A method for automatically driving a vehicle out of trouble and a computer device

Abstract

The present invention provides a method for an autonomous vehicle to escape from an obstacle and a computer device, comprising: determining an accident of the vehicle based on the change in the vehicle's speed, that is, if the acceleration error between the acceleration at the current moment and the acceleration at the previous moment is less than the lower limit of a set threshold range, determining that no accident has occurred; if the acceleration error is greater than or equal to the upper limit of the threshold range and there is no driving speed, determining that a serious accident has occurred; if the acceleration error is within the threshold range and there is a driving speed, determining that a minor accident has occurred; determining a steering strategy corresponding to the current degree of the accident; wherein the steering strategy is used to indicate the dominant wheel, auxiliary wheel, and wheel control information; and controlling the execution of wheel steering operations according to the steering strategy until the vehicle escapes from the obstacle. The present invention can intelligently provide different steering strategies to improve the autonomous escape capability of an autonomous vehicle when it is trapped in an accident, avoid secondary accidents during the escape process, and improve the safety performance of autonomous driving.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method for autonomous driving vehicle escape from distress and computer equipment. Background Art

[0002] Autonomous driving technology, a key application in the current field of artificial intelligence, particularly unmanned driving, has attracted extensive research and development. Within autonomous driving systems, vehicle escape is a complex process. When an autonomous vehicle is trapped in an accident, without human intervention, it often proves difficult to escape quickly and effectively.

[0003] Therefore, there is an urgent need for a solution to help autonomous vehicles escape quickly and effectively when they are trapped in an accident, so as to minimize potential losses. Summary of the Invention

[0004] In view of this, one of the purposes of the present invention is to provide a method and computer equipment for automatically escaping an autonomous driving vehicle, so as to improve the autonomous escaping capability of the autonomous driving vehicle when it is trapped in an accident, and to enhance the safety performance of the autonomous driving.

[0005] In a first aspect, the present invention provides a method for an autonomous driving vehicle to escape from an accident, the method comprising: performing an accident determination on the vehicle based on a change in the vehicle's speed, including: obtaining an acceleration error between the acceleration at a current moment and the acceleration at a previous moment; if the acceleration error is less than a lower limit value of a set threshold range, determining that the vehicle has not had an accident; if the acceleration error is greater than or equal to an upper limit value of the threshold range and there is no driving speed, determining that the vehicle has had a serious accident; if the acceleration error is within the threshold range and there is a driving speed, determining that the vehicle has had a minor accident; determining a steering strategy corresponding to the current degree of the accident; wherein the steering strategy is used to indicate the dominant wheel, auxiliary wheel, and wheel control information; and controlling the execution of wheel steering operations according to the steering strategy until the vehicle escapes from the accident.

[0006] In an optional embodiment, determining the steering strategy corresponding to the current accident severity includes: if it is a minor accident, determining the wheel closest to the accident location as the auxiliary wheel, and using the wheel at the diagonal position of the auxiliary wheel as the dominant wheel to generate the wheel control information.

[0007] In an optional embodiment, the wheel steering operation is performed according to the steering strategy control until the vehicle is out of trouble, including: controlling the dominant wheel to steer in a direction away from the accident location according to the wheel control information, and controlling and adjusting the steering of the auxiliary wheel based on the steering of the dominant wheel and the dynamic response of the vehicle.

[0008] In an optional embodiment, determining the steering strategy corresponding to the current accident severity also includes: if it is the serious accident, judging whether the wheel can execute the steering command; if the steering command cannot be executed, generating wheel control information of the trapped wheel when the state of the trapped wheel meets the preset conditions; wherein, the preset conditions are: there is only one trapped wheel, or the trapped wheels are two wheels located on the same side of the vehicle; if the steering command can be executed, determining the wheel farthest from the accident location as the dominant wheel, and the remaining wheels as auxiliary wheels, and generating wheel control information.

[0009] In an optional embodiment, the wheel steering operation is performed according to the steering strategy control until the vehicle is out of trouble, including: if the steering command cannot be executed, adjusting the turning angle of the trapped wheel according to the wheel control information so that the trapped wheel is at the optimal escape angle.

