Global Path Planning Method, Device, Vehicle and Medium for Valet Parking

Abstract

The present application relates to a global path planning method, device, vehicle and medium for valet parking. The method includes: detecting the actual working condition of the vehicle, and when it is detected that the actual working condition is a valet parking condition, extracting key map information of the target parking area to construct a road topology map based on the key map information; based on the road topology map, taking the current position of the vehicle as the starting point, performing lane matching according to a preset matching rule to obtain multiple first alternative lanes, and taking the end position set by the user as the end point to perform lane matching to obtain multiple second alternative lanes, and then calculating the matching degree between the first and second alternative lanes, and generating a global path planning path for valet parking according to the lanes whose matching degree meets the preset conditions. Based on the road topology map, the present application conducts targeted analysis and processing on the lane matching situation of the starting and ending points, thereby realizing scene recognition more accurately and greatly improving the driving experience of users.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and particularly to a global path planning method, device, vehicle and medium for valet parking. Background Art

[0002] As an important part of the autonomous driving system, the AVP (Automated Valet Parking) system involves multiple aspects such as map construction, planning perception, and prediction and decision-making. It can quantify the performance indicators of the planning algorithm according to different functional requirements to obtain the optimal path under corresponding standards. However, there is still much room for improvement in aspects such as the rationality, effectiveness, and user experience of the paths planned by many AVP systems.

[0003] Currently, related technologies can perform unified map layering according to the obtained batch path planning requests to determine the local map, and then divide the local map into multiple initial local sub-regions according to the historical path planning information to plan the path between the starting position and the target position in the path planning request; in addition, related technologies can also obtain the position information of the target parking space and the current vehicle, and combine the map information of the parking lot to plan multiple paths for the vehicle to reach the target parking space, thereby selecting a specific path and sending it to the current vehicle.

[0004] However, related technologies only consider generating the global path based on the planning algorithm, with incomplete scenario coverage, prone to generating unreasonable paths, and having great functional limitations, which greatly affects the driving experience of users. Summary of the Invention

[0005] This application provides a global path planning method, device, vehicle and medium for valet parking to solve the problems that related technologies only consider generating the global path based on the planning algorithm, with incomplete scenario coverage, prone to generating unreasonable paths, and having great functional limitations.

[0006] The first aspect embodiment of this application provides a global path planning method for valet parking, including the following steps: detecting the actual working condition of the vehicle, and when it is detected that the actual working condition is the valet parking condition, extracting the key map information of the target parking area to construct a road topology map based on the key map information; based on the road topology map, taking the current position of the vehicle as the starting point, and performing lane matching according to a preset matching rule to obtain multiple first alternative lanes, and taking the end position set by the user as the end point to perform lane matching to obtain multiple second alternative lanes; and calculating the matching degree between the multiple first alternative lanes and the multiple second alternative lanes, and generating a global path planning path for valet parking according to the lanes whose matching degree meets the preset conditions.

[0007] According to the above technical means, the embodiment of the present application realizes more accurate vehicle parking scene recognition by constructing a road topology map and performing targeted analysis and processing on the lane matching situation of the starting point and the end point, improves the rationality of the global path planning, and greatly improves the driving experience of users.

[0008] Optionally, in an embodiment of the present application, calculating the matching degree between the multiple first alternative lanes and the multiple second alternative lanes, and generating a global path planning path for valet parking according to the lanes that meet the preset conditions includes: calculating multiple shortest distances from the extended areas of the multiple first alternative lanes to the end point as the first matching degree; calculating multiple shortest distances from the extended areas of the multiple second alternative lanes to the starting point as the second matching degree; generating multiple lane combinations when both the first matching degree and the second matching degree are the minimum values, and based on the multiple lane combinations, and combining the relative positions of the corresponding lanes of the starting point and the end point, to generate the global path planning path.

[0009] According to the above technical means, the embodiment of the present application realizes more accurate scene recognition and reasonably plans the global path by specifically processing the special scene of whether the starting point and the end point belong to the same section of the road in the high-precision map according to the lane matching situation of the starting point and the end point, further improves the rationality and scene coverage rate of the global path planning of the AVP system, and effectively enhances the driving confidence of users.

