A memory-based parking obstacle avoidance method, device, equipment, medium, and product

Abstract

This application provides a memory-based parking obstacle avoidance method, device, equipment, medium, and product, belonging to the field of intelligent driving application technology. The method acquires and stores the vehicle's driving path during obstacle avoidance; when the vehicle cannot continue obstacle avoidance, it controls the vehicle to return to its starting position according to the stored driving path; when the vehicle can avoid the obstacle again, it controls the vehicle to restart obstacle avoidance. This avoids the problems of traditional braking strategies in this scenario, where the system automatically exits when the braking time exceeds the system's set time threshold, greatly reducing the user experience and potentially causing traffic congestion. It increases the success rate of memory-based parking, enriches the user experience, and significantly reduces traffic congestion.

Description

Technical Field

[0001] This application relates to the field of intelligent driving application technology, and in particular to a memory parking obstacle avoidance method, device, equipment, medium and product. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Memory parking uses a pre-built parking map system to control the vehicle to drive into a designated parking space along the original parking route. However, when using the memory parking system to control the vehicle's cruise and encountering obstacles while attempting to maneuver around them, problems often arise such as oncoming vehicles or other dynamic obstacles preventing the vehicle from continuing the obstacle maneuver.

[0004] Currently, when the memory parking system executes obstacle avoidance strategies, if it encounters oncoming vehicles or other dynamic obstacles that prevent the vehicle from continuing its obstacle avoidance, it basically adopts a strategy of controlling the vehicle to stop. This strategy has the problem that if the stopping time exceeds the system's set time threshold, the system will automatically exit, which greatly reduces the user experience and may also cause traffic congestion accidents to a certain extent. Summary of the Invention

[0005] This application provides a memory-based parking obstacle avoidance method, device, equipment, medium, and product, which can solve the problem in related technologies where the vehicle cannot continue obstacle avoidance, and after the vehicle is brought to a stop, the system is forced to exit within a certain threshold time, ultimately causing traffic congestion. The technical solution is as follows:

[0006] On the one hand, a memory-based parking obstacle avoidance method is provided, including:

[0007] During the memory parking process, after the vehicle begins to navigate around obstacles, the driving path of the vehicle during the obstacle-avoidance process is acquired and stored.

[0008] When the vehicle is unable to continue its obstacle avoidance maneuver, control the vehicle to return to the starting position of the obstacle avoidance maneuver according to the stored driving path;

[0009] When the vehicle can perform obstacle avoidance again, control the vehicle to start obstacle avoidance again.

[0010] In some embodiments, during the process of controlling the vehicle to retreat to the starting position of the obstacle avoidance according to the stored driving path, it is determined whether there are pedestrians or dynamic vehicles within the safe distance behind the vehicle; when it is determined that there are pedestrians or dynamic vehicles within the safe distance behind the vehicle, the vehicle is controlled to stop; after the pedestrians or dynamic vehicles leave the safe distance behind the vehicle, the vehicle is controlled to continue to perform the operation of retreating to the starting position of the obstacle avoidance.

[0011] In some embodiments, once the vehicle completes its obstacle avoidance maneuver, the driving path stored during the obstacle avoidance process is cleared.

[0012] In some embodiments, during obstacle avoidance, the vehicle's coordinates and heading angle are acquired in real time, and the vehicle's driving path is obtained based on the vehicle's coordinates and heading angle.

[0013] In some embodiments, during the memory parking process, data on the vehicle's surrounding environment is acquired;

[0014] Based on the surrounding environmental data, determine whether the vehicle needs to navigate around obstacles;

[0015] Once it is determined that the vehicle needs to go around an obstacle, control the vehicle to begin going around the obstacle.

[0016] In some embodiments, based on the surrounding environment data of the vehicle, it is determined whether there are pedestrians or vehicles within a safe distance in front of the vehicle; when there are pedestrians within a safe distance in front of the vehicle, the vehicle is controlled to stop; when there are vehicles within a safe distance in front of the vehicle, the vehicle is controlled to perform a following action with the vehicle as the target.

[0017] On the other hand, a memory parking obstacle avoidance device is provided, including:

[0018] The acquisition module is used to acquire and store the driving path of the vehicle during the obstacle avoidance process after the vehicle starts to avoid obstacles during the memory parking process;

[0019] The control module is used to control the vehicle to return to the starting position of the obstacle course according to the stored driving path when the vehicle cannot continue to perform obstacle course; and to control the vehicle to start obstacle course again when the vehicle can perform obstacle course again.

