Parking space search methods, devices and vehicles

Abstract

This application relates to a parking space search method, apparatus, and vehicle, belonging to the field of vehicle technology. The method includes: constructing a global map based on perception information within the vehicle's perception range when the vehicle's location is not covered by a high-precision map; determining a target exploration point; wherein the target exploration point is the optimal exploration point selected from the perception boundary points in the global map; planning a target path from the vehicle's location to the target exploration point on the global map based on a fast search random tree algorithm, using a first preset condition; wherein the first preset condition is used to make the tree nodes sampled by the fast search random tree algorithm tend to fall within the neighborhood of the target exploration point; and controlling the vehicle to cruise along the target planning path to search for available parking spaces. Thus, parking space search can be achieved efficiently, accurately, and intelligently even without high-precision map coverage.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more particularly to the field of autonomous driving technology, specifically to a parking space search method, device, and vehicle. Background Technology

[0002] As autonomous driving technology continues to advance into more advanced scenarios, valet parking has become one of the core services of intelligent vehicles. By integrating high-precision maps and multi-sensor data, it can achieve accurate parking space search and route planning in known map environments. However, traditional valet parking is heavily reliant on maps, causing it to fail to operate effectively in unknown map environments due to a lack of information such as parking space distribution and lane topology. Therefore, it is necessary to explore effective methods to achieve intelligent parking space exploration in unknown map environments. Summary of the Invention

[0003] This application provides a parking space search method, apparatus, and vehicle to at least solve the technical problem in related technologies that it is difficult to achieve intelligent parking space exploration in unknown map environments. The technical solution of this application is as follows:

[0004] In a first aspect, this application provides a parking space search method, comprising: when the vehicle location is not within the coverage area of ​​a high-precision map, constructing a global map based on perception information within the vehicle's perception range corresponding to the vehicle location; wherein the perception information includes, but is not limited to, perception boundary points not obscured by obstacles and obstacles; determining a target exploration point; wherein the target exploration point is the optimal exploration point selected from the perception boundary points in the global map; based on a first preset condition, using a fast search random tree algorithm to plan a target planning path from the vehicle location to the target exploration point on the global map; wherein the first preset condition is used to make the tree nodes sampled by the fast search random tree algorithm tend to fall into the neighborhood of the target exploration point; controlling the vehicle to cruise along the target planning path to search for available parking spaces.

[0005] Based on the aforementioned technical means, this application can construct a global map based on the perception information within the vehicle's perception range when the vehicle is in an unknown map environment (not in a high-precision map coverage area), and select the best target exploration point from it. Then, using a fast search random tree algorithm, a target planning path from the vehicle's position to the target exploration point is planned according to the first preset conditions, and the tree nodes tend to fall into the neighborhood of the target exploration point. This avoids the problem of blindly exploring parking spaces or being unable to carry out intelligent exploration due to the lack of effective map information in an unknown environment, and achieves parking space exploration efficiently, accurately, and intelligently.

[0006] In one possible implementation, if no available parking space is found when the vehicle cruises to the target exploration point, the above steps of building, determining, planning, and cruising are repeated based on the vehicle's position after cruising, until an available parking space is found.

[0007] Based on the aforementioned technical means, this application can re-execute the steps of building a global map, determining the target exploration point, planning the target path, and controlling vehicle navigation based on the vehicle's position after cruising to the target exploration point if no available parking space is found. This avoids the problem of search interruption or getting stuck in a local invalid search due to the limited search range of a single search or the deviation in the selection of the target exploration point, thereby searching for available parking spaces more comprehensively and efficiently, and improving the completeness and success rate of parking space search.

[0008] In one possible implementation, a global map is constructed based on perception information within the vehicle's perception range corresponding to the vehicle's location, including: constructing a local map corresponding to the vehicle's perception range based on the perception information; and determining the local map as the global map in the absence of a first exploration point; wherein the first exploration point is the exploration point closest to the vehicle's location that the vehicle passes through after parking planning.

[0009] Based on the aforementioned technical means, this application can first construct a local map based on the perception information within the vehicle's perception range, thereby quickly integrating effective information in the current environment where the vehicle is located. Then, when there is no first exploration point (i.e., the nearest exploration point along the path after the vehicle's parking planning), the local map can be directly determined as the global map, reducing unnecessary consumption of computing resources and data processing volume, and improving the efficiency and response speed of the parking space search process.

[0010] In one possible implementation, a global map is constructed based on the perception information within the vehicle's perception range corresponding to the vehicle's location. This also includes: in the presence of a first exploration point, fusing the local map and the historical global map to obtain a fused map; wherein the historical global map is obtained by incorporating target tree nodes into the global map established at the first exploration point, and the target tree nodes are tree nodes sampled when planning the path from the first exploration point to the vehicle's location using a fast search random tree algorithm; and based on the target search range, modifying the fused map to obtain the global map, wherein the target search range is defined based on the vehicle's location.

[0011] Based on the aforementioned technical means, this application can merge a local map constructed based on the current perception information with a historical global map when a first exploration point exists, and then modify the merged map based on the target search range defined by the vehicle position. This prevents the map information from being too complicated and distracting the search effort, and obtains a global map including key search areas, effectively improving the efficiency and accuracy of subsequent parking space searches.

[0012] In one possible implementation, based on the target search range, the fused map is modified to obtain a global map, including: determining the gain value of each tree node in the fused map; deleting the first exploration point and tree nodes in the fused map whose gain value is less than a preset gain value and are outside the target search range, to obtain the global map; wherein, the gain value of each tree node is determined based on the distance between each tree node and other tree nodes in the fused map and / or the number of tree nodes contained in the neighborhood of each tree node.

[0013] Based on the aforementioned technical means, this application can determine the gain value of each tree node based on the distance between the tree node and other tree nodes in the fused map and / or the number of tree nodes in the neighborhood, and delete the first exploration point and tree nodes outside the target search range whose gain value is less than the preset value to modify the fused map. This avoids too many low-value and redundant tree nodes in the fused map interfering with the search process, thereby improving the quality and usability of the global map and thus improving the efficiency and accuracy of parking space search.