[0010] In an optional embodiment, the wheel steering operation is executed according to the steering strategy control until the vehicle is out of trouble, and also includes: if the steering command can be executed, the dominant wheel is controlled to steer in a direction away from the accident location according to the wheel control information, and the steering of the remaining wheels is adjusted according to the steering of the dominant wheel and the dynamic response control of the vehicle.

[0011] In an optional embodiment, determining the steering strategy corresponding to the current accident severity further includes: when the state of the trapped wheel does not meet a preset condition, determining that the vehicle cannot escape and outputting an alarm message.

[0012] In an optional embodiment, before determining whether the wheels can execute the steering command, the method further includes: activating an emergency escape mode; if it is detected that the vehicle has a steering failure or a drive failure, or if it is detected that the vehicle does not have the escape conditions, exiting the emergency escape mode and outputting an alarm message.

[0013] In a second aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the method for escaping an autonomous driving vehicle as described in any of the aforementioned embodiments is implemented.

[0014] An embodiment of the present invention provides a method and computer device for autonomous vehicle escape. By monitoring changes in vehicle speed in real time, the system determines that no accident has occurred if the acceleration error between the current acceleration and the previous acceleration is less than the lower limit of a set threshold range. A serious accident is determined to have occurred if the acceleration error is greater than or equal to the upper limit of the threshold range and there is no driving speed. A minor accident is determined to have occurred if the acceleration error is within the threshold range and there is driving speed. This method allows for rapid identification of whether a vehicle has been involved in an accident and its severity, enabling the immediate initiation of appropriate safety measures. Once the severity of the accident is determined, a steering strategy tailored to the severity of the accident is intelligently selected. This steering strategy not only clearly indicates which wheels should be used for primary steering and which wheels should be used for secondary steering, but also provides precise navigation for the vehicle's autonomous escape, ensuring that the vehicle can continue to follow the established strategy until it is fully free. This intelligent strategy selection can enhance the autonomous escape capability of autonomous vehicles in the event of an accident and enhance the safety of autonomous driving through precise steering control and strategy implementation.

[0015] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without making any creative efforts.

[0017] Figure 1 A schematic flowchart of a method for escaping an autonomous driving vehicle provided by an embodiment of the present invention;

[0018] Figure 2 This is an example diagram of a vehicle escaping from a minor scratch, provided by an embodiment of the present invention;

[0019] Figure 3 An example diagram of a vehicle escaping a severe collision provided by an embodiment of the present invention;

[0020] Figure 4 This is an example diagram of a vehicle getting out of a jam provided by an embodiment of the present invention;

[0021] Figure 5 An example diagram of the process of an autonomous driving vehicle getting out of trouble provided by an embodiment of the present invention;

[0022] Figure 6This is a structural block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0024] Considering that when an autonomous driving vehicle is trapped in an accident, it is often difficult to escape from danger quickly and effectively without human intervention. Based on this, an embodiment of the present invention provides an autonomous driving wheel escape method and vehicle, which are described below through examples.

[0025] It should be noted that the so-called "trapped" in the embodiments of the present invention can cover two situations: a serious accident in which the vehicle cannot move; and a minor accident in which the driving environment deteriorates but the vehicle can still continue to drive.

[0026] See Figure 1 , Figure 1 A schematic flowchart of a method for getting an autonomous vehicle out of trouble provided by an embodiment of the present invention, which method can be implemented on a computer device.

[0027] Optionally, the vehicle involved in the embodiments of the present invention may be, but is not limited to, an unmanned vehicle. The vehicle may be a three-wheeled vehicle or a four-wheeled vehicle. The embodiments of the present invention preferentially apply the autonomous vehicle escape method to four-wheeled vehicles.

[0028] like Figure 1 As shown, the method mainly includes steps S101 to S103, which are described as follows:

[0029] S101: Determining an accident for the vehicle based on a change in vehicle speed, including: obtaining an acceleration error between the current acceleration and the previous acceleration; if the acceleration error is less than a lower limit of a set threshold range, determining that the vehicle has not been in an accident; if the acceleration error is greater than or equal to an upper limit of the threshold range and there is no driving speed, determining that the vehicle has been in a serious accident; if the acceleration error is within the threshold range and there is a driving speed, determining that the vehicle has been in a minor accident;

[0030] S102: Determine a steering strategy corresponding to the current accident severity;

[0031] The steering strategy is used to indicate the dominant wheel, auxiliary wheel and wheel control information;

[0032] S103: Execute wheel steering operations according to the steering strategy control until the vehicle is out of trouble.

