Automatic parking system and method based on parking lot plane map and electronic equipment

Abstract

The invention provides an automatic parking system based on a parking lot plane map, belongs to the field of intelligent driving, constructs a parking lot full-scene structure map based on the plane map by obtaining the plane map of a parking lot, plans a global path for parking based on the structure map, and can cruise in the whole parking lot. In the cruising process, the vehicle can build a local map around the vehicle, obstacle avoidance is carried out based on the local map, surrounding available parking spaces are searched, after the available parking spaces are searched, the vehicle is switched to a parking mode, and the vehicle is parked in a target parking space. The problem of automatic parking in an unmapped parking lot can be effectively solved under the condition of avoiding high-cost reconstruction of a field end, and the efficiency of automatic parking is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, and in particular to an automatic parking system, method and electronic device based on a parking lot plan map. Background Technology

[0002] Automated parking is becoming increasingly common, but the current methods mainly fall into the following categories: The first requires the driver to drive the vehicle to the target parking space before automatic parking, necessitating the driver's manual search for an available space. The second method involves memory parking, where a semantic or feature map of the parking lot is built before parking, and parking is then performed based on this map. This method is suitable for frequently used parking lots, but a new map needs to be built for new parking lots. The third method involves modifying the parking lot, collecting high-precision maps, and then distributing them to the vehicle for parking. This method requires modifications to the parking lot and the collection of high-precision maps, involving costs and regulatory risks, and is not applicable to all parking lots. The fourth method involves uploading maps of the same parking lot from different users, stitching and merging these maps in the cloud to create a crowdsourced map, and then distributing it to users who need it. However, this method also involves qualification and regulatory risks and is not suitable for large-scale mass production. Summary of the Invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art, and proposes an automatic parking system and method based on a parking lot plan map.

[0004] In a first aspect, the present invention provides an automatic parking system based on a parking lot plan map, comprising a vehicle-mounted module, a structure map construction module, a planning module, a control module, a local map construction module, and a perception module;

[0005] The vehicle-mounted module is used to acquire a two-dimensional plan view of the parking lot and transmit the acquired two-dimensional plan view to the structure map construction module;

[0006] The structure map construction module constructs a global mapping relationship based on the two-dimensional planar map;

[0007] The planning module plans a global cruise path based on the mapping relationship;

[0008] The control module cruises according to the planned global cruise path and controls the vehicle and avoids obstacles based on the local path.

[0009] The local map building module constructs a local map around the vehicle during the cruise process to perform local route planning.

[0010] The sensing module is used to sense the environmental information around the vehicle and to detect whether there are any vacant parking spaces around the vehicle.

[0011] In some embodiments, the vehicle-mounted module interacts with the parking lot system via a network to obtain a two-dimensional plan view of the parking lot, and transmits it to the structure map building module to construct a full-scene structure map;

[0012] If the full-scene structure map has only one entrance, then the global path is planned directly based on the entrance to enter the cruise berth;

[0013] When the full-scene structure map has multiple entrances, the driver confirms the entrance and then plans a global path to enter the cruise parking area based on the confirmed entrance.

[0014] In some embodiments, the structure map building module obtains a two-dimensional plan view provided by the vehicle system and then extracts parking information from the map. The parking information includes entrance, exit, lane, lane line, intersection and parking space.

[0015] The extracted lanes are categorized and lane index information is constructed;

[0016] The extracted lane line information is classified and lane line index information is constructed, and then mapped to the lane it belongs to;

[0017] The extracted intersections are classified and intersection index information is constructed, and a mapping relationship is established between them and the lanes and lane lines they are linked to.

[0018] The extracted storage locations are categorized and storage location index information is constructed. Furthermore, a mapping relationship is established between the associated lane lines, intersections, and lanes.

[0019] In some embodiments, classifying the extracted lanes and constructing lane index information includes:

[0020] The lanes are divided into segments based on the intersection, and attributes and index numbers are set according to their direction relative to the entrance.

[0021] Establish connections to link intersection index information, lane line index information, and parking space index information.

