Method and system for automatically planning parking route on basis of memorized route, and device and medium

Abstract

A method and system for automatically planning a parking route on the basis of a memorized route, and a device and a medium. The method comprises: during valet parking assist of a vehicle, starting from the starting point of a memorized route, calculating a point, having the shortest distance to the vehicle, in a memorized route point set according to a preset cycle; and when there is an obstacle in a local travel route between the point having the shortest distance and the N-th point ahead of the point having the shortest distance, if the obstacle is a static obstacle, re-planning the local travel route to avoid the obstacle, and if the obstacle is a dynamic obstacle, generating in real time a predicted motion trajectory of the obstacle, the N-th point being in the memorized route point set, and if the predicted motion trajectory and the local travel route overlap at a same time point, controlling the vehicle to stop and wait until there is no overlapping point before resuming travel.

Description

Method, system, device and medium for automatically planning parking routes based on memory routes

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure claims priority to Chinese patent application No. 202410366987.2, filed on March 18, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to the field of vehicle assisted driving, and in particular to a method, system, device and medium for automatically planning a parking route based on a memory route. Background Art

[0004] Memory parking, whose full name is Valet Parking Assist, is based on the automatic parking function and uses route memory, assisted driving and other functions to achieve a more comprehensive and automatic parking scenario application. The memory parking function can be divided into two parts. The first is to learn the parking route. When used for the first time, the driver needs to manually drive the vehicle through the parking route, memorize it in the basement or in front of the parking lot door, and complete the entire "memory route" process after parking. When using memory parking, the system will assist the driver to drive the vehicle from the starting point of the set route to the end point of the set route based on the "memory route" and park in the parking space that has been memorized by the system.

[0005] However, to ensure the vehicle safely drives along a memorized route, it must be able to autonomously avoid obstacles such as stalls, stone pillars, pedestrians, and moving vehicles. Existing memory parking systems are inadequate for handling obstacles during parking. They simply track the entire memorized route and immediately stop when an obstacle is detected. They lack the flexibility to tailor avoidance strategies to suit different obstacle types, resulting in a poor user experience.

[0006] Summary of the Invention

[0007] The present disclosure provides a method, system, device, and medium for automatically planning a parking route based on a memorized route. By utilizing one or more embodiments of the present disclosure, the present disclosure solves the technical problem that when an obstacle is detected on a memorized route, the vehicle immediately stops and cannot provide different avoidance strategies for different obstacle types, resulting in an inflexible approach.

[0008] In a first aspect of the present disclosure, a method for automatically planning a parking route based on a memory route is provided, comprising: when a vehicle is memory-parked, starting from the starting point of the memory route, calculating, according to a preset period, a point in a memory route point set with the shortest distance from the vehicle position; when an obstacle exists in a local driving route between the point with the shortest distance and the Nth point forward of the point, if the obstacle is a static obstacle, replanning the local driving route to avoid the obstacle; if the obstacle is a dynamic obstacle, generating a predicted motion trajectory of the obstacle in real time, with the Nth point in the memory route point set; and if the predicted motion trajectory overlaps with the local driving route at the same time point, controlling the vehicle to stop and wait until there is no overlap before continuing to drive.

[0009] In a second aspect of the present disclosure, a system for automatically planning a parking route based on a memory route is provided, comprising: a calculation module for calculating, starting from a starting point of a memory route, the point in a point set of the memory route with the shortest distance from the vehicle's position according to a preset period when a vehicle is memory-parked; a judgment module for judging whether there is an obstacle in a local driving route between the point with the shortest distance and the Nth point forward thereof, the Nth point being in the memory route point set; and further for judging, when an obstacle exists, whether the obstacle is a static obstacle or a dynamic obstacle; a control module for replanning the local driving route to avoid the obstacle if the obstacle is a static obstacle; and for generating a predicted motion trajectory of the obstacle in real time if the obstacle is a dynamic obstacle; and if the predicted motion trajectory overlaps with the local driving route at the same time point, controlling the vehicle to stop and wait until there is no overlap and then continue driving.