[0010] Optionally, in an embodiment of the present application, the preset matching rule includes: when the starting point or the end point is a parking space, the lanes matched by the starting point and the end point include the lane on the side close to the parking space and the reverse lane; when the starting point or the end point is a coordinate point, the starting point matches the current lane, and the end point matches the current lane and the reverse lane.

[0011] According to the above technical means, the embodiment of the present application effectively guarantees the rationality of the vehicle matching path and meets the driving needs of users by specifically analyzing and processing the types and relative positions of the starting point and the end point to formulate corresponding matching rules.

[0012] Optionally, in an embodiment of the present application, the relative positions of the corresponding lanes of the starting point and the end point include: when the starting point and the end point are in the same-direction lane or the reverse lane, and the path point corresponding to the starting point is in front of the end point, then determine the global path scheme based on the lane matched by the end point; when the starting point and the end point are in the same-direction lane or the reverse lane, and the path point corresponding to the starting point is behind the end point, then determine the global path scheme based on the lane matched by the starting point.

[0013] According to the above technical means, the embodiment of the present application analyzes the relative positions of the corresponding lanes at the starting point and the ending point, thereby providing important guidance and basis for the subsequent global path planning, improving the reliability and safety of the planned path, and meeting the driving and riding needs of users.

[0014] Optionally, in an embodiment of the present application, the generating a global path planning path for valet parking according to the lane whose matching degree meets a preset condition includes: extracting corresponding lane information in the road topology map based on the matching degree and a preset search algorithm, so as to generate a global planning path in the full scenario according to the lane information.

[0015] According to the above technical means, the embodiment of the present application respectively performs AVP global path planning by considering special scenarios and conventional scenarios, further improving the efficiency and scenario coverage rate of the AVP system, and enhancing the user's willingness and experience in using this function.

[0016] An embodiment of the second aspect of the present application provides a global path planning device for valet parking, including: a construction module, configured to detect the actual working condition of the vehicle, and when detecting that the actual working condition is a valet parking working condition, extract key map information of the target parking area, and construct a road topology map based on the key map information; a matching module, configured to use the current position of the vehicle as the starting point based on the road topology map, perform lane matching according to a preset matching rule to obtain multiple first alternative lanes, and use the end position set by the user as the ending point to perform lane matching to obtain multiple second alternative lanes; and a generating module, configured to calculate the matching degree between the multiple first alternative lanes and the multiple second alternative lanes, and generate a global path planning path for valet parking according to the lane whose matching degree meets a preset condition.

[0017] Optionally, in an embodiment of the present application, the generating module includes: a first calculation unit, configured to calculate multiple shortest distances from the extended areas of the multiple first alternative lanes to the ending point as the first matching degree; a second calculation unit, configured to calculate multiple shortest distances from the extended areas of the multiple second alternative lanes to the starting point as the second matching degree; a combination unit, configured to generate multiple lane combinations when both the first matching degree and the second matching degree are minimum values, and generate the global path planning path based on the multiple lane combinations and in combination with the relative positions of the corresponding lanes at the starting point and the ending point.

[0018] Optionally, in an embodiment of the present application, the preset matching rule includes: when the starting point or the ending point is a parking space, the lanes matched by the starting point and the ending point include the lane on the side close to the parking space and the reverse lane; when the starting point or the ending point is a coordinate point, the starting point matches the current lane, and the ending point matches the current lane and the reverse lane.

[0019] Optionally, in an embodiment of the present application, the relative positions of the corresponding lanes of the starting point and the ending point include: when the starting point and the ending point are in the same-direction lanes or opposite-direction lanes, and the path point corresponding to the starting point is in front of the ending point, then determine the global path plan based on the lane matched with the ending point; when the starting point and the ending point are in the same-direction lanes or the opposite-direction lanes, and the path point corresponding to the starting point is behind the ending point, then determine the global path plan based on the lane matched with the starting point.

[0020] Optionally, in an embodiment of the present application, the generating module further includes: an extraction unit, configured to extract the corresponding lane information in the road topology graph based on the matching degree and a preset search algorithm, so as to generate a globally planned path in the full scenario according to the lane information.

[0021] An embodiment of the third aspect of the present application provides a vehicle, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the global path planning method for valet parking as described in the above embodiments.

[0022] An embodiment of the fourth aspect of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the program is executed by a processor, it implements the global path planning method for valet parking as described above.