[0014] In one possible implementation, determining the target exploration point includes: determining whether a first perception boundary point exists, wherein the first perception boundary point is a boundary point located within the target search range; and, if the existence of the first perception boundary point is determined, determining the target exploration point from the first perception boundary point.

[0015] Based on the above technical means, this application can first determine whether there are first perception boundary points within the target search range, thus avoiding blindly performing subsequent complex screening operations when there are no relevant valid boundary points. It can quickly focus on valuable boundary points within the target search range and accurately determine the target exploration points from them, thereby improving the efficiency of target exploration point determination.

[0016] In one possible implementation, determining the target exploration point from the first sensing boundary points includes: identifying the sensing boundary point with the highest exploration value among the first sensing boundary points as the target exploration point; wherein the exploration value of the first sensing boundary point is determined based on the distance between the vehicle position and the first sensing boundary point, and the angle between the vehicle's first orientation and the vehicle's second orientation pointing towards the first sensing boundary point.

[0017] Based on the aforementioned technical means, this application can determine the exploration value of a vehicle by considering the distance between its position and the first sensing boundary point, as well as the angle between the vehicle's first orientation and the second orientation pointing towards the first sensing boundary point. The point with the highest exploration value is selected as the target exploration point, thus avoiding the problems of unreasonable vehicle driving paths and low exploration efficiency caused by arbitrarily selecting exploration points. This enables the vehicle to plan its exploration route in a more efficient manner, prioritizing the exploration of the most valuable areas for searching parking spaces, thereby improving the overall success rate and speed of parking space search.

[0018] In one possible implementation, determining the target exploration point further includes: determining the target exploration point from a second perception boundary point if it is determined that there is no first perception boundary point; wherein the second perception boundary point is a perception boundary point in the global map that is outside the target search range.

[0019] Based on the above technical means, this application can determine the target exploration point from the second perception boundary point outside the target search range when there is no first perception boundary point within the target search range, thereby increasing the possibility of finding available parking spaces and improving the success rate of parking space search.

[0020] In one possible implementation, the target exploration point is determined from the second sensing boundary points, including: determining the connecting path with the minimum path length between the vehicle position and each second sensing boundary point based on the branch and bound method; wherein the connecting path connects the vehicle position and the corresponding second sensing boundary point through multiple tree nodes in the global map; and determining the sensing boundary point with the minimum connecting path length among the second sensing boundary points as the target exploration point.

[0021] Based on the aforementioned technical means, this application can determine the connection path with the minimum path length between the vehicle position and each second sensing boundary point by using the branch and bound method, and use the corresponding second sensing boundary point as the target exploration point. This avoids the waste of time and resources caused by blindly exploring areas outside the target search range, and can efficiently and accurately select the most worthwhile points to explore from the sensing boundary points outside the range, thereby improving the efficiency of parking space search.

[0022] In one possible implementation, based on a first preset condition, a fast search random tree algorithm is used to plan a target planning path from the vehicle's location to the target exploration point on a global map. This includes: generating multiple planned branches from the vehicle's location to the target exploration point using the fast search random tree algorithm based on the first preset condition; determining the planned branch with the highest exploration value among the multiple planned branches as the target planning path; wherein the exploration value of the planned branch is related to at least one of the following: the forward distance of the edge between two adjacent tree nodes in the planned branch relative to the vehicle's orientation; the angle between different edges in the planned branch; the distance between the tree node in the planned branch and the vehicle's location; the similarity between the planned branch and the planned path from the first exploration point to the vehicle's location; and the number of unknown voxels in the neighborhood of the tree node in the planned branch.

[0023] Based on the above technical means, this application can generate multiple planned branches using a fast search random tree algorithm based on the first preset conditions, and select the branch with the highest value as the target planned path according to the exploration value related to the forward distance, edge angle, tree node distance, path similarity, number of unknown voxels, etc. This avoids the situation where single path planning may fall into local optima or not meet the actual exploration needs, and can plan a path that is more in line with the vehicle driving characteristics, more efficient and more meaningful for exploration.

[0024] In one possible implementation, the first preset condition includes: when the target value is less than or equal to a preset value threshold, randomly generating a tree node in the neighborhood of the target exploration point; and when the target value is greater than the preset value threshold, randomly generating a tree node outside the neighborhood of the target exploration point; wherein the target value is a value randomly generated within the preset value range.

[0025] Based on the above technical means, this application can flexibly decide whether to randomly generate tree nodes in or outside the neighborhood of the target exploration point by comparing the target value with a preset value threshold, thereby avoiding the tree node generation being too concentrated or scattered during path planning by the fast search random tree algorithm, and thus effectively finding a high-quality path from the vehicle location to the target exploration point.

[0026] Secondly, this application provides a parking space search device, comprising: a construction unit, a determination unit, a planning unit, and a control unit; the construction unit is used to construct a global map based on perception information within the vehicle's perception range corresponding to the vehicle's location when the vehicle's location is not within the coverage area of ​​a high-precision map; wherein, the perception information includes, but is not limited to, perception boundary points not obscured by obstacles and obstacles; the determination unit is used to determine a target exploration point; wherein, the target exploration point is the best exploration point selected from the perception boundary points in the global map; the planning unit is used to plan a target planning path from the vehicle's location to the target exploration point on the global map based on a first preset condition and using a fast search random tree algorithm; wherein, the first preset condition is used to make the tree nodes sampled by the fast search random tree algorithm tend to fall into the neighborhood of the target exploration point; the control unit is used to control the vehicle to cruise along the target planning path to search for available parking spaces.

[0027] In one possible implementation, the building unit, determining unit, planning unit, and control unit are respectively used to re-execute the above-mentioned building, determining, planning, and cruising steps based on the vehicle's position after cruising, if no available parking space is found when the vehicle cruises to the target exploration point, until an available parking space is found.