[0020] On the other hand, a control device is provided, the control device including one or more processors and one or more memories, the one or more memories storing at least one piece of program code, the at least one piece of program code being loaded and executed by the one or more processors to implement a memory-based parking obstacle avoidance method as described in any of the above implementations.

[0021] On the other hand, a computer-readable storage medium is provided, wherein at least one piece of program code is stored in the computer-readable storage medium, the at least one piece of program code being loaded and executed by a processor to implement a memory-based parking obstacle avoidance method as described in any of the above implementations.

[0022] On the other hand, a computer program product is provided, the computer program product including computer program code stored in a computer-readable storage medium, a processor of a control device reading the computer program code from the computer-readable storage medium, the processor executing the computer program code, causing the control device to execute a memory-based parking obstacle avoidance method as described in any of the above implementations.

[0023] The technical solution provided in this application can bring at least the following beneficial effects:

[0024] In this application, during obstacle avoidance, the vehicle's driving path is acquired and stored. When the vehicle cannot continue obstacle avoidance, it is controlled to return to its starting position according to the stored driving path. When the vehicle can continue obstacle avoidance, it is controlled to restart the obstacle avoidance. This avoids the problem of traditional braking strategies in this scenario, where the system automatically exits when the braking time exceeds the system's set time threshold, greatly reducing the user experience and potentially causing traffic congestion. This increases the success rate of memory parking, enriches the user experience, and significantly reduces traffic congestion. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 A flowchart of a memory-based parking obstacle avoidance method provided in this application embodiment;

[0027] Figure 2 A dead reckoning principle diagram of a memory-based parking obstacle avoidance method provided in this application embodiment;

[0028] Figure 3 This is a schematic diagram of the return path of a memory parking obstacle avoidance method provided in an embodiment of this application;

[0029] Figure 4 A strategy flowchart of a memory-based parking obstacle avoidance method provided in an embodiment of this application;

[0030] Figure 5 This is a system architecture diagram of a memory parking obstacle avoidance device provided in an embodiment of this application.

[0031] This application provides a schematic diagram of the architecture of a remote reservation boarding control device. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0033] Before providing a detailed explanation of the memory parking obstacle avoidance method provided in the embodiments of this application, the application scenarios and system architecture provided in the embodiments of this application will be introduced first.

[0034] First, the application scenarios involved in the embodiments of this application will be introduced.

[0035] Currently, to prevent collisions during parking, cars use ultrasonic sensors and cameras to detect obstacles around the vehicle and brake to a stop when an obstacle is detected. However, if the braking time exceeds a pre-set threshold, the system automatically disengages, significantly reducing the user experience and potentially causing traffic congestion.

[0036] Based on this application scenario, this application provides a memory-based parking obstacle avoidance method.

[0037] Finally, the system architecture involved in the embodiments of this application will be described.

[0038] Figure 5 A system architecture diagram of a memory parking obstacle avoidance device provided in this application embodiment is shown below. Figure 5 The system includes a vehicle controller and multiple sensors for sensing the vehicle's surrounding environment.