[0010] In a third aspect of the present disclosure, a computer device is provided, comprising: a processor; and a memory for storing instructions executable by the processor, wherein the processor is configured to execute the instructions to implement the method for automatically planning a parking route based on a memory route as described in any embodiment of the first aspect.

[0011] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for automatically planning a parking route based on a memory route as described in any embodiment of the first aspect is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] FIG1 is a schematic flow chart showing a method for automatically planning a parking route based on a memory route according to some embodiments of the present disclosure;

[0013] FIG2 shows a schematic flow chart of step S50 in FIG1 ;

[0014] FIG3 is a schematic diagram of a system for automatically planning a parking route based on a memory route according to some embodiments of the present disclosure;

[0015] FIG4 shows a schematic structural diagram of a computer device according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0016] To help those skilled in the art better understand the present disclosure, the following will provide a clear and complete description of the technical solutions in the embodiments of the present disclosure, in conjunction with the accompanying drawings. It is clear that the described embodiments are only a portion of the embodiments of the present disclosure, not all of them. All other embodiments derived by those skilled in the art based on the embodiments of the present disclosure without creative effort are within the scope of protection of the present disclosure.

[0017] In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0018] In a first aspect of the present disclosure, a method for automatically planning a parking route based on a memory route is provided. FIG1 illustrates a flow chart of a method for automatically planning a parking route based on a memory route according to some embodiments of the present disclosure. As shown in FIG1 , the method for automatically planning a parking route based on a memory route includes the following steps S10 to S50.

[0019] In step S10 , when the vehicle is memory parking, starting from the starting point of the memory route, the point in the memory route point set with the shortest distance to the vehicle position is calculated according to a preset period.

[0020] In some embodiments, when a vehicle reaches a memory route, the user is prompted to enable the memory parking function based on the stored memory route. Upon receiving the user's instruction to enable the memory parking function, the vehicle is controlled to enter the memory parking state. During memory parking, the vehicle traverses the memory route point set along the entire memory route and, starting from the starting point of the memory route, calculates the point in the memory route point set with the shortest distance to the vehicle's position based on a preset period.

[0021] In some embodiments, the memory route point set is generated during the learning and memorizing of the route, and the memory route point set is used to constrain the driving trajectory of the vehicle.

[0022] In some embodiments, the preset period is set before memorizing parking, for example, 50 ms as a period.

[0023] In step S20: determine whether there is an obstacle in the local driving route between the point with the shortest distance and the Nth point ahead of it, and the Nth point is in the memory route point set; if so, proceed to step S30.

[0024] In some embodiments, a memory route is sequentially arranged with multiple points along the vehicle's travel direction, forming a memory route point set. The segment between the point with the shortest distance to the vehicle's position and the point Nth forward from that point is considered a local route. The vehicle is then required to determine in real time whether there are obstacles along the local route. By determining whether there are obstacles ahead of the vehicle in real time, collisions with obstacles can be avoided during memory parking, ensuring the safety of both the driver and the vehicle, and providing a better user experience.

[0025] In some embodiments, radar is used to determine whether there are obstacles on the local driving route. If there are no obstacles, the vehicle is controlled to drive according to the memorized route.

[0026] In step S30: if there is an obstacle in the local driving route, obstacle data needs to be collected through multiple data collection devices, and the type of obstacle needs to be determined; if the obstacle is a static obstacle, proceed to step S40; if the obstacle is a dynamic obstacle, proceed to step S50.

[0027] In some embodiments, when there is an obstacle in the local driving route, the following steps are also included: collecting image data of the obstacle; matching the collected image data with pre-stored image data of multiple obstacles, and selecting the type of obstacle corresponding to the stored image data with the highest similarity as the type of the collected obstacle, where the types of obstacles include static obstacles and dynamic obstacles.