[0023] Therefore, the embodiments of the present application have the following beneficial effects:

[0024] (1) By constructing a road topology graph and performing targeted analysis and processing on the lane matching situation of the starting and ending points, the embodiments of the present application can achieve more accurate vehicle parking scene recognition, improve the rationality of global path planning, and greatly improve the driving and riding experience of users.

[0025] (2) By specifically processing the special scenario where the starting and ending points belong to the same section of the road in the high-precision map according to the lane matching situation of the starting and ending points, the embodiments of the present application can achieve more accurate scene recognition and reasonably plan the global path, further improving the rationality and scene coverage rate of the global path planning of the AVP system, and effectively enhancing the driving and riding confidence of users.

[0026] (3) By specifically analyzing and processing the types and relative positions of the starting and ending points to formulate corresponding matching rules, the embodiments of the present application can effectively ensure the rationality of the vehicle matching path and meet the driving and riding needs of users.

[0027] (4) By analyzing the relative positions of the corresponding lanes at the starting point and the ending point in the embodiments of the present application, important guidance and basis are provided for the subsequent global path planning, the reliability and safety of the planned path are improved, and the driving and riding needs of users are met.

[0028] (5) By considering special scenarios and regular scenarios, the embodiments of the present application perform AVP global path planning respectively, further improving the efficiency and scenario coverage rate of the AVP system, and enhancing the user's willingness and experience in using this function.

[0029] Additional aspects and advantages of the present application will be given in part in the following description, will become apparent in part from the following description, or will be understood through the practice of the present application. Description of the Drawings

[0030] The above and / or additional aspects and advantages of the present application will become apparent and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0031] Figure 1 is a flowchart of a global path planning method for valet parking according to an embodiment of the present application;

[0032] Figure 2 is a schematic diagram of the logical architecture of a global path planning method for valet parking provided by an embodiment of the present application;

[0033] Figure 3 is a schematic diagram of the execution logic of a global path planning method for valet parking provided by an embodiment of the present application;

[0034] Figure 4 is an example diagram of a global path planning device for valet parking according to an embodiment of the present application;

[0035] Figure 5 is a schematic diagram of the structure of a vehicle provided by an embodiment of the present application.

[0036] Wherein, 10 - global path planning device for valet parking, 100 - construction module, 200 - matching module, 300 - generation module, 501 - memory, 502 - processor, 503 - communication interface. Detailed Embodiments

[0037] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions from beginning to end. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present application, but should not be construed as limiting the present application.

[0038] The global path planning method, device, vehicle, and medium for valet parking according to the embodiments of the present application will be described below with reference to the accompanying drawings. In response to the problems mentioned in the above background art, the present application provides a global path planning method for valet parking. In this method, the actual working conditions of the vehicle are detected, and when the detected actual working conditions are valet parking conditions, the key map information of the target parking area is extracted to construct a road topology map based on the key map information; based on the road topology map, the current position of the vehicle is used as the starting point, and lane matching is performed according to a preset matching rule to obtain multiple first alternative lanes, and the end position set by the user is used as the end point to perform lane matching to obtain multiple second alternative lanes. Furthermore, the matching degree between the first and second alternative lanes is calculated, and a global path planning path for valet parking is generated based on the lanes whose matching degree meets the preset conditions. Based on the road topology map, the present application conducts targeted analysis and processing on the lane matching conditions of the starting and ending points, thereby more accurately realizing scene recognition and greatly improving the driving experience of users. Thus, the problems in the related art, such as only considering generating a global path based on a planning algorithm, incomplete scene coverage, easy generation of unreasonable paths, and large functional limitations, are solved.

[0039] Specifically, Figure 1 FIG. is a flowchart of a global path planning method for valet parking provided by an embodiment of the present application.

[0040] As Figure 1 shown, the global path planning method for valet parking includes the following steps:

[0041] In step S101, the actual working conditions of the vehicle are detected, and when the detected actual working conditions are valet parking conditions, the key map information of the target parking area is extracted to construct a road topology map based on the key map information.