[0039] The vehicle controller includes the following modules: 1) Memory parking system controller, which includes functions such as panoramic imaging, parking distance detection, memory parking, adaptive cruise control, highway navigation assistance, and automatic emergency braking. The memory parking system controller integrates environmental perception algorithms to classify information about the vehicle's surroundings, such as pedestrians, vehicles (moving or stationary), trash cans, traffic cones, etc., and makes different response strategies based on this classified information during the parking process. For example, when a pedestrian is detected in front of the vehicle, the system controls the vehicle to stop and waits for the pedestrian to move away from the vehicle to a safe distance. After leaving, the parking operation continues; when a vehicle is detected, the system will perform deceleration or acceleration strategies based on the speed and distance of the vehicle in front, etc.; in addition, the memory parking system controller can also obtain the distance values ​​between the vehicle and objects in the surrounding environment, and the system will perform corresponding parking operations based on the obtained distances; 2) ESP (Electronic Stability Program) is an important actuator to ensure longitudinal control of driving after parking is completed. During the parking process, ESP controls the vehicle speed smoothly by controlling braking pressure, requesting engine torque, and requesting gear shifts according to the acceleration commands of the memory parking system; at the same time, after parking is completed, ESP can maintain The vehicle is stationary, and the EPB (Electronic Parking Brake) system is activated for parking; simultaneously ensuring the reliability of acceleration and gear selection during parking, and braking the vehicle to a stop in extreme situations of unexpected acceleration and gear shifting; 3) The EPS (Electronic Steering Controller) is the actuator that controls the lateral movement of the vehicle during parking. During parking, the memory parking system sends steering angle commands to the EPS, which executes the corresponding steering requests to complete the parking operation, while ensuring the reliability of vehicle steering and the suppression of unexpected steering; 4) The BCM (Body Control Module) controls and ensures that all four doors and two hoods are closed, and the windows and sunroof are closed during parking. Functions include closing doors, locking doors, turning on headlights, and honking the horn; 5) The TCU (Transmission Control Unit) responds to the ESP's shift requests during parking, and promptly notifies the parking system and ESP of unexpected gear malfunctions caused by driver intervention or other circumstances, ensuring parking safety; 6) The EMS (Engine Management System) provides power output during parking, the ESP sends control torque to the EMS, the EMS outputs the current virtual accelerator pedal position to the TCU, and finally the TCU internally calculates and feeds back the torque limit value and the idle torque required for vehicle start-up to the EMS, thereby ensuring normal vehicle operation; 7) The IHU (Information Host) is used to display and memorize the processing results of the parking system controller.

[0040] Sensors used to perceive the vehicle's surrounding environment include: 1) Surround-view cameras, a total of four channels (front, rear, left, and right), whose main function is to acquire real-time data on the vehicle's surrounding environment and process the acquired video stream through the SOC processor in the memory parking system controller before finally inputting it to the IHU (Information Host) for display; 2) 12 ultrasonic probes, arranged around the vehicle, with six on each of the front and rear bumpers. The four side ultrasonic probes are mainly used to identify parking spaces on the left and right sides, with a maximum detection distance of at least 5.5m, and to transmit the identified parking space information to the memory parking system controller in a timely manner. The four front and four rear ultrasonic probes (located in the middle of the front and rear bumpers) are mainly used to detect the distance of obstacles in front and behind in real time when the vehicle speed is less than 15km / h and upload the data to the system controller in real time, with a minimum detection distance of at least 5.5m; 4) FCM forward-facing multi-function camera, installed above the windshield to monitor the environmental data in front of the vehicle. Because FCM has a wider monitoring range, its main function is to combine with surround-view cameras for vehicle detection, pedestrian detection, road sign detection, and determination of drivable areas. Additionally, during map creation, it extracts feature points and semantic features from the environment surrounding the vehicle using FCM and surround-view cameras, saving them to the memory parking system controller. These features are then matched and identified when locating the starting point for the memory parking function. In summary, environmental perception sensors distributed around the vehicle ensure the safe use of the memory parking function. Users simply follow the step-by-step prompts on the main unit to complete parking, greatly improving parking convenience and saving time.

[0041] Those skilled in the art should understand that the above system architecture is merely an example, and other existing or future components or modules that are applicable to this application should also be included within the scope of protection of this application, and are hereby incorporated by reference.

[0042] The obstacle avoidance control method for automobiles provided in the embodiments of this application will now be explained in detail with reference to the accompanying drawings.

[0043] Figure 1 This is a flowchart of a memory-based obstacle avoidance parking method provided in an embodiment of this application. This method is applied to vehicles. (Refer to...) Figure 1 The method includes the following steps:

[0044] Step 101: During the memory parking process, after controlling the vehicle to start bypassing the obstacle, acquire and store the driving path of the vehicle during the obstacle bypass process.

[0045] In this application, sensors are used to perceive the vehicle's surrounding environment to acquire data on the vehicle's surrounding environment; then, based on the distance to the vehicle's surrounding environment, parking control and obstacle avoidance control during parking are performed.

[0046] In some embodiments, during the memory parking process, the vehicle's surrounding environment data is acquired; based on the surrounding environment data, it is determined whether the vehicle needs to bypass an obstacle; when it is determined that the vehicle needs to bypass an obstacle, the vehicle is controlled to begin bypassing the obstacle.

[0047] In some embodiments, during obstacle avoidance, the vehicle's coordinates and heading angle are acquired in real time, and the vehicle's driving path is obtained based on the vehicle's coordinates and heading angle.