[0028] In some embodiments, image data of obstacles is captured by a camera device, and the captured image data is matched with pre-stored image data of multiple obstacles. The type of obstacle corresponding to the stored image data with the highest similarity is selected as the captured obstacle type. Obstacle types include static obstacles and dynamic obstacles. For example, multiple images of vehicles, pedestrians, trees, stone piles, and earth piles are pre-stored. The captured image data is compared with each pre-stored image to determine whether the obstacles on the local driving route are vehicles, pedestrians, trees, stone piles, or earth piles. The identified trees, stone piles, and earth piles are then recorded as static obstacles, and the identified vehicles, pedestrians, and other obstacles are recorded as dynamic obstacles. This allows for accurate identification of obstacle types, helping to provide different avoidance strategies based on the different types of obstacles.

[0029] In step S40: if the obstacle is a static obstacle, the local driving route is replanned to avoid the obstacle.

[0030] In some embodiments, based on the collected obstacle data, it is determined that the obstacle is a static obstacle. Since static obstacles are always in a fixed position, to ensure normal parking of the vehicle, it is necessary to replan a portion of the driving route, resulting in a replanned local driving route. For example, if the collected obstacle is a mound, the replanned local driving route is one that circumvents the mound. By controlling the vehicle to avoid the obstacle according to the replanned local driving route, the vehicle can autonomously avoid static obstacles without human intervention, providing a good user experience.

[0031] In some embodiments, the step of replanning the local driving route to avoid obstacles includes: replanning the local driving route using a hybrid A* algorithm, and controlling the vehicle to travel according to the replanned local driving route.

[0032] In some embodiments, the Hybrid A* algorithm is a heuristic search-based path planning algorithm that combines the advantages of the A* algorithm and the Dijkstra algorithm. It can quickly search for the optimal path under different road structures while being unaffected by road topology. The Hybrid A* algorithm is applicable to a variety of path planning scenarios, including robot navigation, autonomous driving, and drone path planning.

[0033] In some embodiments, based on the positions of the vehicle and static obstacles on the grid map, a hybrid A* algorithm is used to replan the local driving route between the point in the memory route point set with the shortest distance to the vehicle position and the Nth point forward of this point to obtain a replanned local driving route. The vehicle is controlled to drive according to the replanned local driving route, thereby ensuring that the vehicle avoids static obstacles and does not affect the vehicle's continued parking, greatly improving the user experience.

[0034] In step S50: if the obstacle is a dynamic obstacle, a predicted motion trajectory of the obstacle is generated in real time; if the predicted motion trajectory overlaps with the local driving route at the same time point, the vehicle is controlled to stop and wait until there is no overlapping point before continuing to drive.

[0035] In some embodiments, an obstacle is determined to be a dynamic obstacle based on obstacle data collected by multiple acquisition devices. Based on the collected dynamic obstacle data, the vehicle generates a predicted motion trajectory of the dynamic obstacle in real time, and compares the predicted motion trajectory with the local driving route to detect whether the predicted motion trajectory and the local driving route overlap at the same time point. If it is detected that the predicted motion trajectory and the local driving route overlap at the same time point, the vehicle is controlled to stop and wait until there is no overlapping point before continuing to drive.

[0036] In some embodiments, the collected dynamic obstacle data includes: the moving speed, lateral movement acceleration, and longitudinal movement acceleration of the dynamic obstacle.

[0037] In some embodiments, after determining whether there are obstacles in the local driving route between the point with the shortest distance and the Nth point forward thereof, if there are no obstacles in the local driving route, it means that the local driving route is unobstructed or the obstacles are not sufficient to affect the normal passage of the vehicle, then step S60 is entered: the vehicle is controlled to drive normally according to the memorized route.

[0038] In some embodiments, if an obstacle suddenly appears in a local driving route, the vehicle will first slow down and stop to ensure the safety of people and vehicles, and then re-enter the current local driving route.

[0039] In some embodiments, referring to FIG. 2 , which shows a flow chart of step S50 in FIG. 1 , the step of generating a predicted motion trajectory of an obstacle includes steps S501 to S503 .

[0040] In step S501 : the moving speed, lateral moving acceleration and longitudinal moving acceleration of the dynamic obstacle are collected.

[0041] In step S502 , the lateral displacement and longitudinal displacement of the dynamic obstacle at each future time point are determined based on the moving speed, lateral movement acceleration, and longitudinal movement acceleration of the dynamic obstacle.