[0022] In some embodiments, the construction of the lane line index information includes extracting lane line information from a planar map, setting lane line attributes according to the type of lane line, and constructing a connection relationship to associate lane index information and intersection index information according to the lane to which the lane line belongs.

[0023] The construction of the intersection index information includes extracting intersection information from the planar map, setting the attributes of the intersection according to the type of lane lines, and constructing a connection relationship between the lanes and lane lines connected to the intersection to associate the lane index information and the intersection index information.

[0024] The construction of the storage location index information includes extracting storage location information from the planar map, determining the storage location type based on the vertical relationship between the storage location and the lane, constructing a connection relationship between the lane and lane line based on the lane to which the storage location belongs, and associating the lane index information and lane line index information.

[0025] In some embodiments, the sensing module detects whether there are vacant parking spaces around the vehicle and determines whether the parking conditions are met; if so, the parking space is pushed to the planning module as the target parking space to plan the parking route, and the control module controls the vehicle to park in the parking space according to the planned parking route.

[0026] In some embodiments, an odometer module is also included for calculating the current position and attitude of the vehicle and for performing local positioning.

[0027] In some embodiments, the local mapping module uses keyframe information about the vehicle's surroundings provided by the perception module and pose information calculated by the odometer to construct a local map of the vehicle's surroundings based on inter-frame matching. The local map includes information on parking spaces, lane lines, and intersections around the vehicle. The local map is matched with the structure map to locate the vehicle's position in the global map.

[0028] Secondly, the present invention also provides an automatic parking method based on a parking lot floor plan map for implementing the above system, comprising:

[0029] Obtain a two-dimensional floor plan of the parking lot;

[0030] Construct a global mapping relationship based on the two-dimensional planar diagram;

[0031] Plan the global cruise path based on the mapping relationship;

[0032] Cruise driving according to the planned global cruise route;

[0033] During the cruise, a local map is constructed based on the detection data;

[0034] The vehicle automatically parks itself by finding available parking spaces around it using a local map.

[0035] Thirdly, the present invention also provides an electronic device, comprising:

[0036] One or more processors;

[0037] Memory, used to store one or more programs;

[0038] When the one or more programs are executed by the one or more processors, the one or more processors implement the above method.

[0039] Fourthly, the present invention also provides a computer-readable medium on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps in the above-described method.

[0040] The automatic parking system based on a parking lot planar map provided by this invention constructs a full-scene structure map of the parking lot by acquiring a planar map of the parking lot. The global parking path planned based on the structure map can cruise within the entire parking lot. During the cruise, the vehicle constructs a local map of its surroundings. The local map can be matched with the global map to determine the vehicle's approximate position in the global map. Based on the local map, the driving path is planned and obstacle avoidance is performed, and the surrounding available parking spaces are searched. When an available parking space is found, the vehicle switches to parking mode and parks the vehicle in the target parking space. This system can effectively solve the problem of automatic parking in parking lots without high-cost on-site modifications, thus improving the efficiency of automatic parking.

[0041] Furthermore, this invention uses a full-scene structure map for cruise and coarse positioning, and relies on local maps to search for available parking spaces. As long as an available parking space is found, automatic parking can be performed. It does not rely heavily on the accuracy of global positioning, but mainly on the results of local perception. Moreover, there is no need to pre-set a target parking space or worry about the target parking space being occupied. This can effectively improve the success rate of automatic parking and provide a more human-like parking experience for customers. Attached Figure Description

[0042] Figure 1 This is a schematic diagram illustrating the steps of an embodiment of the automatic parking system based on a parking lot floor map according to the present invention;

[0043] Figure 2 This is a schematic diagram of an embodiment of the present invention that constructs a global structure diagram based on a parking lot plan map;

[0044] Figure 3 This is a schematic diagram of an embodiment of the present invention for planning a global route based on a global structure graph;

[0045] Figure 4 This is a schematic diagram of the steps of an embodiment of the automatic parking method based on a parking lot floor map of the present invention;

[0046] Figure 5 This is a schematic diagram of the structure of an embodiment of the electronic device of the present invention. Detailed Implementation

[0047] To enable those skilled in the art to better understand the technical solutions of the present invention, exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0048] Where there is no conflict, the various embodiments of the present invention and the features thereof may be combined with each other.