[0048] In some embodiments, real-time vehicle coordinates and heading angles are inseparable from vehicle dead reckoning, such as... Figure 2 This diagram illustrates the dead reckoning principle. The odometer and gyroscope, acting as distance and angular velocity sensors respectively, measure the displacement vector to calculate the vehicle's instantaneous position. For current intelligent vehicle navigation systems, the vehicle can be considered to be traveling in a two-dimensional plane, with the vehicle positioned in a T-plane. k The position at a given time can be represented as (1):

[0049]

[0050]

[0051] Where (x0, y0) is the initial position of the vehicle at time T0, (x k y k ) for T k The position of time, S i θ i The vehicles are from T i Position at time T i+1 The displacement and absolute heading at any given moment. Relative heading is determined by the difference between two consecutive absolute headings, denoted by ω. i This indicates that, given T0, T1, ..., T... k Relative heading measurement ω at time i Then the absolute heading of the vehicle at time t can be calculated by equation (2).

[0052]

[0053] In summary, during obstacle avoidance, the vehicle acquires its coordinates and heading angle in real time, obtains and stores its driving path based on these coordinates and heading angle, and thus enables the vehicle to return to its starting position according to the stored driving path when it can no longer avoid an obstacle.

[0054] In some embodiments, once the vehicle completes its obstacle avoidance maneuver, the stored driving path for that maneuver is cleared. The next round of memory processing continues when the next obstacle avoidance maneuver begins.

[0055] Step 102: When the vehicle cannot continue to bypass the obstacle, control the vehicle to return to the starting position of the obstacle bypass according to the stored driving path.

[0056] In some embodiments, during the obstacle avoidance process, environmental data of the vehicle's surroundings is acquired. Based on this data, it is determined whether there are oncoming vehicles or dynamic obstacles within a safe distance in front of the vehicle. If there are oncoming vehicles or dynamic obstacles within this safe distance, the obstacle avoidance process cannot continue. At this point, the vehicle is controlled to return to its obstacle avoidance starting point position according to the stored driving path. Figure 3 As shown.

[0057] It should be noted that during the process of controlling the vehicle to return to the starting position of the obstacle avoidance according to the stored driving path, the vehicle's coordinates and heading angle are acquired in real time. The current vehicle coordinates and heading angle are compared with the previously stored vehicle coordinates and heading angle, thereby controlling the vehicle to return along the stored driving path.

[0058] In addition, during the process of controlling the vehicle to return to the starting position of the obstacle avoidance according to the stored driving path, the surrounding environment data of the vehicle is also acquired. Based on the surrounding environment data, the driving area around the vehicle is determined. Based on the driving area around the following vehicle, the coordinates and heading angle of the vehicle are determined, thereby avoiding other traffic accidents during the vehicle's return process and ensuring the safety of the vehicle's return.

[0059] Since the vehicle may encounter different targets during the process of reversing back to the starting position of the obstacle avoidance according to the stored driving path, this application formulates different control strategies according to the types of targets during the vehicle's reversal process to ensure the safety of the targets.

[0060] In some embodiments, during the process of controlling the vehicle to retreat to the starting position of the obstacle avoidance according to the stored driving path, it is determined whether there are pedestrians or moving vehicles within a safe distance behind the vehicle; when it is determined that there are pedestrians or moving vehicles within the safe distance behind the vehicle, the vehicle is controlled to stop; after the pedestrians or moving vehicles have moved away from the safe distance behind the vehicle, the vehicle is controlled to continue to perform the operation of retreating to the starting position of the obstacle avoidance. This ensures the safety of moving vehicles and pedestrians.

[0061] Step 103: When the obstacle avoidance maneuver can be performed again, control the vehicle to restart the obstacle avoidance maneuver.

[0062] When the vehicle returns to the starting position of the obstacle avoidance according to the stored driving path, if an oncoming vehicle or dynamic obstacle is detected that has moved away from the vehicle at a safe distance, it is determined that the obstacle avoidance can be performed again. At this time, the vehicle is controlled to start the obstacle avoidance again.

