printer, etc. Computing device 400 may also communicate with one or more external devices (not shown) through communication unit 440 as needed, such as storage devices, display devices, etc., with one or more devices that allow a user to interact with computing device 400, or with any device that allows computing device 400 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0097] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0098] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0099] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0100] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0101] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0102] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for escaping a vehicle, comprising: In response to the state information of the vehicle satisfying a preset condition, providing a set of feature representations associated with the vehicle to the target model; In response to the target model determining that the vehicle is in a trapped state based on the set of feature representations, determining whether the vehicle can autonomously escape from the trapped state; as well as In response to determining that the vehicle is unable to autonomously escape the entrapment condition, a request for assistance is sent to a remote device.

2. The method according to claim 1, wherein the preset condition comprises at least one of the following: The vehicle is in an autonomous driving mode; A set of preset modules of the vehicle are in normal working condition; The speed of the vehicle is below a threshold. 3 . The method of claim 1 , wherein the set of feature representations includes a first set of feature representations for indicating the state information of the vehicle. The method of claim 1 , wherein the set of feature representations includes a second set of feature representations indicating a traffic environment of the vehicle.

5. The method of claim 4, wherein the second set of feature representations indicates at least one of the following: lane information associated with the vehicle; traffic light information associated with the vehicle; Obstacle information associated with the vehicle. The method of claim 1 , wherein the set of feature representations includes a third set of feature representations indicating a traversability of the vehicle.

7. The method of claim 6, wherein the third set of features indicates at least one of: restraint information associated with a longitudinal restraint of the vehicle; a drivable area of ​​the vehicle; The interaction information between the vehicle and the dynamic traffic object.

8. The method according to claim 7, further comprising: determining at least one dynamic traffic object associated with a planned route of the vehicle; The interaction information is determined based on the position and / or speed of the at least one dynamic traffic object.

9. The method of claim 1, wherein the set of feature representations is generated based on a first set of information associated with a current moment and a second set of information associated with at least one historical moment.

10. The method of claim 1, wherein the target model is trained based on the following process: Acquire a training sample set generated based on a simulation process, wherein the training sample set includes a group of positive samples and a group of negative samples; and The target model is trained using the training samples.

11. The method according to claim 10, wherein obtaining a training sample set generated based on a simulation process comprises: Based on the simulation process of a set of preset traffic scenarios, at least one negative sample is constructed. The set of preset traffic scenarios includes at least one of the following: parking scenarios associated with traffic stop signals, Parking scenarios associated with vehicle cruising, vehicle lane changing, or vehicle following, Parking scenarios associated with abnormal states of the vehicle.

12. The method of claim 1, wherein determining whether the vehicle can autonomously escape from the trapped state comprises: determining whether at least one autonomous escape module of the vehicle detects the trapped state of the vehicle; as well as In response to the at least one autonomous escape module not detecting the trapped state of the vehicle within a first period of time, it is determined that the vehicle cannot autonomously escape the trapped state.

13. The method of claim 12, wherein determining whether the vehicle can autonomously escape from the trapped state comprises: In response to the at least one autonomous escape module detecting the trapped state of the vehicle within the first time period, determining whether the vehicle can escape the trapped state by using the at least one autonomous escape module within a second time period; as well as In response to the vehicle being unable to escape the trapped state using the at least one autonomous escape module within the second period of time, it is determined that the vehicle is unable to autonomously escape the trapped state.

14. The method according to claim 1, further comprising: An assistance message for guiding the vehicle to get out of trouble is received from the remote device.

15. A device for assisting a vehicle to escape from distress, comprising: A providing module, configured to provide a set of feature representations associated with the vehicle to a target model in response to the state information of the vehicle satisfying a preset condition; a determination module configured to determine whether the vehicle can autonomously escape from the trapped state in response to the target model determining that the vehicle is in a trapped state based on the set of feature representations; as well as The sending module is configured to send an assistance request to a remote device in response to determining that the vehicle cannot escape the trapped state autonomously.

16. An electronic device, comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 14 when executed by the at least one processing unit.

17. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 14.

18. A computer program product comprising computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 14.

Images