[0049] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0050] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0051] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0052] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example: appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely locating a specific individual.

[0053] The relevant technologies require parking lots to be upgraded and renovated, and corresponding tagging devices need to be installed. It is also necessary to collect and create corresponding tag topology maps and provide parking space management services based on the tag information. This is not applicable to most general parking lots.

[0054] To address at least one of the technical problems existing in the aforementioned related technologies, the present invention provides an automatic parking system based on a parking lot floor plan map. Figure 1 This invention provides a schematic diagram of an automated parking system based on a parking lot plan map, comprising: a vehicle-mounted system module, a structure map construction module, a planning module, a control module, a local map construction module, a sensing module, and an odometer module. The specific implementation methods of each module are described in detail below.

[0055] The vehicle-mounted module is used to acquire a two-dimensional plan view of the parking lot and transmit the acquired two-dimensional plan view to the structure map construction module.

[0056] Specifically, the vehicle-mounted module can interact with the parking lot system via the network to confirm whether the parking lot has a floor plan (plan diagram or floor design drawing). If it does, the module obtains the floor plan of the parking lot and passes it to the structure map construction module to build a full-scene structure map. When the map is completed, the driver is prompted to save the map. If the map has only one entrance, the driver directly plans a global path based on the entrance to enter the cruise parking area. If the map has multiple entrances, the driver confirms the entrance and then plans a global path based on the confirmed entrance to enter the cruise parking area.

[0057] Furthermore, the vehicle-mounted module supports map management, including map deletion, map merging, and map renaming.

[0058] The structure map building module constructs a global mapping relationship based on the two-dimensional planar map.

[0059] Specifically, after obtaining the planar map provided by the vehicle-mounted module, the structure map construction module can quickly extract parking information from the map, including information such as entrances, exits, lanes, lane lines, intersections, and parking spaces. The extracted lanes are categorized and lane index information is constructed. The extracted lane line information is categorized, lane line index information is constructed, and it is mapped to the lanes they belong to. The extracted intersections are categorized, intersection index information is constructed, and a mapping relationship is established between them and the lanes and lane lines they are linked to. The extracted parking spaces are categorized, parking space index information is constructed, and a mapping relationship is established between them and the associated lane lines, intersections, and lanes.

[0060] Furthermore, the lane index information construction includes extracting lane information from the planar map, dividing the lanes into segments according to intersections, setting attributes and index numbers according to their direction relative to the entrance, constructing connection relationships to associate the incoming intersection index and the outgoing intersection index, as well as the lane line index, and associating the parking space index according to the parking space information on both sides.

[0061] Furthermore, the construction of the lane line index information includes extracting lane line information from the planar map, setting lane line attributes according to the type of lane line, and constructing a connection relationship between the lane index and the intersection index according to the lane to which the lane line belongs. The lane line attributes include white solid line, white dashed line, yellow solid line, yellow dashed line, and yellow double solid line.

[0062] Furthermore, the construction of the intersection index information includes extracting intersection information from the planar map, setting the attributes of the intersection according to the type of lane lines, and constructing a connection relationship between the lanes and lane lines connected by the intersection to associate the lane index and the intersection index. The types of lane lines include crossroads, T-junctions, and Y-junctions.

[0063] Furthermore, the construction of the storage location index information includes extracting storage location information from the planar map, determining the storage location type based on the vertical relationship between the storage location and the lane, constructing a connection relationship between the lane and lane line based on the lane to which the storage location belongs, and associating the lane index and lane line index. The storage location type includes vertical storage location, parallel storage location, and diagonal storage location.

[0064] The planning module plans the global cruise path based on the mapping relationship.

[0065] It is understood that the planning module plans a global path based on the full-scene structure map constructed by the structure map construction module. Since the target parking space is unknown, the planned route can cover as many parking spaces as possible. It also plans local routes based on the local map constructed by the local mapping module for vehicle cruising and obstacle avoidance.