[0042] In the embodiments of the present application, the user can turn on the valet parking function through voice commands or by pressing buttons at positions such as the steering wheel. After the vehicle detects the valet parking start signal, it can call the in-vehicle high-precision map to obtain map data of the target parking area where the vehicle is currently located or the nearest parking lot to the vehicle. Furthermore, the embodiments of the present application can process the high-precision map information of the parking lot, extract key map element information such as lanes and parking spaces, and thus construct a road topology map with lanes as the smallest unit of the search algorithm and lane endpoints as search nodes, including important information such as the connection relationship between lanes, the association relationship between lanes, and the relative position relationship between lanes and parking spaces.

[0043] Thus, the embodiments of the present application construct a road topology map, thereby establishing the position association of key elements such as lanes and parking spaces, realizing the precise matching between parking spaces and lanes, and providing a reliable basis for generating a global path through a search algorithm in the subsequent process.

[0044] In step S102, based on the road topology map, the current position of the vehicle is used as the starting point, and lane matching is performed according to a preset matching rule to obtain multiple first alternative lanes, and the end position set by the user is used as the end point to perform lane matching to obtain multiple second alternative lanes.

[0045] After constructing the above road topology map, further, in an embodiment of the present application, the current position of the vehicle is used as the starting point to obtain a series of passable lanes as alternative lanes for the starting path of the global path; at the same time, when the user activates the parking or pick-up function by issuing an instruction through a terminal device such as a mobile phone APP (Application), the vehicle can perform lane matching according to the end point information (parking space or specific coordinate point) selected by the user, and also obtain a series of lanes that meet the vehicle passing conditions as alternative lanes for the ending path.

[0046] Thus, the embodiment of the present application can perform corresponding lane matching according to the starting point and end point of the vehicle, so as to be able to extract reasonable passable lanes as alternative lane paths at the starting point and the end point, ensuring the accuracy of subsequent path planning.

[0047] Optionally, in an embodiment of the present application, the preset matching rule includes: when the starting point or the end point is a parking space, the lanes matched by the starting point and the end point include the lane on one side close to the parking space and the reverse lane; when the starting point or the end point is a coordinate point, the starting point matches the current lane, and the end point matches the current lane and the reverse lane.

[0048] It should be noted that when performing lane matching based on the road topology map and according to the vehicle positioning information and the end point information selected by the user, in order to ensure the reasonableness of the subsequent planned path, the embodiment of the present application also needs to specifically analyze and process the starting and ending point types and relative positions to formulate corresponding matching rules.

[0049] Specifically, when the type of the starting point or the end point of the global path planning is a parking space, that is, when the vehicle is currently positioned in the parking space (performing a parking out action) or the selected end point is a specific parking space (performing a parking in action) when the user activates the function, the range of lanes that can be matched by the starting point or the end point includes the lane on one side of the parking space and the oncoming lane;

[0050] When the type of the starting point or the end point is a specific coordinate point rather than a parking space, considering the heading provided by the vehicle's current positioning information, in order to avoid planning abnormal paths that are unfavorable for passing such as U-turns, the embodiment of the present application needs to distinguish the lane matching of the starting and ending points:

[0051] 1. Since it is illegal to drive in reverse at the starting point, the starting point can only match the lane where the positioning point is currently located;

[0052] 2. To avoid path planning failure in the scenario where the starting and ending points are in reverse lanes, the ending point is allowed to match the current lane and the oncoming lane, that is, the generated path extends from one side of the lane where the starting point is located to the opposite side of the lane where the ending point is located.

[0053] Thus, the embodiments of the present application effectively ensure the rationality of the vehicle matching path and meet the driving and riding needs of users by specifically analyzing and processing the types and relative positions of the starting and ending points to formulate corresponding matching rules.

[0054] In step S103, calculate the matching degree between multiple first alternative lanes and multiple second alternative lanes, and generate a global path planning path for valet parking based on the lanes that meet the preset conditions.

[0055] After obtaining multiple alternative lanes for the starting and ending points, further, the embodiments of the present application can also combine the above alternative lanes, such as Figure 2 shown, and calculate the matching degree between the combined lanes, and combine the lane relationships provided in the above topological structure diagram to judge whether the starting and ending point lanes are the same lane or belong to the same section of the road (in opposite directions), so as to formulate corresponding planning schemes according to the judgment results to achieve more reasonable path planning.