[0028] In one possible implementation, the building unit is specifically used to: construct a local map corresponding to the vehicle's perception range based on perception information; and determine the local map as the global map in the absence of a first exploration point; wherein the first exploration point is the exploration point closest to the vehicle's position that the vehicle will pass through after parking planning.

[0029] In one possible implementation, the building unit is specifically used for: merging the local map and the historical global map in the presence of a first exploration point to obtain a merged map; wherein the historical global map is obtained by incorporating target tree nodes into the global map established at the first exploration point, and the target tree nodes are tree nodes sampled when planning the path from the first exploration point to the vehicle location using a fast search random tree algorithm; and modifying the merged map based on the target search range to obtain a global map, wherein the target search range is defined based on the vehicle location.

[0030] In one possible implementation, the building unit is specifically used to: determine the gain value of each tree node in the fused map; delete the first exploration point and tree nodes in the fused map whose gain value is less than a preset gain value and are outside the target search range, to obtain a global map; wherein, the gain value of each tree node is determined based on the distance between each tree node and other tree nodes in the fused map and / or the number of tree nodes contained in the neighborhood of each tree node.

[0031] In one possible implementation, the determining unit is specifically used to: determine whether a first sensing boundary point exists, wherein the first sensing boundary point is a boundary point located within the target search range; and, if the existence of the first sensing boundary point is determined, determine a target exploration point from the first sensing boundary point.

[0032] In one possible implementation, the determining unit is specifically used to: determine the first sensing boundary point with the highest exploration value among the first sensing boundary points as the target exploration point; wherein the exploration value of the first sensing boundary point is determined based on the distance between the vehicle position and the first sensing boundary point, and the angle between the vehicle's first orientation and the vehicle position's second orientation pointing to the first sensing boundary point.

[0033] In one possible implementation, the determining unit is specifically used to: determine the target exploration point from the second perception boundary points if it is determined that there is no first perception boundary point; wherein the second perception boundary point is a perception boundary point in the global map that is outside the target search range.

[0034] In one possible implementation, the determining unit is specifically used to: determine the connection path with the minimum path length between the vehicle position and each second sensing boundary point based on the branch and bound method; wherein the connection path connects the vehicle position and the corresponding second sensing boundary point through multiple tree nodes in the global map; and determine the sensing boundary point with the minimum connection path length among the second sensing boundary points as the target exploration point.

[0035] In one possible implementation, the planning unit is specifically used to: generate multiple planned paths from the vehicle's location to the target exploration point using a fast search random tree algorithm based on a first preset condition; and determine the planned path with the highest exploration value among the multiple planned paths as the target planned path; wherein the exploration value of the planned path is related to at least one of the following: the forward distance of the edge between two adjacent tree nodes in the planned path relative to the vehicle's orientation; the angle between different edges in the planned path; the distance between the tree node in the planned path and the vehicle's location; the similarity between the planned path and the planned path from the first exploration point to the vehicle's location; and the number of unknown voxels in the neighborhood of the tree node in the planned path.

[0036] Thirdly, this application provides a vehicle that includes the parking space search device described in the second aspect.

[0037] Fourthly, this application provides an electronic device, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the method described in the first aspect and any possible implementation thereof.

[0038] Fifthly, this application provides a computer-readable storage medium that, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the methods described in the first aspect and any of their possible implementations.

[0039] Sixthly, this application provides a computer program product including computer instructions that, when executed on an electronic device, cause the electronic device to perform the method described in the first aspect and any possible implementation thereof.

[0040] It should be noted that the technical effects of any of the implementation methods in aspects two through six can be found in the technical effects of the corresponding implementation methods in aspect one, and will not be repeated here.

[0041] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application, and do not constitute an undue limitation of this application.

[0043] Figure 1 This is a schematic diagram illustrating the structure of a parking space search system according to an exemplary embodiment;

[0044] Figure 2 This is a flowchart illustrating a parking space search method according to an exemplary embodiment;

[0045] Figure 3 This is a schematic diagram illustrating a parking space search process according to an exemplary embodiment;

[0046] Figure 4 This is a schematic diagram illustrating a fast search random tree construction process according to an exemplary embodiment;

[0047] Figure 5 This is a schematic diagram illustrating a fast search random tree construction result according to an exemplary embodiment;

[0048] Figure 6 This is a schematic diagram illustrating a process for determining a target planning path according to an exemplary embodiment;

[0049] Figure 7 This is a block diagram illustrating a parking space search device according to an exemplary embodiment;

[0050] Figure 8 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0051] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0052] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0053] In the embodiments of this application, the words "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the words "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a specific manner.

[0054] The technical solutions of the embodiments of this application will be described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0055] The parking space search method provided in this application can be applied to vehicles. Vehicles can also be referred to as vehicles, mobile carriers, electric vehicles (EVs), hybrid electric vehicles (HEVs), plug-in hybrid electric vehicles (PHEVs), fuel cell vehicles (FCVs), autonomous vehicles, intelligent and connected vehicles (ICVs), driverless vehicles, etc.

[0056] In this application, the vehicle can be a sedan, a sport utility vehicle (SUV), a truck, an electric vehicle, a motorcycle, a tricycle, a special vehicle (such as an ambulance, fire truck, police car, etc.), a driverless taxi, an intelligent connected bus, an autonomous logistics vehicle, an electric truck, etc. Furthermore, this method is also applicable to various special-purpose vehicles, such as agricultural vehicles, mining vehicles, forestry vehicles, airport vehicles, and port vehicles. This application does not impose specific limitations in this regard.

[0057] like Figure 1 As shown, the parking space search system provided in this application includes a parking space search device 101 and a data acquisition device 102.

[0058] Optionally, Figure 1 A communication connection can be established between the parking space search device 101 and the data acquisition device 102.