[0063] like Figure 4As shown, this application utilizes a total of 12 ultrasonic radars (front, rear, left, and right) to output real-time distance information of obstacles around the vehicle. Simultaneously, it uses four surround-view cameras (front, rear, left, and right) to identify pedestrians, static and dynamic vehicles, and obstacles at close range during the reversing process. Additionally, a forward-facing multi-function camera identifies pedestrians, static and dynamic vehicles, and obstacles at a distance. By using sensors around the vehicle to perceive real-time environmental data, parking control and obstacle avoidance control during parking are achieved. Furthermore, this application provides the vehicle's heading angle and attitude information to the memory parking system domain controller via an inertial sensor system (IMU), and the vehicle system provides vehicle status information (such as wheel speed pulses, vehicle speed, etc.). The memory parking system domain controller acquires this key information and performs real-time path planning and data processing.

[0064] Once the planned path is completed, it needs to be executed by the vehicle's actuators. For example, actuators for lateral control include the electric power steering system; actuators for longitudinal control include the electronic stability system, vehicle warning lights, and exterior mirrors. Each actuator in the vehicle will complete the relevant operations according to the instructions of the parking controller and feed back the status of the memory parking system domain controller, forming a closed-loop control system. The entire memory parking system's vehicle hardware architecture has a clear and detailed division of labor and is planned in an orderly manner, ensuring reliable vehicle operation under the guidance of the core memory parking system domain controller.

[0065] In this embodiment, during the memory parking process, after the vehicle begins obstacle avoidance, its driving path is acquired and stored. When obstacle avoidance cannot continue, the vehicle is controlled to return to its starting position according to the stored driving path. When obstacle avoidance can be performed again, the vehicle restarts obstacle avoidance. This avoids the problem of traditional braking strategies in this scenario, where the system automatically exits when the braking time exceeds the system's set time threshold, greatly reducing the user experience and potentially causing traffic congestion. This method increases the success rate of memory parking, enriches the user experience, and significantly reduces traffic congestion. It is simple, clear, practical, and versatile.

[0066] After explaining the memory parking obstacle avoidance method provided in the embodiments of this application, the memory parking obstacle avoidance device provided in the embodiments of this application will be introduced next.

[0067] This application also provides a memory parking obstacle avoidance device, including:

[0068] The acquisition module is used to acquire and store the driving path of the vehicle during the obstacle avoidance process after the vehicle starts to avoid obstacles during the memory parking process;

[0069] The control module is used to control the vehicle to return to the starting position of the obstacle course according to the stored driving path when the vehicle cannot continue to perform obstacle course; and to control the vehicle to start obstacle course again when the vehicle can perform obstacle course again.

[0070] In some embodiments, the control module is configured to determine whether there are pedestrians or dynamic vehicles within a safe distance behind the vehicle during the process of controlling the vehicle to retreat to the starting position of the obstacle avoidance according to the stored driving path; when it is determined that there are pedestrians or dynamic vehicles within the safe distance behind the vehicle, control the vehicle to stop; and when the pedestrians or dynamic vehicles leave the safe distance behind the vehicle, control the vehicle to continue to perform the operation of retreating to the starting position of the obstacle avoidance.

[0071] In some embodiments, the acquisition module is used to clear the driving path remembered during the obstacle avoidance process after the vehicle has completed the obstacle avoidance.

[0072] In some embodiments, the acquisition module is used to acquire the vehicle's coordinates and heading angle in real time during obstacle avoidance, and to obtain the vehicle's driving path based on the vehicle's coordinates and heading angle.

[0073] The acquisition module can employ sensors for sensing the vehicle's surrounding environment, including 12 ultrasonic probes, 4 surround-view cameras, and a forward-facing multi-function camera.

[0074] In some embodiments, the control module is used to acquire surrounding environmental data of the vehicle during the parking process; determine whether the vehicle needs to bypass an obstacle based on the surrounding environmental data; and control the vehicle to start bypassing the obstacle after determining that the vehicle needs to bypass the obstacle.

[0075] In some embodiments, the control module is configured to determine whether there are pedestrians or vehicles within a safe distance in front of the vehicle based on the surrounding environment data of the vehicle; when there are pedestrians within a safe distance in front of the vehicle, control the vehicle to stop; when there are vehicles within a safe distance in front of the vehicle, control the vehicle to perform a following action with the vehicle as the target.

[0076] The control module can be a memory parking system controller.

[0077] In summary, the memory parking obstacle avoidance device provided in this application can solve the problem in related technologies where the vehicle cannot continue to perform obstacle avoidance, and after the vehicle is brought to a stop, the system is forced to exit within a certain threshold time, ultimately causing traffic congestion. This increases the success rate of memory parking, enriches the user experience, and greatly reduces traffic congestion accidents.