[0033] The above-mentioned autonomous vehicle escape method provided by an embodiment of the present invention determines an accident by monitoring the vehicle's speed change. Specifically, it includes: obtaining the acceleration error between the current acceleration and the previous acceleration; if the acceleration error is less than the lower limit of a set threshold range, the vehicle is determined to have not been in an accident; if the acceleration error is greater than or equal to the upper limit of the threshold range and there is no driving speed, the vehicle is determined to have been in a serious accident; if the acceleration error is within the threshold range and there is driving speed, the vehicle is determined to have been in a minor accident. This allows the device to immediately identify whether the vehicle has been in an accident and the severity of the accident, thereby quickly triggering appropriate safety measures. Once the system determines the severity of the accident, it will determine a steering strategy corresponding to the current accident severity. This means that different accident severity requires different steering strategies. The steering strategy can indicate which vehicle wheels are in charge of steering and which wheels are in follow-up steering, providing precise guidance for the vehicle's autonomous escape and ensuring that the vehicle can continue to act according to the established strategy until it is completely out of trouble. This intelligent strategy selection can improve the autonomous escape capability of autonomous vehicles in the event of an accident and enhance the safety performance of autonomous driving through precise steering control and strategy implementation.

[0034] Next, the embodiment of the present invention will introduce and illustrate the above steps S101 to S103 in detail with reference to the relevant drawings.

[0035] In step S101, the embodiment of the present invention uses speed changes to determine whether the vehicle is currently in an accident and the severity of the accident. It is easy to understand that the vehicle driving data can be obtained during the driving process.

[0036] Among them, the vehicle driving data can be the data collected by various sensors on the vehicle during the driving process, such as but not limited to driving speed, wheel angle, surrounding obstacles, etc. The type and quantity of vehicle driving data obtained can be set according to actual conditions and are not specifically limited here.

[0037] Optionally, based on the data type required for the severity of the accident, vehicle driving data corresponding to the data type can be read from the vehicle's data memory or CAN bus. The accident severity determination can be based on comparing the acquired vehicle speed information with corresponding threshold data to determine whether the vehicle is currently in an accident or the severity of the accident.

[0038] In the embodiment of the present invention, when using speed changes to determine the current accident severity of a vehicle, the vehicle's speed and acceleration are obtained. The vehicle's speed can be the actual speed of the vehicle during travel, which can be read from the vehicle's instrument panel. Acceleration primarily includes the current acceleration and the previous acceleration. Acceleration can be obtained using an acceleration sensor installed on the vehicle.

[0039] In the embodiment of the present invention, the threshold range includes an upper limit and a lower limit, which are expressed as [a, b]. The driver can flexibly set the threshold range according to actual needs, which is not limited here.

[0040] For example, the threshold range can be set to [0.1, 0.3]. Under this setting, if the acceleration error is less than 0.1, the vehicle is considered to have not been in an accident and can maintain its current driving plan and continue forward. Conversely, if the acceleration error is greater than or equal to 0.3 and the vehicle's speed drops to zero, this indicates that the vehicle may have been in a serious accident, such as a collision, and is currently trapped. When the acceleration error falls within the range [0.1, 0.3) and the vehicle's speed is not zero, it is considered that the vehicle may have been in a minor accident, such as a minor scratch.

[0041] In other implementations, the device may also combine the vehicle's GPS data and the image information from the vehicle-mounted camera to perform accident determination. For details, please refer to the prior art and will not be described in detail here.

[0042] The threshold setting and acceleration error analysis provided by the above-mentioned implementation method can accurately and timely identify accidents and the severity of the accidents. Subsequently, corresponding steering measures can be taken based on the judgment results to ensure that the vehicle can escape in time.

[0043] In step S101, if it is determined that the vehicle has not been involved in an accident, for example, no scratches or collisions have occurred, then subsequent steps may not be performed and the vehicle continues to travel. If it is determined that the vehicle has been involved in an accident, step S102 may be performed.