[0056] Optionally, in an embodiment of the present application, calculating the matching degree between multiple first alternative lanes and multiple second alternative lanes, and generating a global path planning path for valet parking based on the lanes that meet the preset conditions includes: calculating multiple shortest distances from the extended areas of multiple first alternative lanes to the ending point as the first matching degree; calculating multiple shortest distances from the extended areas of multiple second alternative lanes to the starting point as the second matching degree; generating multiple lane combinations when both the first matching degree and the second matching degree are the minimum values, and based on each lane combination, and combining the relative positions of the corresponding lanes of the starting and ending points to generate a global path planning path.

[0057] It should be noted that the embodiments of the present application combine the starting and ending point alternative lanes to identify special scenarios, that is, the process of determining whether the matching lanes belong to the same section of the road is as follows:

[0058] 1. Calculate the shortest distances from the extended areas of multiple alternative lanes matched based on the starting point to the ending point, and use the shortest distances corresponding to each alternative lane as the corresponding first matching degree of the lane;

[0059] 2. Calculate the shortest distances from the extended areas of multiple alternative lanes matched based on the ending point to the starting point, and use the shortest distances corresponding to each alternative lane as the corresponding second matching degree of the lane;

[0060] 3. Analyze and judge the first matching degree and the second matching degree of multiple matching lanes of the above starting and ending points. If both the above first matching degree and the second matching degree are the minimum values, then the starting and ending point lane combination is the same section of road;

[0061] 4. Based on multiple lane combinations and in combination with the relative positions of the corresponding lanes of the starting point and the ending point, generate a global path planning route.

[0062] In addition, during the actual execution process, those skilled in the art can select other methods to calculate the above matching degree according to the actual situation, or identify special scenarios, and no specific limitations are made here.

[0063] Thus, the embodiments of the present application specifically handle special scenarios of whether the starting and ending points belong to the same section of road in the high-precision map according to the situation of the starting and ending point matching lanes, so as to achieve more accurate scenario recognition and reasonably plan the global path, further improving the rationality and scenario coverage rate of the global path planning of the AVP system, and effectively enhancing the user's driving confidence.

[0064] Optionally, in an embodiment of the present application, the relative positions of the corresponding lanes of the starting point and the ending point include: when the starting point and the ending point are in the same-direction lanes or opposite-direction lanes, and the path point corresponding to the starting point is in front of the ending point, then determine the global path plan based on the lane matched by the ending point; when the starting point and the ending point are in the same-direction lanes or opposite-direction lanes, and the path point corresponding to the starting point is behind the ending point, then determine the global path plan based on the lane matched by the starting point.

[0065] It should be noted that when the lanes matched by the starting point (parking space) and the ending point (parking space) belong to the same section of road, the embodiments of the present application can further judge the relative positions of the path points corresponding to the lanes matched by the starting and ending points (parking spaces):

[0066] Specifically, taking the remote summon parking out scenario as an example, the front and rear position relationships corresponding to the lane direction matched by the starting parking space can be divided into the following four situations:

[0067] Situation 1: When the lane direction matched by the starting parking space is the same-direction lane, and the path point corresponding to the starting parking space is in front of the ending point;

[0068] Situation 2: When the lane direction matched by the starting parking space is the opposite-direction lane, and the path point corresponding to the starting parking space is in front of the ending point;

[0069] Situation 3: When the lane direction matched by the starting parking space is the same-direction lane, and the path point corresponding to the starting parking space is behind the ending point;

[0070] Situation 4: When the lane direction matched by the starting parking space is the opposite-direction lane, and the path point corresponding to the starting parking space is behind the ending point.

[0071] For cases one and two, the embodiments of the present application use the lane that matches the end point as the reference to determine the global path plan; for cases three and four, the lane that matches the starting parking space is used as the reference to determine the global path plan.

[0072] Thus, the embodiments of the present application analyze the relative positions of the corresponding lanes at the starting point and the end point, thereby providing important guidance and basis for the subsequent global path planning, improving the reliability and safety of the planned path, and meeting the driving and riding needs of users.

[0073] Optionally, in an embodiment of the present application, a global path planning path for valet parking is generated based on lanes whose matching degree meets a preset condition, including: extracting corresponding lane information in the road topology map based on the matching degree and a preset search algorithm, so as to generate a global planning path in the full scenario according to the lane information.