[0042] In some embodiments, the moving speed, lateral acceleration, and longitudinal acceleration of the dynamic obstacle are collected, and the collected moving speed, lateral acceleration, and longitudinal acceleration of the dynamic obstacle are substituted into the displacement calculation formula. The lateral displacement and longitudinal displacement of the dynamic obstacle at each future time point are calculated using the displacement calculation formula.

[0043] In some embodiments, the displacement calculation formula may be:

[0044] Among them, S x 、S y Respectively represent the lateral displacement and longitudinal displacement of the dynamic obstacle; V x 、V y They represent the lateral and longitudinal moving speeds of the dynamic obstacle respectively; t represents the future time point; a x 、a y They represent the lateral acceleration and longitudinal acceleration of the dynamic obstacle respectively.

[0045] In step S503 , a predicted motion trajectory of the dynamic obstacle is generated based on the lateral displacement and longitudinal displacement of the dynamic obstacle at each future time point.

[0046] In some embodiments, the position of the dynamic obstacle at each future time point can be obtained based on the lateral displacement and longitudinal displacement of the dynamic obstacle at each future time point, where the position is determined based on coordinates; based on the position of the dynamic obstacle at each future time point, a predicted motion trajectory of the dynamic obstacle is fitted and generated.

[0047] In some embodiments, if the predicted motion trajectory does not overlap with the local driving route at the same time point, the vehicle travels according to the local driving route.

[0048] In some embodiments, a predicted motion trajectory of an obstacle is generated in real time; if the predicted motion trajectory does not overlap with the local driving route at the same time point, the vehicle can drive normally according to the local driving route corresponding to the memory route.

[0049] In some embodiments, a method for determining whether a predicted motion trajectory overlaps with a local driving route at the same time point includes: obtaining the position of the obstacle at each time point based on the predicted motion trajectory of the obstacle; calculating the position of the vehicle at each time point on the local driving route based on the longitudinal velocity constant of the vehicle; and determining whether the position of the obstacle and the position of the vehicle at the same time point overlap. If the position of the obstacle and the position of the vehicle at the same time point overlap, determining that the predicted motion trajectory and the local driving route overlap at the same time point.

[0050] In some embodiments, the position of the dynamic obstacle at various future time points can be further determined based on the predicted motion trajectory of the dynamic obstacle, where the position is determined based on coordinates. In addition, since the vehicle is unmanned throughout the memory parking process, the vehicle's position at various future time points along the local driving route can be calculated based on the vehicle's longitudinal velocity constant. Combined with the position of the dynamic obstacle at various future time points, it can be determined whether the obstacle's position at the same time point overlaps with the vehicle's position.

[0051] In some embodiments, when the vehicle is controlled to stop and wait, a predicted motion trajectory of the obstacle is generated in real time until the predicted motion trajectory does not overlap with the local driving route at the same time point, and the vehicle drives according to the local driving route.

[0052] In some embodiments, when a vehicle detects a dynamic obstacle on a local route, it generates a predicted trajectory for the dynamic obstacle in real time. If the vehicle's movement along the local route overlaps with the predicted trajectory of the dynamic obstacle at a certain point in the future, the vehicle is stopped and waits. During this time, the predicted trajectory of the dynamic obstacle continues to be generated in real time until the predicted trajectory of the dynamic obstacle and the local route no longer overlap at the same point in time, meaning that the predicted trajectory of the dynamic obstacle deviates from the local route. At this point, the dynamic obstacle and the vehicle travel independently, and even if they both pass through the same location or coordinates, no collision or friction will occur as long as the dynamic obstacle and the vehicle do not pass through the same location or coordinates at the same time.

[0053] In some embodiments, if the vehicle parking time is longer than a preset time, a user takeover message is output.

[0054] In some embodiments, a vehicle may be stuck for a long time due to slow-moving dynamic obstacles. To save user time and prevent traffic congestion, if the vehicle is parked for longer than a preset time, the vehicle exits the memory parking function and a message indicating the user has taken over the vehicle may be displayed via the speaker or display. In some embodiments, the preset time can be set to 10 seconds.