[0059] In practical applications, the parking space search device 101 can communicate with one or more data acquisition devices 102.

[0060] For ease of understanding, this application uses the communication connection between a parking space search device 101 and a data acquisition device 102 as an example for illustration.

[0061] Optionally, Figure 1 The parking space search device 101 and the data acquisition device 102 can be functional modules integrated into the same device, or they can be independently set up. This application does not impose any restrictions on this.

[0062] It is easy to understand that when the parking space search device 101 and the data acquisition device 102 are functional modules integrated into the same device, the communication method between the parking space search device 101 and the data acquisition device 102 is the same as the communication method between internal modules of the device. In this case, the communication process between the two is the same as the communication process when the parking space search device 101 and the data acquisition device 102 are set up independently.

[0063] For ease of understanding, this application mainly uses the example of parking space search device 101 and data acquisition device 102 being set up independently of each other.

[0064] Figure 1 The data acquisition device 102 can collect perception information within the vehicle's perception range corresponding to the vehicle's location and send the perception information to the parking space search device 101. The parking space search device 101 can construct a global map based on the perception information and determine a target exploration point. Then, based on a first preset condition, it uses a fast search random tree algorithm to plan a target planning path from the vehicle's location to the target exploration point on the global map, further controlling the vehicle to cruise along the target planning path to search for available parking spaces.

[0065] Optionally, Figure 1 The parking space search device 101 can be a terminal, a server, or other types of electronic devices. Figure 1 The diagram shown is merely an example of the device configuration of the parking space search device 101 and does not constitute a limitation thereof.

[0066] When the parking space search device 101 is a terminal, the terminal can be a device providing voice and / or data connectivity to the user, a handheld device with wireless connectivity, or other processing device connected to a wireless modem. The terminal can communicate with one or more core networks via a radio access network (RAN). The terminal can be a mobile terminal, such as a computer with a mobile terminal, or a mobile device built into a fault detection system that exchanges voice and / or data with the radio access network, such as a mobile phone, tablet, laptop, netbook, or personal digital assistant (PDA). This application does not impose any limitations on this.

[0067] When the parking space search device 101 is a server, the server can be a single server or a server cluster consisting of multiple servers. In some embodiments, the server cluster can also be a distributed cluster. This application does not impose any limitations in this regard.

[0068] It should be noted that the structures illustrated in the embodiments of this application do not constitute a limitation on the group obstacle detection system. It may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0069] For ease of understanding, the parking space search method provided in this application will be described in detail below with reference to the accompanying drawings.

[0070] Figure 2 This is a flowchart illustrating a parking space search method according to an exemplary embodiment, such as... Figure 2 As shown, the parking space search method includes the following steps: S201-S204.

[0071] S201. When the vehicle's location is not within the coverage area of ​​the high-precision map, construct a global map based on the perception information within the vehicle's perception range corresponding to the vehicle's location.

[0072] The perceived information may include, but is not limited to, perceived boundary points that are not obscured by obstacles and obstacles themselves.

[0073] Optionally, the sensing information can be set according to actual needs. For example, the sensing information may include walls, curbs, cones, etc., or it may be ground markings or lane lines. This application does not impose specific limitations in this regard.

[0074] In one possible implementation, if the parking space search device does not store a high-precision map corresponding to the current environment, it can send a request to the user via the in-vehicle interactive interface or user terminal to request whether to start mapless valet parking, and then perform the corresponding operation after waiting for the user's confirmation.

[0075] For example, the parking space search device can send a message to the user via the in-vehicle interface or user terminal stating, "The vehicle location has not been entered into the high-precision map. Please confirm whether to activate the mapless valet parking mode." If the user selects to confirm the activation of the mapless valet parking mode, the parking space search device can output a prompt message via the in-vehicle interface or user terminal: "In mapless mode, the vehicle may trigger a safety pause due to environmental complexity exceeding the algorithm's boundaries, requiring the user to take over control at any time," and then activate the mapless valet parking mode.

[0076] In one possible implementation, the parking space search device can communicate with onboard sensors. In response to a mapless parking request, the parking space search device can collect sensing information via the onboard sensors.

[0077] Optionally, the vehicle-mounted sensor can be configured as needed. For example, the vehicle-mounted sensor can be a LiDAR, a camera, an ultrasonic radar, or a combination of LiDAR, a camera, and an ultrasonic radar. This application does not impose specific limitations in this regard.

[0078] In one possible implementation, the parking space search device can construct a local map corresponding to the vehicle's perception range based on perception information, and determine the local map as the global map if a first exploration point does not exist. The first exploration point is the exploration point closest to the vehicle's location that the vehicle will pass through after parking planning.

[0079] In other words, the parking space search device can identify a local map as the global map even when a historical global map is not available.

[0080] The historical global map can be obtained by incorporating the target tree node into the global map established at the first exploration point. The target tree node can be a tree node sampled when planning the path from the first exploration point to the vehicle location using the fast search random tree algorithm.

[0081] Alternatively, the parking space search device can merge the local map and the historical global map to obtain a merged map, provided a first exploration point exists. The parking space search device can then modify the merged map based on the target search area to obtain a global map.

[0082] The target search area is defined based on the vehicle's position. The target search area can be a local region in three-dimensional space centered on the vehicle's current position.

[0083] Optionally, the target search range can be set according to actual needs. For example, the target search range can be smaller than or equal to the vehicle's perception range. This application does not impose specific limitations in this regard.

[0084] Specifically, the parking space search device can determine the gain value of each tree node in the fused map. Then, the parking space search device deletes the first exploration point in the fused map and tree nodes in the fused map whose gain value is less than the preset gain value and are outside the target search range, thus obtaining a global map.

[0085] The gain value of each tree node is determined based on the distance between each tree node and other tree nodes in the fused map and / or the number of tree nodes contained in the neighborhood of each tree node.