[0044] In step S102, embodiments of the present invention can formulate steering strategies tailored to the severity of the accident. The steering strategy specifies the lead wheel, auxiliary wheels, and steering control information for the lead wheel. This can be understood as follows: after an accident occurs, the lead wheel will first perform a steering operation based on the steering control information, with the auxiliary wheels following suit. The purpose of the steering control information is to guide the lead wheel away from the accident location during the steering process.

[0045] In the first application scenario of this embodiment, a minor vehicle accident, such as a minor scratch, is considered. In this case, the steering strategy designed in this embodiment is to identify the wheel closest to the accident location as the auxiliary wheel, use the wheel diagonally opposite the auxiliary wheel as the dominant wheel, and generate wheel control information to ensure the vehicle can safely and effectively move away from the accident location.

[0046] Alternatively, the steering control information for the leading wheel can be determined based on a combination of parameters, including the current wheel angle, vehicle speed, and vehicle driving status. This information works together to provide the leading wheel with precise steering instructions, including the steering direction and target steering angle.

[0047] Based on the above steering strategy, in an embodiment of the present invention, step S103 can be implemented in the following manner: according to the wheel control information, the dominant wheel is controlled to steer in a direction away from the accident location, and the steering of the auxiliary wheel is synchronously adjusted according to the steering of the dominant wheel and the dynamic response of the vehicle. Such a collaborative control strategy ensures the stability and consistency of the vehicle during the steering process, and the vehicle can autonomously and quickly escape from a minor accident.

[0048] For ease of understanding, the following example uses a minor scratch as an example. Figure 2 , Figure 2 This is an example diagram of a vehicle escaping from a minor scratch provided by an embodiment of the present invention. It should be understood that Figure 2 The invention is described with reference to a four-wheeled vehicle as an example, but this does not limit the vehicles to which the present invention is applicable.

[0049] exist Figure 2 In the process, the vehicle can first identify the location of the scratch, and then determine that the theoretical scratch location is closest to the left front wheel. Then the wheel farthest away is the right rear wheel at the diagonal position of the left front wheel. Different steering controls are performed on the left front wheel and the right rear wheel respectively, and the escape efficiency is the highest.

[0050] Through the above-mentioned implementation, when a minor accident occurs, the vehicle's steering response is optimized through precise wheel control. The coordinated work of the leading wheels and the auxiliary wheels enables the vehicle to adjust its direction quickly and smoothly after a minor accident to avoid further damage.

[0051] It can be seen from the above embodiment that after determining that the vehicle has had a minor accident, the vehicle can first determine the accident location, and then determine which wheels serve as leading wheels and which serve as auxiliary wheels.

[0052] Optionally, the vehicle can utilize the equipped vision sensor to identify the accident location through visual recognition technology.

[0053] Through the above implementation, the vehicle can use the wheel farthest away to dominate the steering, and the wheel at the accident location follows, so that it can get away from the scratched surface as quickly as possible.

[0054] In a second application scenario of the embodiment of the present invention, a serious accident of a vehicle, such as a collision causing the vehicle to stop, is considered. In this case, the embodiment of the present invention formulates a steering strategy based on whether the wheels can execute the steering command.

[0055] First, the embodiment of the present invention considers that the wheels can execute steering commands. In this case, the steering strategy designed by the embodiment of the present invention is: the wheel farthest from the accident location is determined as the dominant wheel, and the remaining wheels are auxiliary wheels, and wheel control information is generated.

[0056] Based on this steering strategy, in an embodiment of the present invention, step S103 can be implemented in the following manner: according to the wheel control information, the dominant wheel is controlled to steer in a direction away from the accident location, and according to the steering of the dominant wheel and the dynamic response of the vehicle, the steering of the remaining wheels is synchronously controlled and adjusted, so that the vehicle can move away from the accident location as quickly as possible, and the remaining wheels can also assist the vehicle in getting out of trouble by following the steering.