[0066] The control module cruises according to the planned global cruise path.

[0067] Specifically, the control module controls the vehicle to cruise according to the planned global route; and to drive according to the local route and perform obstacle avoidance.

[0068] During the cruise, the local map construction module constructs a local map based on the keyframe information detected by the perception module and the pose information calculated by the odometer.

[0069] Specifically, the perception module includes a forward-looking camera, a surround-view camera, and an ultrasonic radar. The forward-looking camera can perceive road information in front of the vehicle, including road structure, lane lines, intersections, and other information. The surround-view camera can collect environmental information around the vehicle and perform distortion correction, coordinate transformation, and image stitching to form a surround-view mosaic map of the vehicle's surroundings. This mosaic map is then input into a deep learning model to extract road marking information, which is used to construct a local map of the vehicle's surroundings. The road marking information includes parking spaces, arrows, and speed bumps. The ultrasonic radar can perceive obstacle information around the vehicle for obstacle avoidance and bypass during vehicle cruising.

[0070] Furthermore, the odometer module integrates the wheel speed or wheel pulse signals provided by the wheels and the acceleration and angular velocity information provided by the IMU to calculate the current position and attitude for local positioning.

[0071] It is understood that the local mapping module utilizes keyframe information about the vehicle's surroundings (such as road information and road markings) provided by the perception module and pose information calculated by the odometer to construct a local map of the vehicle's surroundings based on inter-frame matching. The local map includes information such as parking spaces, lane lines, and intersections around the vehicle. The local map can be matched with the global map to determine the vehicle's approximate position within the global structural map.

[0072] The sensing module is also used to detect whether there are any vacant parking spaces around the vehicle and the distance between the vacant parking spaces and the vehicle. When a parking space that meets the parking conditions is detected, the parking process is executed to park the vehicle in the parking space.

[0073] It is understood that the above embodiment proposes an automatic parking system based on a parking lot floor plan map. It only requires obtaining a standard floor plan map of the parking lot via the network. On the vehicle side, it extracts road, intersection, parking space, and landmark information from the floor plan map to construct a full-scene structural map of the parking lot. Then, it plans a global path based on this structural map and cruises along the planned path. During cruise driving, a local map is built in real time to search for available parking spaces and perform obstacle avoidance and maneuvering. When a available parking space is found, it switches from cruise mode to parking mode to park the vehicle in the parking space. This helps avoid high-cost site modifications and high-precision map acquisition costs, and it also addresses the issue of vehicles being unable to use the memory parking function when entering new parking lots.

[0074] The technical solution of the present invention will be described in detail below with reference to specific embodiments. This embodiment provides an automatic parking system based on a parking lot plan map, which is executed according to the following specific method:

[0075] S1: When a vehicle enters the parking lot entrance, the vehicle system interacts with the parking lot system through the Tbox and obtains a 2D map of the parking lot via the network;

[0076] S2: The vehicle system transmits the acquired 2D planar map to the structure map building module. The structure map building module extracts information such as lanes, intersections, lane lines, and parking spaces from the planar map and builds a global structure map.

[0077] The structure map construction method specifically includes:

[0078] 1. Extract map elements:

[0079] like Figure 2 As shown, lanes, intersections, lane lines, and parking spaces are extracted from a two-dimensional planar map. Based on the set principles (e.g., adding IDs from left to right and from bottom to top), the extracted objects are assigned ID values, and the corresponding type is set according to the type of the extracted objects.