[0074] It should be noted that the embodiments of the present application execute different planning schemes based on the judgment results of the above special scenarios, as described in detail below:

[0075] 1. When the lanes matched by the starting point and the end point of the global path planning belong to the same section of the road, there is no need to perform path planning through a search algorithm, and the path points are directly extracted based on the lane combination to generate a lane-level global planning path;

[0076] 2. When the lanes matched by the starting point (parking space) and the end point (parking space) do not belong to the same section of the road in the conventional scenario, the search algorithm is used to traverse based on the road topology map to obtain a global path plan that meets the requirements.

[0077] Thus, the embodiments of the present application perform AVP global path planning separately by considering special scenarios and conventional scenarios, further improving the efficiency and scenario coverage of the AVP system, and enhancing the user's willingness and experience in using this function.

[0078] The following will illustrate the global path planning method for valet parking proposed in the present application through specific embodiments and in combination with the accompanying drawings.

[0079] Figure 3 This is a schematic execution logic diagram of the global path planning method for valet parking in the embodiments of the present application. As Figure 3 shown, the execution process of the global path planning method for valet parking in the embodiments of the present application is as follows:

[0080] S1. Extract key element information of the high-precision map of the parking lot;

[0081] S2. Establish a topological map;

[0082] S3. Perform matching of the starting and ending parking spaces / lanes;

[0083] S4. Determine whether the matching lanes belong to the same section of road. If so, go to S5; otherwise, go to S7.

[0084] S5. Analyze the relative positions of the lanes corresponding to the starting and ending points.

[0085] S6. Determine the path planning scheme based on the lanes where the starting and ending points are matched.

[0086] S7. Use a search algorithm to determine the global path planning scheme.

[0087] S8. Extract path points to generate a lane-level global planned path.

[0088] The global path planning method for valet parking proposed according to the embodiments of the present application detects the actual working conditions of the vehicle, and when it detects that the actual working condition is a valet parking condition, extracts the key map information of the target parking area to construct a road topology map based on the key map information; based on the road topology map, uses the current position of the vehicle as the starting point, performs lane matching according to a preset matching rule to obtain multiple first alternative lanes, and uses the end position set by the user as the end point to perform lane matching to obtain multiple second alternative lanes, and then calculates the matching degree between the first and second alternative lanes, and generates a global path planning path for valet parking according to the lanes that meet the preset conditions. Based on the road topology map, the present application conducts targeted analysis and processing on the lane matching situation of the starting and ending points, thereby more accurately realizing scene recognition and greatly improving the driving experience of users.

[0089] Secondly, a global path planning device for valet parking proposed according to the embodiments of the present application is described with reference to the accompanying drawings.

[0090] Figure 4 It is a block diagram of the global path planning device for valet parking according to the embodiments of the present application.

[0091] As Figure 4 shown, the global path planning device 10 for valet parking includes: a construction module 100, a matching module 200, and a generation module 300.

[0092] Among them, the construction module 100 is used to detect the actual working conditions of the vehicle, and when it detects that the actual working condition is a valet parking condition, extracts the key map information of the target parking area to construct a road topology map based on the key map information.

[0093] The matching module 200 is used to, based on the road topology map, use the current position of the vehicle as the starting point, perform lane matching according to a preset matching rule to obtain multiple first alternative lanes, and use the end position set by the user as the end point to perform lane matching to obtain multiple second alternative lanes.

[0094] The generation module 300 is configured to calculate the matching degrees between multiple first alternative lanes and multiple second alternative lanes, and generate a global path planning path for valet parking based on the lanes whose matching degrees meet the preset conditions.

[0095] Optionally, in an embodiment of the present application, the generation module 300 includes: a first calculation unit, a second calculation unit, and a combination unit.

[0096] The first calculation unit is configured to calculate multiple shortest distances from the extended areas of the multiple first alternative lanes to the end point as the first matching degrees.

[0097] The second calculation unit is configured to calculate multiple shortest distances from the extended areas of the multiple second alternative lanes to the start point as the second matching degrees.

[0098] The combination unit is configured to generate multiple lane combinations when both the first matching degree and the second matching degree are at the minimum values, and based on the multiple lane combinations, and in combination with the relative positions of the corresponding lanes at the start point and the end point, to generate a global path planning path.