[0055] In some embodiments, when parking via vehicle memory, the system calculates the point on the memorized route with the shortest distance from the vehicle's location based on a preset period, starting from the starting point of the memorized route. This allows for more accurate determination of the vehicle's location and direction of travel, while also enhancing route adjustment flexibility. The system first determines whether there are any obstacles in the local route between the shortest point and the Nth point forward. Then, based on the collected obstacle data, it determines whether the obstacle is static or dynamic. If an obstacle is present, the local route is replanned to avoid it if it is static. If an obstacle is present, a predicted trajectory of the obstacle is generated in real time. If the predicted trajectory overlaps with the local route at the same time point, the vehicle is stopped and waits until there are no more overlapping points before continuing. Consequently, the obstacle identification and avoidance method eliminates lag, achieving the effect of early prediction and avoidance. Furthermore, when an obstacle is detected on the memorized route, the vehicle does not immediately stop, but instead provides different avoidance strategies based on the obstacle type, providing a flexible approach and enhancing the user experience.

[0056] In a second aspect of the present disclosure, a system for automatically planning a parking route based on a memory route is provided. Figure 3 shows a schematic diagram of a system for automatically planning a parking route based on a memory route, according to some embodiments of the present disclosure. As shown in Figure 3, the system for automatically planning a parking route based on a memory route includes a calculation module, a determination module, and a control module.

[0057] The calculation module is used when the vehicle is memory parking. Starting from the starting point of the memory route, it calculates the point in the memory route point set with the shortest distance to the vehicle position according to a preset period; the judgment module is used to determine whether there is an obstacle in the local driving route between the point with the shortest distance and the Nth point forward of the memory route point set, and the Nth point is in the memory route point set; it is also used to determine whether the obstacle is a static obstacle or a dynamic obstacle when there is an obstacle; the control module is used to replan the local driving route to avoid the obstacle when the obstacle is a static obstacle; it is also used to generate the predicted motion trajectory of the obstacle in real time when the obstacle is a dynamic obstacle; if the predicted motion trajectory overlaps with the local driving route at the same time point, the vehicle is controlled to stop and wait until there is no overlapping point before driving again.

[0058] In some embodiments, the system for automatically planning a parking route based on a memory route may further include a storage module for storing a pre-generated memory route point set.

[0059] In some embodiments, when the vehicle memorizes parking, the calculation module starts from the starting point of the memorized route and calculates the point with the shortest distance from the vehicle position in the memorized route point set according to a preset period. This allows the vehicle position to be observed in real time and prevents the vehicle from deviating. The judgment module needs to determine whether there is an obstacle on the local driving route between the point with the shortest distance from the vehicle position and the Nth point forward of the point. If there is an obstacle on the local driving route, the type of obstacle is further determined based on the collected obstacle data, that is, whether the obstacle is a static obstacle or a dynamic obstacle; if the obstacle is a static obstacle, the control module replans the local driving route and then drives according to the replanned local driving route to avoid the static obstacle; if the obstacle is a dynamic obstacle, the control module generates a predicted motion trajectory of the obstacle in real time. If it is found that the predicted motion trajectory at the same time point is the same as the local driving trajectory, the control module generates a predicted motion trajectory of the obstacle in real time. Overlapping trajectories indicate that the vehicle will collide with a dynamic obstacle at that point in time, so it is necessary to stop and wait to ensure that the vehicle and the dynamic obstacle travel at different times. During the parking and waiting process, the control module will generate a predicted motion trajectory of the obstacle in real time until no overlapping points are found. In this way, there is no lag in the obstacle recognition and avoidance methods, achieving the effect of early prediction and early avoidance. This solves the technical problem in related technologies that when an obstacle is found on the memory route, the vehicle will stop immediately, and different avoidance strategies cannot be provided to the vehicle according to different obstacle types. The method is not flexible enough, and the user experience is very poor.