[0057] For an intuitive understanding, see Figure 3 , Figure 3 This is an example diagram of a vehicle escaping from a severe collision provided by an embodiment of the present invention. Figure 3 In the process, the vehicle can first identify the collision location, and then determine that the left rear wheel is the farthest from the collision location, then perform steering control on the left rear wheel, and the remaining wheels follow to assist the vehicle to quickly escape.

[0058] By optimizing wheel steering control through the above implementation, the vehicle is guided safely out of the accident location. The selection of the leading wheels ensures the stability and controllability of the vehicle during steering, while the coordinated action of the auxiliary wheels further enhances the vehicle's maneuverability and flexibility.

[0059] Secondly, the embodiment of the present invention considers that the wheel cannot execute the steering command.In this case, the embodiment of the present invention will formulate the steering strategy based on the state of the trapped wheel.

[0060] On the one hand, if the state of the trapped wheel meets the preset conditions, the steering strategy provided by the embodiment of the present invention generates wheel control information for the trapped wheel. In this case, the trapped wheel is the dominant wheel, and no auxiliary wheel is designated. The preset conditions designed in the embodiment of the present invention are: there is only one trapped wheel or the trapped wheels are two wheels on the same side of the vehicle.

[0061] During the escape process, the vehicle can adjust the steering angle of the trapped wheel according to the control information of the trapped vehicle to achieve the optimal escape angle. The "optimal escape angle" is defined as the angle at which the trapped wheel has the largest contact area with the edge of the road when the vehicle is moving forward. This design can maximize friction and effectively assist the vehicle in escape.

[0062] On the other hand, if the condition of the trapped wheel fails to meet the above-mentioned preset conditions, it indicates that the vehicle may not be able to complete the process of freeing itself. In this case, the embodiment of the present invention will promptly trigger the alarm mechanism and output a warning message to prompt the driver to intervene and take manual intervention measures to help the vehicle escape from the predicament.

[0063] For an intuitive understanding, see Figure 4 , Figure 4 This is an example diagram of a vehicle getting out of trouble when it is stuck, provided by an embodiment of the present invention. Figure 4 in Figure 4 In the scenario shown, the system first identifies that the right front wheel and right rear wheel of the vehicle are stuck. Then, the system will synchronously adjust the steering angle of these two wheels to achieve the optimal escape angle, thereby assisting the vehicle to escape smoothly.

[0064] Through the above implementation, the embodiment of the present invention can formulate different steering strategies for minor accidents and serious accidents respectively, so that the vehicle can escape from trouble autonomously and quickly according to the steering strategy.

[0065] In one embodiment of the present invention, if a serious accident occurs, the following implementation methods may be performed before formulating a steering strategy:

[0066] Step a1: Activate emergency escape mode;

[0067] Step a2: If a steering fault or a driving fault is detected in the vehicle, or if it is detected that the vehicle does not have the conditions for escaping, the emergency escape mode is exited and an alarm message is output.

[0068] In this embodiment of the present invention, when emergency escape mode is activated, the system checks whether the vehicle retains the ability to steer and drive. If the vehicle loses steering or driving capabilities, this indicates that the vehicle is currently unable to free itself. In this case, the system exits emergency escape mode and prompts the driver to intervene promptly to manually free the vehicle. If the vehicle confirms that it has steering and driving capabilities, the system will further collect vehicle status information to more accurately determine whether the vehicle meets the escape conditions.

[0069] In the embodiments of the present invention, the so-called escape conditions include, but are not limited to: the vehicle's drive shaft is not broken, the motor is operating normally, the wheels are not all stuck, and the vehicle body is not trapped. If any of these conditions is not met, it indicates that the vehicle lacks the conditions for escape, and the system will also exit the emergency escape mode, requiring timely intervention by the driver.

[0070] Once the system determines that the vehicle is ready for escape, it will collect information about the vehicle's gear position, speed, and other driving conditions that may be helpful. Using this information, the system will then plan an escape route that will lead away from the accident site.