[0099] Optionally, in an embodiment of the present application, the preset matching rules include:

[0100] When the start point or the end point is a parking space, the lanes matched by the start point and the end point include the lane on the side close to the parking space and the reverse lane;

[0101] When the start point or the end point is a coordinate point, the start point matches the current lane, and the end point matches the current lane and the reverse lane.

[0102] Optionally, in an embodiment of the present application, the relative positions of the corresponding lanes at the start point and the end point include:

[0103] When the start point and the end point are in the same-direction lanes or reverse lanes, and the path point corresponding to the start point is in front of the end point, then determine the global path plan based on the lanes matched by the end point;

[0104] When the start point and the end point are in the same-direction lanes or reverse lanes, and the path point corresponding to the start point is behind the end point, then determine the global path plan based on the lanes matched by the start point.

[0105] Optionally, in an embodiment of the present application, the generation module 300 further includes: an extraction unit, configured to extract the corresponding lane information in the road topology map based on the matching degree and the preset search algorithm, so as to generate a global planning path in the full scenario according to the lane information.

[0106] It should be noted that the foregoing explanations of the embodiments of the global path planning method for valet parking also apply to the global path planning device for valet parking in this embodiment, and will not be elaborated here.

[0107] The global path planning device for valet parking proposed according to the embodiments of the present application detects the actual working conditions of the vehicle, and when it detects that the actual working condition is a valet parking condition, extracts the key map information of the target parking area to construct a road topology map based on the key map information; based on the road topology map, takes the current position of the vehicle as the starting point, performs lane matching according to a preset matching rule to obtain multiple first alternative lanes, and takes the end position set by the user as the end point to perform lane matching to obtain multiple second alternative lanes, and then calculates the matching degree between the first and second alternative lanes, and generates a global path planning path for valet parking according to the lanes whose matching degree meets the preset conditions. Based on the road topology map, the present application conducts targeted analysis and processing on the lane matching conditions of the starting and ending points, thereby more accurately realizing scene recognition and greatly improving the driving experience of users.

[0108] Figure 5 The structural schematic diagram of the vehicle provided by the embodiment of the present application. The vehicle may include:

[0109] A memory 501, a processor 502, and a computer program stored on the memory 501 and executable on the processor 502.

[0110] When the processor 502 executes the program, it implements the global path planning method for valet parking provided in the above embodiment.

[0111] Further, the vehicle further includes:

[0112] A communication interface 503 for communication between the memory 501 and the processor 502.

[0113] The memory 501 is used to store a computer program executable on the processor 502.

[0114] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0115] If the memory 501, the processor 502, and the communication interface 503 are implemented independently, the communication interface 503, the memory 501, and the processor 502 can be interconnected through a bus and communicate with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation,Figure 5 It is represented by only one thick line in the figure, but it does not mean that there is only one bus or one type of bus.

[0116] Optionally, in a specific implementation, if the memory 501, the processor 502, and the communication interface 503 are integrated on a single chip, the memory 501, the processor 502, and the communication interface 503 can communicate with each other through an internal interface.

[0117] The processor 502 may be a central processing unit (CPU for short), or an application specific integrated circuit (ASIC for short), or one or more integrated circuits configured to implement the embodiments of the present application.

[0118] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the global path planning method for valet parking as described above is implemented.

[0119] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0120] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0121] Any process or method description represented in a flowchart or otherwise described herein can be understood to represent a module, segment, or portion of code including one or N executable instructions for implementing a customized logical function or process. The scope of the preferred embodiments of the present application includes additional implementations, where functions can be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed. This should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0122] The logic and / or steps represented in a flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing a logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or N wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0123] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or combinations thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0124] Those of ordinary skill in the art can understand that all or part of the steps carried out in implementing the above-described embodiment methods can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0125] In addition, in each of the embodiments of the present application, the functional units can be integrated into one processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0126] The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A global path planning method for valet parking, characterized in that, It includes the following steps: Detect the actual working condition of the vehicle, and when it is detected that the actual working condition is the valet parking condition, extract the key map information of the target parking area to construct a road topology map based on the key map information; Based on the road topology map, use the current position of the vehicle as the starting point, perform lane matching according to a preset matching rule to obtain multiple first alternative lanes, and use the end position set by the user as the end point to perform lane matching to obtain multiple second alternative lanes; And Calculate the matching degree between the multiple first alternative lanes and the multiple second alternative lanes, and generate a global path planning path for valet parking based on the lanes that meet the preset conditions according to the matching degree.