[0060] Among them, the functional implementation of each module in the above-mentioned system for automatically planning a parking route based on a memory route corresponds to the steps in the above-mentioned method embodiment for automatically planning a parking route based on a memory route, and their functions and implementation processes are not repeated here one by one.

[0061] In a third aspect of the present disclosure, a computer device is further provided, as shown in FIG4 . FIG4 shows a schematic structural diagram of a computer device according to some embodiments of the present disclosure. The computer device includes a memory 404, a processor 402, and a computer program stored in the memory 404 and executable on the processor 402. The processor 402 executes the program to implement the method for automatically planning a parking route based on a memory route as described in any of the above embodiments.

[0062] In FIG4 , a bus architecture (represented by bus 400) is shown. Bus 400 may include any number of interconnected buses and bridges. Bus 400 links various circuits together, including one or more processors represented by processor 402 and memory represented by memory 404. Bus 400 may also link various other circuits together, such as peripherals, voltage regulators, and power management circuits, all of which are well known in the art and, therefore, will not be described further herein. Bus interface 405 provides an interface between bus 400 and receiver 401 and transmitter 403. Receiver 401 and transmitter 403 may be the same component, namely a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 402 is responsible for managing bus 400 and general processing, while memory 404 may be used to store data used by processor 402 when performing operations.

[0063] In a fourth aspect of the present disclosure, a computer-readable storage medium is further provided, on which a computer program is stored. When the program is executed by a processor, the method for automatically planning a parking route based on a memory route as described in any of the above embodiments is implemented.

[0064] It should be noted that the serial numbers of the above-mentioned embodiments of the present disclosure are only for description and do not represent the advantages or disadvantages of the embodiments.

[0065] The technical solutions provided by one or more embodiments of the present disclosure provide the following beneficial effects: When parking through vehicle memory, starting from the starting point of the memory route, the point in the memory route point set with the shortest distance to the vehicle's position is calculated according to a preset period. This allows for more accurate determination of the vehicle's position and driving direction, while also enhancing route adjustment flexibility. When an obstacle exists in the local driving route between the point in the memory route point set with the shortest distance to the vehicle's position and the Nth point forward of it, if the obstacle is a static obstacle, the local driving route is replanned to avoid the obstacle. If the obstacle is a dynamic obstacle, a predicted motion trajectory of the obstacle is generated in real time. If the predicted motion trajectory overlaps with the local driving route at the same time point, the vehicle is controlled to stop and wait until there are no overlapping points before continuing to drive. Therefore, the present invention has no lag in the obstacle identification and obstacle avoidance method, achieving the effect of early prediction and early avoidance. Moreover, when an obstacle is found on the memory route, the vehicle does not stop immediately, but instead provides the vehicle with different avoidance strategies based on different obstacle types, which is flexible and improves the user experience.

[0066] The terms "including" and "having," and any variations thereof, in the specification and claims of the present disclosure and the accompanying drawings, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0067] In the description of the embodiments of the present disclosure, the words "exemplary," "for example," or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary," "for example," or "for example" in the embodiments of the present disclosure should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "for example," or "for example" is intended to present the relevant concepts in a concrete manner.

[0068] In the description of the embodiments of the present disclosure, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present disclosure, “multiple” refers to two or more than two.

[0069] In some processes described in the embodiments of the present disclosure, multiple operations or steps are included that appear in a specific order. However, it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present disclosure or may be executed in parallel. The sequence numbers of the operations are only used to distinguish different operations and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0070] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course, by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device to execute the methods described in each embodiment of the present disclosure.

[0071] The above are only preferred embodiments of the present disclosure and are not intended to limit the patent scope of the present disclosure. Any equivalent structure or equivalent process transformation made using the contents of the present disclosure and the drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present disclosure.

Claims

1. A method for automatically planning a parking route based on a memory route, comprising: When the vehicle is memory parking, starting from the starting point of the memory route, the point with the shortest distance to the vehicle position in the memory route point set is calculated according to the preset period; When an obstacle exists in the local driving route between the point with the shortest distance and the Nth point ahead of it, if the obstacle is a static obstacle, the local driving route is replanned to avoid the obstacle; if the obstacle is a dynamic obstacle, a predicted motion trajectory of the obstacle is generated in real time, with the Nth point being included in the memory route point set; If the predicted motion trajectory overlaps with the local driving route at the same time point, the vehicle is controlled to stop and wait until there is no overlapping point before continuing to drive.