[0086] In one possible implementation, the gain value of each tree node is negatively correlated with the distance between that tree node and other tree nodes in the merged map, and also with the number of tree nodes contained in its neighborhood. In other words, the shorter the distance between a tree node and other tree nodes in the merged map, the higher the gain value; and the more tree nodes a node contains in its neighborhood, the higher the gain value. This avoids fragmentation of the constructed global map, making it difficult to form continuous paths.

[0087] In one possible implementation, the newly added tree nodes to the global map satisfy the following first formula:

[0088]

[0089] in, It can be used to represent tree nodes that have been newly added to the global map. It can be used to characterize including The path. Can be used for characterization Its exploratory value. It can be used to represent other tree nodes in the global map. It can be used to characterize point P and The Euclidean distance between them. It can be used to characterize a preset distance threshold. It can be used to characterize point P and The ratio of the map distance to the Euclidean distance. It can be used to characterize a preset ratio threshold.

[0090] S202. Determine the target exploration point.

[0091] Among them, the target exploration point is the best exploration point selected from the perception boundary points in the global map.

[0092] In one possible implementation, the parking space search device can determine whether a first sensing boundary point exists.

[0093] The first perception boundary point can be a boundary point located within the target search range. The first boundary point satisfies the following formulas 2 to 4:

[0094]

[0095]

[0096]

[0097] Among them, F L It can be used to characterize the first sensing boundary point. H F It can be used to characterize the target search range. P can be used to characterize a tree node. FOV(P) can be used to characterize the field of view of point P, that is, the search range of the vehicle within the tree node. P B It can be used to characterize the current position of a vehicle. FOV (P B ) can be used to characterize P B The field of vision, that is, the vehicle's perception range.

[0098] The first formula can be used to characterize a perception boundary point within the target search range as the first perception boundary point. The second and third formulas can be used to characterize that the first perception boundary point must be within the field of view of at least one tree node, or within the vehicle's perception range.

[0099] In one possible implementation, the parking space search device can determine the target exploration point from the first sensing boundary point if the existence of the first sensing boundary point is determined.

[0100] Specifically, the parking space search device can identify the highest-value perception boundary point among the first perception boundary points as the target exploration point.

[0101] The exploration value of the first sensing boundary point can be determined based on the distance between the vehicle's position and the first sensing boundary point, as well as the angle between the vehicle's first orientation and the second orientation pointing from the vehicle's position to the first sensing boundary point. This ensures that the parking space search device can guarantee that the vehicle reaches the first sensing boundary point with minimal cost (shortest path, turning), that is, by minimizing the vehicle's turning and travel path.

[0102] In another possible implementation, the parking space search device can determine the target exploration point from the second perception boundary point if the first perception boundary point does not exist. That is, the parking space search device can determine the target exploration point from the perception boundary point outside the target search range on the global map if the perception boundary point does not exist within the target search range.

[0103] The second perception boundary point can be a perception boundary point located outside the target search range in the global map.

[0104] Specifically, the parking space search device can determine the connection path with the shortest path length between the vehicle position and each second sensing boundary point based on the branch and bound method, and thus determine the sensing boundary point with the shortest connection path length among the second sensing boundary points as the target exploration point.

[0105] The connection path can be a combination of multiple tree nodes in the global map that connect the vehicle's location with the corresponding second perception boundary point.

[0106] In other words, the parking space search device can efficiently traverse the second sensing boundary points using a branch and bound method based on the traveling salesman problem: First, the global map and the set of boundary points are dynamically updated, and each second sensing boundary point is mapped to a dynamic distance weight between cities in the branch and bound method, constructing a cost matrix. Then, the optimal path is searched using the branch and bound method to quickly generate a priority access sequence for the second sensing boundary points. Finally, the current optimal second sensing boundary point is determined as the target exploration point.

[0107] S203. Based on the first preset condition, a fast search random tree algorithm is used to plan the target planning path from the vehicle location to the target exploration point on the global map.

[0108] The first preset condition can be used to make the tree nodes sampled by the fast search random tree algorithm tend to fall into the neighborhood of the target exploration point.

[0109] In one possible implementation, the parking space search device can generate multiple planned routes from the vehicle location to the target exploration point based on a first preset condition and using a fast search random tree algorithm.

[0110] Specifically, the parking space search device can randomly generate a tree node within the neighborhood of the target exploration point when the target value is less than or equal to a preset value threshold. Conversely, the parking space search device can randomly generate a tree node outside the neighborhood of the target exploration point when the target value is greater than the preset value threshold.

[0111] The target value can be a value randomly generated within a preset value range.

[0112] Optionally, the preset numerical range can be set according to actual needs. For example, the preset numerical range can be 0-1, or the preset numerical range can be 0-2. This application does not impose specific limitations in this regard.

[0113] Optionally, the preset value threshold can be set according to a preset value range and actual needs. For example, when the preset value range is 0-1, the preset value threshold can be 0.7 or 0.6; or when the preset value range is 0-2, the preset value threshold can be 1.5 or 1.4. This application does not impose specific limitations on this.

[0114] In one possible implementation, the parking space search device can identify the most valuable planned route among multiple planned routes and determine it as the target planned path.

[0115] The exploration value of a planned branch path is related to at least one of the following: the distance of the edge between two adjacent tree nodes in the planned branch path relative to the vehicle's orientation; the angle between different edges in the planned branch path; the distance between a tree node in the planned branch path and the vehicle's position; the similarity between the planned branch path and the planned path from the first exploration point to the vehicle's position; and the number of unknown voxels in the neighborhood of a tree node in the planned branch path.