2. The method according to claim 1, wherein The calculating the matching degree between the multiple first alternative lanes and the multiple second alternative lanes, and generating a global path planning path for valet parking based on the lanes that meet the preset conditions according to the matching degree includes: Calculate multiple shortest distances from the extended areas of the multiple first alternative lanes to the end point as the first matching degree; Calculate multiple shortest distances from the extended areas of the multiple second alternative lanes to the starting point as the second matching degree; Generate multiple lane combinations when both the first matching degree and the second matching degree are at the minimum value, and based on the multiple lane combinations, combine the relative positions of the corresponding lanes at the starting point and the end point to generate the global path planning path.

3. The method according to claim 1, wherein The preset matching rule includes: When the starting point or the end point is a parking space, the lanes matched by the starting point and the end point include the lane on the side close to the parking space and the reverse lane; When the starting point or the end point is a coordinate point, the starting point matches the current lane, and the end point matches the current lane and the reverse lane.

4. The method according to claim 2, wherein The relative positions of the corresponding lanes at the starting point and the end point include: When the starting point and the end point are in the same-direction lane or the reverse lane, and the path point corresponding to the starting point is in front of the end point, determine the global path plan based on the lane matched by the end point; When the starting point and the end point are in the same-direction lane or the reverse lane, and the path point corresponding to the starting point is behind the end point, determine the global path plan based on the lane matched by the starting point.

5. The method according to claim 4, wherein The generating a global path planning path for valet parking based on the lanes that meet the preset conditions according to the matching degree includes: Based on the matching degree and a preset search algorithm, extract the corresponding lane information in the road topology map to generate a global planning path in the full scenario according to the lane information.

6. A global path planning device for valet parking, characterized in that, It includes: A construction module for detecting the actual working condition of the vehicle, and when it is detected that the actual working condition is the valet parking condition, extracting the key map information of the target parking area to construct a road topology map based on the key map information; A matching module for, based on the road topology map, using the current position of the vehicle as the starting point, performing lane matching according to a preset matching rule to obtain multiple first alternative lanes, and using the end position set by the user as the end point to perform lane matching to obtain multiple second alternative lanes; And A generation module for calculating the matching degree between the multiple first alternative lanes and the multiple second alternative lanes, and generating a global path planning path for valet parking based on the lanes whose matching degree meets the preset conditions.

7. The device according to claim 6, characterized in that, The generation module includes: A first calculation unit for calculating multiple shortest distances from the extended areas of the multiple first alternative lanes to the end point as the first matching degree; A second calculation unit for calculating multiple shortest distances from the extended areas of the multiple second alternative lanes to the start point as the second matching degree; A combination unit for generating multiple lane combinations when both the first matching degree and the second matching degree are at the minimum value, and based on the multiple lane combinations, and in combination with the relative positions of the corresponding lanes of the start point and the end point, to generate the global path planning path.

8. The device according to claim 6, characterized in that, The preset matching rules include: When the start point or the end point is a parking space, the lanes matched by the start point and the end point include the lane on the side close to the parking space and the reverse lane; When the start point or the end point is a coordinate point, the start point matches the current lane, and the end point matches the current lane and the reverse lane.

9. The device according to claim 7, characterized in that, The relative positions of the corresponding lanes of the start point and the end point include: When the start point and the end point are in the same-direction lanes or reverse lanes, and the path point corresponding to the start point is in front of the end point, then determine the global path plan based on the lane matched by the end point; When the start point and the end point are in the same-direction lanes or the reverse lanes, and the path point corresponding to the start point is behind the end point, then determine the global path plan based on the lane matched by the start point.

10. The device according to claim 9, characterized in that, The generation module further includes: An extraction unit for extracting the corresponding lane information in the road topology map based on the matching degree and a preset search algorithm, so as to generate a global planning path in the full scenario according to the lane information.

11. A vehicle, characterized in that, Comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the global path planning method for valet parking according to any one of claims 1-5.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to be used to implement the global path planning method for valet parking according to any one of claims 1-5.

Images