[0071] In order to facilitate the overall understanding of the embodiments of the present invention, the following describes the escape process provided by the embodiments of the present invention using two scenarios: a minor scratch and a serious collision. Figure 5 , Figure 5 This is an example diagram of the process of an autonomous driving vehicle getting out of trouble provided by an embodiment of the present invention. The main process includes:

[0072] Obtain the acceleration at the current moment and the previous moment and calculate the acceleration error, and determine whether the acceleration error is less than 0.1. If so, it means that the vehicle has not had an accident and continues to drive; if not, continue to determine whether the acceleration error is less than 0.3. If so, it means that the vehicle has had a minor scratch, identify the scratch location, and let the wheel farthest from the location take the lead in steering, and the vehicle closest to the location follows until it is away from the scratch location; if the acceleration error is greater than or equal to 0.3, first determine whether the wheel can execute the steering command. If the steering command can be executed, it means that the vehicle has had a serious collision, and the wheel farthest from the collision location will take the lead in steering, and the other wheels will follow until they are away from the collision location; if the steering command cannot be executed, determine whether the number of stuck vehicles is 1 or two wheels on the same side. If not, it means that the vehicle cannot get out of trouble, and turn on the hazard warning; if so, adjust the turning angle of the stuck vehicle to achieve the optimal escape angle to assist the vehicle in getting out of trouble.

[0073] Through the above implementation methods, the embodiments of the present invention not only improve the self-rescue efficiency of the vehicle in an emergency, enhance the safety and autonomy of the autonomous driving vehicle, but also provide technical support for the vehicle's driving in complex road conditions.

[0074] Based on the above analysis, it can be seen that the method for autonomous driving vehicle escape provided by the embodiment of the present invention can use the change of vehicle speed (including driving speed and acceleration) to monitor whether the vehicle has an accident and the severity of the accident, ensuring that the corresponding steering measures can be initiated in the first time. Secondly, for minor accidents, the embodiment of the present invention uses the two vehicles that are closest and farthest apart to perform different steering controls, which has the highest escape efficiency. For serious accidents, the embodiment of the present invention can use the wheel farthest from the accident location to lead the steering if the wheel has the ability to steer, and the other vehicles will follow the steering to complete the escape together. For the situation where the wheel has lost the ability to steer, the embodiment of the present invention can adjust the steering angle of the trapped wheel to complete the escape if the trapped wheel meets the conditions. The entire escape process can be completed autonomously by the vehicle, thereby improving the autonomous escape capability of the autonomous driving vehicle when it is trapped in an accident, and improving the safety performance of autonomous driving.

[0075] The embodiment of the present invention may also provide an autonomous driving vehicle escape device, which may be specific hardware on the vehicle or software or firmware installed on the vehicle. The autonomous driving vehicle escape device provided by the embodiment of the present invention has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the aforementioned systems, devices, and units may refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0076] See Figure 6 , Figure 6 This is a block diagram of the structure of a computer device according to an embodiment of the present invention. The computer device 60 includes a memory 601, a processor 602, and a communication interface 603. The memory 601, processor 602, and communication interface 603 are electrically connected to each other, directly or indirectly, to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines.

[0077] Optionally, the bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0078] In an embodiment of the present invention, the processor 602 may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. A general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly embodied as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor. The software module may be located in the memory 601, and the processor 602 reads the program instructions in the memory 601 and performs the steps of the above-mentioned method in conjunction with its hardware.

[0079] In an embodiment of the present invention, the memory 601 may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), or a volatile memory (Volatile Memory), such as RAM. The memory may also be any other medium that can be used to carry or store the desired program executable code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory in an embodiment of the present invention may also be a circuit or any other device that can implement a storage function, for storing instructions and / or data.

[0080] Memory 601 can be used to store software programs and modules, such as the instructions / modules of the autonomous vehicle escape device provided in an embodiment of the present invention. These can be stored in the form of software or firmware in memory 601 or embedded in the operating system (OS) of computer device 60. Processor 602 executes the software programs and modules stored in memory 601 to perform various functional applications and data processing. Communication interface 603 can be used for signaling or data communication with other node devices.

[0081] I understand. Figure 6 The structure shown is for illustration only. The computer device 60 may also include Figure 6 More or fewer components than shown, or with Figure 6 Different configurations shown. Figure 6 The components shown may be implemented in hardware, software, or a combination thereof.

[0082] Based on the above embodiments, the present invention further provides a storage medium containing a computer program. When executed by a computer, the computer program causes the computer to execute the autonomous driving vehicle escape method provided in the above embodiments. The specific implementation can be found in the method embodiments and will not be further described here.