[0116] In one possible implementation, the exploratory value of planning branch paths satisfies the following fifth and sixth formulas:

[0117]

[0118]

[0119] in, It can be used to characterize the planned branch roads from the vehicle's current location to the target exploration point. Can be used for characterization Its exploratory value. Can be used for characterization The j-th node in the tree. DTW ( ) can be used to characterize The gain value corresponding to the similarity between the planned path from the first exploration point to the vehicle's location and the path from the first exploration point. Can be used for characterization The penalty parameter corresponding to the angle between different sides of the middle. It can be used to characterize the exploratory value of point P. Can be used for characterization The number of unknown voxels in the neighborhood of a tree node P, which is also the area of ​​the unknown region. Can be used for characterization The distance between the middle tree node P and the vehicle's location. Can be used for characterization The penalty parameter is the distance the edge between two adjacent tree nodes travels relative to the vehicle's orientation.

[0120] S204. Control the vehicle to cruise along the target planned path to search for available parking spaces.

[0121] In one possible implementation, the parking space search device can control a vehicle to cruise along the target planned path based on the coordinates of multiple tree nodes in the target planned path in order to search for available parking spaces.

[0122] In one possible implementation, the parking space search device can control the vehicle to park if a parking space is found. Alternatively, if the vehicle has cruised to the target exploration point but no available parking space has been found, the parking space search device can re-execute the above-described steps of constructing, determining, planning, and cruising based on the vehicle's position after cruising, until an available parking space is found.

[0123] Based on the above technical solution, this application can construct a global map based on the perception information within the vehicle's perception range when the vehicle is in an unknown map environment (not in a high-precision map coverage area), and select the best target exploration point from it. Then, using a fast search random tree algorithm, a target planning path from the vehicle's position to the target exploration point is planned according to the first preset conditions, and the tree nodes tend to fall into the neighborhood of the target exploration point. This avoids the problem of blindly exploring parking spaces or being unable to carry out intelligent exploration due to the lack of effective map information in unknown environments, and achieves parking space exploration efficiently, accurately and intelligently.

[0124] In some embodiments, such as Figure 3 The diagram shown is a schematic of a parking space search process provided in this application.

[0125] In one possible implementation, the process begins with the parking space search device, in the presence of a high-definition map, controlling the vehicle to cruise towards a selected parking space. During this cruise, a global map is built based on a fast search random tree and a first perception boundary point. The parking space search device can determine if the selected parking space is empty. If empty, it performs automatic parking, placing the vehicle in the space; otherwise, it searches for a parking space based on the high-definition map. The parking space search device can then determine if an empty parking space exists on the high-definition map. If an empty space exists, it performs automatic parking, placing the vehicle in the space; otherwise, it determines if a second perception boundary point exists. If so, it determines a target exploration point based on the second perception boundary point in the global map. The parking space search device can then control the vehicle to cruise towards the target exploration point. Alternatively, if no second perception boundary point exists, the parking space search device can determine if a first perception point exists. If so, it plans a target route based on the first perception boundary point; otherwise, the process ends.

[0126] The parking space search device can plan a target path based on a first sensing boundary point when the vehicle arrives at the target exploration point. The device can then cruise along the planned path and determine if an empty parking space exists. If one exists, it performs automatic parking, placing the vehicle in the space and ending the process. Otherwise, the device can determine if a second sensing boundary point exists. If the first sensing boundary point exists, the device can plan a target path based on it; otherwise, it can determine if a second sensing boundary point exists.

[0127] The parking space search device can determine the target exploration point based on the second perception boundary point in the global map if a second perception boundary exists; otherwise, the process ends.

[0128] In another possible implementation, the parking space search device can establish a global map by quickly searching a random tree and first sensing boundary points, provided a high-definition map is available. The parking space search device can then determine a second sensing boundary point; if it exists, the target exploration point is determined based on the second sensing boundary point in the global map; if it does not exist, the device then determines whether a first sensing boundary point exists.

[0129] In some embodiments, such as Figure 4 The diagram shown is a schematic of a fast search random tree construction process provided in this application.

[0130] In one possible implementation, the parking space search device can determine the vehicle's location and the target exploration point. The parking space search device can prune the previously constructed fast search random tree. The parking space search device can then reconstruct the fast search random tree based on the remaining nodes.

[0131] The parking space search device can determine a target value and a preset value threshold. The device can then determine whether the target value is less than or equal to the preset value threshold.

[0132] The parking space search device can randomly generate a tree node within the neighborhood of the target exploration point when the target value is less than or equal to a preset value threshold, and randomly generate a tree node outside the neighborhood of the target exploration point when the target value is greater than the preset value threshold.

[0133] The parking space search device can determine whether the number of times it generates a space is less than a preset threshold. If so, it will re-determine the target value; otherwise, it will end the process.

[0134] In some embodiments, such as Figure 5 The diagram shown is a schematic representation of the construction result of a fast search random tree provided in this application.

[0135] In one possible implementation method Figure 5 This includes a fast search random tree that is continuously generated as the vehicle travels from point A to point B. Figure 5 It also includes the vehicle's target search range at point B, the original tree nodes, the newly added tree nodes, and multiple first perception boundary points and second perception boundary points.

[0136] In some embodiments, such as Figure 6 The diagram shown is a flowchart illustrating a method for determining a target planning path as provided in this application.

[0137] In one possible implementation, the parking space search device can determine the vehicle's location and multiple first sensing boundary points. The parking space search device can then determine a target exploration point from these first sensing boundary points. Based on first preset conditions, the parking space search device can use a fast search random tree algorithm to generate multiple planned routes from the vehicle's location to the target exploration point. The parking space search device can determine that the optimal exploration value is 0. The parking space search device can determine the exploration value of each planned route.

[0138] Determining the exploration value of each planned path can include:

[0139] The parking space search device can count from 1 to N, where N is the number of planned routes. The device calculates the exploration value of the i-th planned route and determines whether its exploration value is greater than the optimal exploration value. If so, the exploration value of the i-th planned route is determined as the optimal exploration value; otherwise, it checks if i equals N. If i equals N, the planned route corresponding to the optimal exploration value is determined as the target planned route; otherwise, i is incremented by 1.