2. The method for automatically planning a parking route based on a memory route according to claim 1, further comprising: The radar is used to determine whether there are obstacles on the local driving route. If there are no obstacles, the vehicle is controlled to travel according to the memorized route.

3. The method for automatically planning a parking route based on a memory route according to claim 1, wherein: When there is an obstacle on the local driving route, the method further comprises the steps of: collecting image data of the obstacle; as well as The collected image data is matched with pre-stored image data of multiple obstacles, and the type of obstacle corresponding to the stored image data with the highest similarity is selected as the type of collected obstacle, which includes static obstacles and dynamic obstacles.

4. The method for automatically planning a parking route based on a memory route according to claim 1, wherein: The step of replanning the local driving route to avoid the obstacle includes: The local driving route is replanned, and the vehicle is controlled to travel according to the replanned local driving route.

5. The method for automatically planning a parking route based on a memory route according to claim 1, wherein: The step of generating the predicted motion trajectory of the obstacle comprises: Collect the moving speed, lateral acceleration and longitudinal acceleration of dynamic obstacles; Determining the lateral displacement and longitudinal displacement of the dynamic obstacle at each future time point based on the moving speed, lateral movement acceleration, and longitudinal movement acceleration of the dynamic obstacle; and Based on the lateral and longitudinal displacements of the dynamic obstacle at each future time point, the predicted motion trajectory of the dynamic obstacle is generated.

6. The method for automatically planning a parking route based on a memory route according to claim 1, further comprising: If the predicted motion trajectory does not overlap with the local driving route at the same time point, the vehicle travels according to the local driving route.

7. The method for automatically planning a parking route based on a memory route according to claim 1, further comprising: Based on the predicted motion trajectory of the obstacle, obtaining the position of the obstacle at each time point; Calculate the position of the vehicle at each time point on the local driving route based on the longitudinal velocity constant of the vehicle; as well as It is determined whether the position of the obstacle and the vehicle position at the same time point overlap. If the position of the obstacle and the vehicle position at the same time point overlap, it is determined that the predicted motion trajectory and the local driving route at the same time point overlap.

8. The method for automatically planning a parking route based on a memory route according to claim 1, wherein: Control the vehicle to stop and wait until there is no overlap, including: When the vehicle is controlled to stop and wait, a predicted motion trajectory of the obstacle is generated in real time until the predicted motion trajectory does not overlap with the local driving route at the same time point, and the vehicle drives according to the local driving route.

9. The method for automatically planning a parking route based on a memory route according to claim 8, further comprising: If the vehicle parking time is longer than the preset time, the user takeover information is output.

10. A system for automatically planning a parking route based on a memory route, comprising: A calculation module is used to calculate the point with the shortest distance from the vehicle position in the memory route point set according to a preset period when the vehicle is memory parking, starting from the starting point of the memory route; a judgment module, configured to judge whether an obstacle exists in the local driving route between the point with the shortest distance and the Nth point ahead of it; and further configured to judge whether the obstacle is a static obstacle or a dynamic obstacle when an obstacle exists; as well as The control module is configured to replan a local driving route to avoid a static obstacle; generate a predicted motion trajectory of the obstacle in real time when the obstacle is dynamic; and control the vehicle to stop and wait until there is no overlap between the predicted motion trajectory and the local driving route at the same time point if the predicted motion trajectory overlaps with the local driving route.

11. The system for automatically planning a parking route based on a memory route as claimed in claim 10, further comprising a storage module for storing the pre-generated memory route point set.

12. A computer device comprising: processor; A memory for storing instructions executable by the processor, wherein the processor is configured to execute the instructions to implement the method for automatically planning a parking route based on a memory route according to any one of claims 1 to 9.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for automatically planning a parking route based on a memory route according to any one of claims 1 to 9 is implemented.

Images