[0078] This application also provides a control device, which includes one or more processors and one or more memories. The one or more memories store at least one piece of program code, which is loaded and executed by the one or more processors to implement the memory-based parking obstacle avoidance method described in any of the above implementations.

[0079] This application also provides a computer-readable storage medium storing at least one piece of program code, which is loaded and executed by a processor to implement the memory-based parking obstacle avoidance method described in any of the above implementations.

[0080] This application also provides a computer program product, which includes computer program code stored in a computer-readable storage medium. A processor of a control device reads the computer program code from the computer-readable storage medium and executes the computer program code, causing the control device to execute a memory-based parking obstacle avoidance method as described in any of the above implementations.

[0081] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only.

[0082] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A memory-based obstacle avoidance parking method, characterized in that, include: During the memory parking process, after the vehicle starts to avoid obstacles, the driving path of the vehicle during the obstacle avoidance process is acquired and stored; When the vehicle is unable to continue its obstacle avoidance maneuver, control the vehicle to return to the starting position of the obstacle avoidance maneuver according to the stored driving path; During the process of controlling the vehicle to return to the starting position of the obstacle avoidance according to the stored driving path, it is determined whether there are pedestrians or dynamic vehicles within the safe distance behind the vehicle. When it is determined that there are pedestrians or moving vehicles within a safe distance behind the vehicle, control the vehicle to stop; after the pedestrians or moving vehicles have moved away from the safe distance behind the vehicle, control the vehicle to continue to reverse back to the starting position of the vehicle's obstacle avoidance operation. When the vehicle can perform obstacle avoidance again, control the vehicle to start obstacle avoidance again.

2. The memory-based parking obstacle avoidance method as described in claim 1, characterized in that, Once the vehicle has completed its obstacle avoidance maneuver, the driving path stored during this maneuver will be cleared.

3. The memory-based parking obstacle avoidance method as described in claim 1, characterized in that, During obstacle avoidance, the vehicle's coordinates and heading angle are acquired in real time, and the vehicle's driving path is obtained based on these coordinates and heading angle.

4. The memory-based parking obstacle avoidance method as described in claim 1, characterized in that, During the parking memory process, acquire data on the vehicle's surrounding environment; Based on the surrounding environmental data, determine whether the vehicle needs to navigate around obstacles; Once it is determined that the vehicle needs to go around an obstacle, control the vehicle to begin going around the obstacle.

5. The memory-based parking obstacle avoidance method as described in claim 4, characterized in that, Based on the surrounding environmental data, determine whether there are pedestrians or vehicles within a safe distance in front of the vehicle; when there are pedestrians within a safe distance in front of the vehicle, control the vehicle to stop; when there are vehicles within a safe distance in front of the vehicle, use the vehicle as the target and control the vehicle to follow.

6. A memory parking obstacle avoidance device, characterized in that, include: The acquisition module is used to acquire and store the driving path of the vehicle during the obstacle avoidance process after the vehicle starts to avoid obstacles during the memory parking process. The control module is used to control the vehicle to return to the starting position of the obstacle avoidance according to the stored driving path when the vehicle cannot continue to perform obstacle avoidance. During the process of controlling the vehicle to return to the starting position of the obstacle avoidance according to the stored driving path, it is determined whether there are pedestrians or dynamic vehicles within the safe distance behind the vehicle. When it is determined that there are pedestrians or moving vehicles within a safe distance behind the vehicle, control the vehicle to stop; after the pedestrians or moving vehicles have moved away from the safe distance behind the vehicle, control the vehicle to continue to perform the operation of reversing back to the starting position of the vehicle's obstacle course; when the vehicle can perform the obstacle course operation again, control the vehicle to start the obstacle course operation again.

7. A control device, characterized in that, The control device includes one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to implement a memory-based parking obstacle avoidance method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one piece of program code, which is loaded and executed by a processor to implement a memory-based parking obstacle avoidance method as described in any one of claims 1 to 5.

9. A computer program product, characterized in that, The computer program product includes computer program code stored in a computer-readable storage medium. The processor of the control device reads the computer program code from the computer-readable storage medium and executes the computer program code, causing the control device to perform a memory-based parking obstacle avoidance method as described in any one of claims 1 to 5.

Images