[0140] The above primarily describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the parking space search device or electronic device includes corresponding hardware structures and / or software modules for performing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0141] This application embodiment can, according to the above method, exemplarily divide a parking space search device or electronic device into functional modules. For example, the parking space search device or electronic device may include various functional modules corresponding to each functional division, or two or more functions may be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division; in actual implementation, there may be other division methods.

[0142] Figure 7 This is a block diagram illustrating a parking space search device according to an exemplary embodiment. (Refer to...) Figure 7 The parking space search device includes: a construction unit 701, a determination unit 702, a planning unit 703, and a control unit 704.

[0143] In one possible implementation, construction unit 701 is used to construct a global map based on perception information within the vehicle's perception range corresponding to the vehicle's location, even when the vehicle's location is not within the coverage area of ​​the high-precision map.

[0144] In one possible implementation, a determining unit 702 is used to determine the target exploration point.

[0145] In one possible implementation, planning unit 703 is used to plan a target planning path from the vehicle location to the target exploration point on the global map based on a first preset condition and using a fast search random tree algorithm.

[0146] In one possible implementation, control unit 704 controls the vehicle to cruise along a target planned path to search for available parking spaces.

[0147] In one possible implementation, the construction unit 701, the determination unit 702, the planning unit 703, and the control unit 704 are respectively used to re-execute the above-mentioned construction, determination, planning, and cruising steps based on the vehicle's position after cruising, until an available parking space is found, if the vehicle has not found an available parking space when it has cruised to the target exploration point.

[0148] In one possible implementation, construction unit 701 is specifically used to: construct a local map corresponding to the vehicle's perception range based on perception information. In the absence of a first exploration point, the local map is determined as the global map.

[0149] In one possible implementation, construction unit 701 is specifically used to: merge the local map and the historical global map when a first exploration point exists, to obtain a merged map. Based on the target search range, the merged map is modified to obtain a global map, wherein the target search range is defined based on the vehicle's position.

[0150] In one possible implementation, construction unit 701 is specifically used to: determine the gain value of each tree node in the fused map; delete the first exploration point and tree nodes in the fused map whose gain value is less than a preset gain value and are outside the target search range, to obtain the global map.

[0151] In one possible implementation, the determining unit 702 is specifically used to: determine whether a first sensing boundary point exists. If the existence of the first sensing boundary point is determined, the target exploration point is determined from the first sensing boundary point.

[0152] In one possible implementation, the determining unit 702 is specifically used to: determine the perceptual boundary point with the highest exploration value among the first perceptual boundary points as the target exploration point.

[0153] In one possible implementation, the determining unit 702 is specifically used to: determine the target exploration point from the second sensing boundary point if it is determined that there is no first sensing boundary point.

[0154] In one possible implementation, the determining unit 702 is specifically used to: determine the connection path with the minimum path length between the vehicle position and each of the second sensing boundary points based on the branch and bound method. The sensing boundary point with the minimum connection path length among the second sensing boundary points is then determined as the target exploration point.

[0155] In one possible implementation, planning unit 703 is specifically used to: generate multiple planned routes from the vehicle's location to the target exploration point using a fast search random tree algorithm based on a first preset condition; and determine the planned route with the highest exploration value among the multiple planned routes as the target planned path.

[0156] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0157] Figure 8 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Figure 8 As shown, the electronic device includes, but is not limited to, a processor 801 and a memory 802.

[0158] The memory 802 described above is used to store the executable instructions of the processor 801. It is understood that the processor 801 is configured to execute instructions to implement the parking space search method in the above embodiment.

[0159] It should be noted that those skilled in the art will understand that Figure 8 The electronic device structure shown does not constitute a limitation on the electronic device; the electronic device may include, but is not limited to, other electronic devices. Figure 8 This may indicate more or fewer components, or combinations of certain components, or different component arrangements.

[0160] The processor 801 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 802, and by calling data stored in the memory 802, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. The processor 801 may include one or more processing units. Optionally, the processor 801 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 801.

[0161] The memory 802 can be used to store software programs and various data. The memory 802 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required by at least one functional module (such as a determination unit, processing unit, etc.), etc. Furthermore, the memory 802 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0162] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 802 including instructions, which can be executed by a processor 801 of an electronic device to implement the methods in the above embodiments.

[0163] In actual implementation, Figure 7 The functions of the construction unit 701, determination unit 702, planning unit 703, and control unit 704 can all be derived from... Figure 8 The processor 801 calls the computer program stored in the memory 802 to implement the process. The specific execution process can be found in the method section of the previous embodiment, and will not be repeated here.

[0164] Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device. In an exemplary embodiment, this application also provides a computer program product including one or more instructions, which can be executed by a processor 801 of an electronic device to perform the methods in the above embodiments.

[0165] It should be noted that when one or more instructions in the computer-readable storage medium or computer program product are executed by the processor of an electronic device, they implement the various processes of the above method embodiments and achieve the same technical effect as the above method. To avoid repetition, they will not be described again here.

[0166] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0167] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0168] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0169] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0170] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0171] This application provides a computer program product containing instructions that, when run on a computer, cause the computer to execute the parking space search method described in the above method embodiments.

[0172] This application also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the parking space search method in the method flow shown in the above method embodiments.

[0173] The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, registers, hard disks, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof, or any other form of computer-readable storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can reside in an application-specific integrated circuit (ASIC). In embodiments of this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0174] Since the parking space search device, computer-readable storage medium, and computer program product in the embodiments of this application can be applied to the above method, the technical effects they can achieve can also be referred to the above method embodiments. The embodiments of this application will not be repeated here.