[0083] Based on the above embodiments, embodiments of the present invention further provide a computer program that, when executed on a computer, causes the computer to execute the autonomous driving vehicle escape method provided in the above embodiments. For specific implementation, please refer to the method embodiments and will not be further described here.

[0084] The present invention also provides a computer program product comprising instructions that, when executed on a computer, cause the computer to execute the autonomous driving vehicle escape method provided in the above embodiments. The specific implementation can be found in the method embodiments and will not be further described here.

[0085] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by instructions. These instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0086] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0088] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for escaping an autonomous driving vehicle, characterized in that: The vehicle is an unmanned vehicle, and the method includes: Performing an accident determination on the vehicle based on the acceleration error and the driving speed of the vehicle, including: obtaining an acceleration error between the acceleration at a current moment and the acceleration at a previous moment; if the acceleration error is less than a lower limit of a set threshold range, determining that the vehicle has not been in an accident; if the acceleration error is greater than or equal to an upper limit of the threshold range and there is no driving speed, determining that the vehicle has been in a serious accident; if the acceleration error is within the threshold range and there is a driving speed, determining that the vehicle has been in a minor accident; Determining a steering strategy corresponding to the current accident severity; wherein the steering strategy is used to indicate the leading wheel, the auxiliary wheel, and wheel control information; The wheel steering operation is performed according to the steering strategy control until the vehicle is out of trouble.

2. The method for escaping an autonomous driving vehicle according to claim 1, wherein: Determine the steering strategy corresponding to the current accident severity, including: If it is a minor accident, the wheel closest to the accident location is determined to be the auxiliary wheel, and the wheel at the diagonal position of the auxiliary wheel is used as the dominant wheel to generate the wheel control information.

3. The method for escaping an autonomous driving vehicle according to claim 2, characterized in that: Performing wheel steering operations according to the steering strategy control until the vehicle is freed from distress includes: According to the wheel control information, the leading wheel is controlled to steer in a direction away from the accident location, and the steering of the auxiliary wheel is controlled and adjusted according to the steering of the leading wheel and the dynamic response of the vehicle.

4. The method for escaping an autonomous driving vehicle according to claim 1, wherein: Determine the steering strategy corresponding to the current accident severity, including: If it is the serious accident, determining whether the wheels can execute the steering command; If the steering command cannot be executed, wheel control information of the trapped wheel is generated if the state of the trapped wheel meets a preset condition; wherein the preset condition is: there is only one trapped wheel, or the trapped wheels are two wheels located on the same side of the vehicle; If the steering command can be executed, the wheel farthest from the accident location is determined to be the leading wheel, and the remaining wheels are determined to be auxiliary wheels, and wheel control information is generated.

5. The method for escaping an autonomous driving vehicle according to claim 4, characterized in that: Performing wheel steering operations according to the steering strategy control until the vehicle is freed from distress includes: If the steering command cannot be executed, the turning angle of the trapped wheel is adjusted according to the wheel control information so that the trapped wheel is at the best escape angle.

6. The method for escaping an autonomous driving vehicle according to claim 4, characterized in that: The method further comprises: performing wheel steering operations according to the steering strategy control until the vehicle is free from trouble; If the steering command can be executed, the leading wheel is controlled to steer in a direction away from the accident location according to the wheel control information, and the steering of the remaining wheels is adjusted according to the steering of the leading wheel and the dynamic response control of the vehicle.

7. The method for escaping an autonomous driving vehicle according to claim 4, wherein: Determine the steering strategy corresponding to the current accident severity, including: If the state of the trapped wheel does not meet the preset conditions, it is determined that the vehicle cannot be freed and an alarm message is output.

8. The method for escaping an autonomous driving vehicle according to any one of claims 4 to 6, characterized in that: Before determining whether the wheel can execute the steering command, the method further includes: Activate emergency escape mode; If it is detected that the vehicle has a steering fault or a driving fault, or if it is detected that the vehicle does not have the escape conditions, the emergency escape mode is exited and an alarm message is output.

9. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the method for escaping an autonomous driving vehicle as described in any one of claims 1 to 8 is implemented.

Images