[0175] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A parking space search method, characterized in that, The method includes: When the vehicle's location is not within the coverage area of ​​the high-precision map, a local map is constructed based on the perception information within the vehicle's perception range corresponding to the vehicle's location; wherein, the perception information includes perception boundary points that are not obscured by obstacles and obstacles. The local map and the historical global map are merged to construct a global map. The historical global map is obtained by incorporating target tree nodes into the global map established at the first exploration point. The target tree nodes are tree nodes sampled when planning the path from the first exploration point to the vehicle's location using a fast search random tree algorithm. The first exploration point is the exploration point closest to the vehicle's location that the vehicle passes through after parking planning. If no first perception boundary point exists within the target search range, a second perception boundary point is determined; wherein, the target search range is a local area in three-dimensional space centered on the current position of the vehicle; the first perception boundary point is a boundary point located within the target search range; and the second perception boundary point is a perception boundary point in the global map located outside the target search range. Based on the branch and bound method, the connection path with the minimum path length between the vehicle location and each of the second sensing boundary points is determined; the connection path connects the vehicle location and the corresponding second sensing boundary points through multiple tree nodes in the global map. The sensing boundary point with the shortest connecting path length among the second sensing boundary points is determined as the target exploration point; Based on a first preset condition, a fast search random tree algorithm is used to plan a target path from the vehicle's location to the target exploration point on the global map; wherein, the first preset condition is used to make the tree nodes sampled by the fast search random tree algorithm tend to fall into the neighborhood of the target exploration point; Control the vehicle to cruise along the planned target path in order to search for available parking spaces.

2. The parking space search method according to claim 1, characterized in that, The method further includes: If no available parking space is found when the vehicle cruises to the target exploration point, the above steps of constructing, determining, planning, and cruising are repeated based on the vehicle's position after the cruise until an available parking space is found.

3. The parking space search method according to claim 1, characterized in that, The process of fusing the local map and the historical global map to construct a global map includes: If the first exploration point does not exist, the historical global map will be determined as an empty map; The empty map is merged with the local map to obtain the global map.

4. The parking space search method according to claim 3, characterized in that, The process of fusing the local map and the historical global map to construct a global map includes: The local map and the historical global map are merged to obtain a merged map; Based on the target search range, the fused map is modified to obtain the global map, wherein the target search range is defined based on the vehicle location.

5. The parking space search method according to claim 4, characterized in that, The process of modifying the fused map based on the target search range to obtain the global map includes: Determine the gain value of each tree node in the fused map; Delete the first exploration point and the tree nodes in the fused map whose gain value is less than the preset gain value and are outside the target search range to obtain the global map; The gain value of each tree node is determined based on the distance between each tree node and other tree nodes in the fused map and / or the number of tree nodes contained in the neighborhood of each tree node.

6. The parking space search method according to any one of claims 1-5, characterized in that, The method further includes: If the existence of the first sensing boundary point is confirmed, the target exploration point is determined from the first sensing boundary point.

7. The parking space search method according to claim 6, characterized in that, Determining the target exploration point from the first sensing boundary point includes: The perception boundary point with the highest exploration value among the first perception boundary points is determined as the target exploration point; The exploration value of the first sensing boundary point is determined based on the distance between the vehicle position and the first sensing boundary point, and the angle between the first orientation of the vehicle and the second orientation of the vehicle position pointing to the first sensing boundary point.

8. The parking space search method according to claim 3 or 4, characterized in that, The step of planning a target path from the vehicle's location to the target exploration point on the global map based on a first preset condition and using a fast search random tree algorithm includes: Based on the first preset condition, a fast search random tree algorithm is used to generate multiple planned branch roads from the vehicle location to the target exploration point; The planning branch with the highest exploration value among the multiple planned branches is identified as the target planning path; The exploratory value of the planned branch roads is related to at least one of the following: The distance of the edge between two adjacent tree nodes in the planned branch road relative to the direction of the vehicle; The included angle between different sides of the planned branch road; The distance between the tree node in the planned branch road and the vehicle's location; The similarity between the planned branch road and the planned path from the first exploration point to the vehicle's location; The number of unknown voxels in the neighborhood of a tree node in the planned branch.

9. The parking space search method according to claim 8, characterized in that, The first preset conditions include: If the target value is less than or equal to a preset value threshold, a tree node is randomly generated in the neighborhood of the target exploration point. In addition, if the target value is greater than a preset value threshold, a tree node is randomly generated outside the neighborhood of the target exploration point; The target value is a value randomly generated within a preset value range.

10. A parking space search device, characterized in that, The device includes: a construction unit, a determination unit, a planning unit, and a control unit; The construction unit is used to construct a local map based on the perception information within the vehicle's perception range corresponding to the vehicle's location when the vehicle's location is not within the coverage area of ​​the high-precision map; wherein, the perception information includes perception boundary points that are not obscured by obstacles and obstacles. The construction unit is further configured to merge the local map and the historical global map to construct a global map; wherein the historical global map is obtained by incorporating target tree nodes into the global map established at the first exploration point, and the target tree nodes are tree nodes sampled when planning the path from the first exploration point to the vehicle location using a fast search random tree algorithm; the first exploration point is the exploration point closest to the vehicle location that the vehicle passes through after parking planning; The determining unit is configured to determine a second sensing boundary point when a first sensing boundary point does not exist within the target search range; wherein, the target search range is a local area in a three-dimensional space centered on the current position of the vehicle; the first sensing boundary point is a boundary point located within the target search range; and the second sensing boundary point is a sensing boundary point in the global map located outside the target search range. The determining unit is further configured to determine, based on the branch and bound method, the connection path with the minimum path length between the vehicle position and each of the second sensing boundary points; the connection path is a connection between the vehicle position and the corresponding second sensing boundary points through multiple tree nodes in the global map. The determining unit is further configured to determine the sensing boundary point with the smallest connecting path length among the second sensing boundary points as the target exploration point; The planning unit is used to plan a target planning path from the vehicle location to the target exploration point on the global map based on a first preset condition and using a fast search random tree algorithm; wherein, the first preset condition is used to make the tree nodes sampled by the fast search random tree algorithm tend to fall into the neighborhood of the target exploration point; The control unit is used to control the vehicle to cruise along the target planned path in order to search for available parking spaces.

11. A vehicle, characterized in that, Includes the parking space search device as described in claim 10.

Images