[0080] 2. Construct lane connection relationships: Based on the connection relationships in the 2D map, associate the lane entry intersection ID with the destination intersection ID, and the left lane line ID with the right lane line ID. For example... Figure 2 In the code, the link association information for road_id 1 is: from_junction_id: 1, to_junction_id: 6, left_lane_id: 2, right_lane_id: 1, left_ps_number: 7, right_ps_number: 7

[0081] Lane information includes:

[0082] describe type Signal Range of values Road ID uint64_t road_id Road type uint8_t road_type Unknown = 0, One-way street = 1, Two-way street = 2 Entry ID uint8_t from_junction_id Destination intersection ID uint8_t to_junction_id Left lane line ID uint8_t left_lane_id Right lane line ID uint8_t right_lane_id Number of associated storage locations on the left uint8_t left_ps_number Number of associated storage locations on the right uint8_t right_ps_number

[0083] 3. Establish intersection connections:

[0084] Based on the connectivity in the two-dimensional map, associate road information and entrance / exit information related to the intersection. For example... Figure 2 In the diagram, the intersection structure with junction_id 7 is as follows: from_road_ids is (3,18), there is no to_right_road_ids_1 (3,17), to_left_road_ids_2 (18,4), link_with_entrance is 0, link_with_exit is 1, and link_ps_number is 0.

[0085] Intersection information includes:

[0086] describe type Signal Range of values intersection ID uint64_t junction_id Intersection Types uint8_t junction_type Unknown = 0, Crossroads = 1, T-junctions = 2, L-shaped intersections = 3, Y-shaped intersections = 4, Intersections with multiple branches = 5, Roundabouts = 6 Entrance lane ID std::vector<road_id> from_road_ids The exit straight lane ID corresponding to entrance lane 1 std::map<road_id,road_id> to_straight_road_ids_1 The exit left-turn lane ID corresponding to entrance lane 1 std::map<road_id,road_id> to_left_road_ids_1 The exit right-turn lane ID corresponding to entrance lane 1 std::map<road_id,road_id> to_right_road_ids_1 The exit straight lane ID corresponding to entrance lane 2 std::map<road_id,road_id> to_straight_road_ids_2 The exit left-turn lane ID corresponding to entrance lane 2 std::map<road_id,road_id> to_left_road_ids_2 The exit right-turn lane ID corresponding to entrance lane 2 std::map<road_id,road_id> to_right_road_ids_2 The exit straight lane ID corresponding to entrance lane 3 std::map<road_id,road_id> to_straight_road_ids_3 The exit left-turn lane ID corresponding to entrance lane 3 std::map<road_id,road_id> to_left_road_ids_3 The exit right-turn lane ID corresponding to entrance lane 3 std::map<road_id,road_id> to_right_road_ids_3 The exit straight lane ID corresponding to entrance lane 4 std::map<road_id,road_id> to_straight_road_ids_4 The exit left-turn lane ID corresponding to entrance lane 4 std::map<road_id,road_id> to_left_road_ids_4 The exit right-turn lane ID corresponding to entrance lane 4 std::map<road_id,road_id> to_right_road_ids_4 Is the entry point connected? bool link_with_entrance No connection = 0 Connection = 1 Is it connected to the outlet? bool link_with_exit No connection = 0 Connection = 1 Number of associated parking spaces uint_8 link_ps_number

[0087] 4. Establish lane line connection relationships:

[0088] Based on the connectivity in the 2D map, lane lines are segmented according to the extracted lane structure, and the structural relationship between lane lines and the road is constructed. For example... Figure 2 The lane with lane_id 2 has the following structure: in_road_ids(1,2), near_parking_slots is 0, and link_ps_number is 0.

[0089] describe type Signal Range of values Lane ID uint64_t lane_id Lane line type uint8_t lane_type unknown = 0, solid white line = 1, dashed white line = 2, solid yellow line = 3, dashed yellow line = 4, double solid yellow line = 5 Lane ID std::vector<uint8_t> in_road_ids Is it close to the storage location? bool near_parking_slots Number of associated parking spaces uint_8 link_ps_number

[0090] 5. Establish storage location connections:

[0091] Based on the connectivity in the two-dimensional map, the structural relationships between storage locations, intersections, and lanes are constructed using extracted information on storage locations, lanes, and intersections. For example... Figure 2 The library location with ps_id of 5 has the following structure: link_road_ids is (1,2), link_lane_id is 3, and link_with_junction is 0.

[0092] describe type Signal Range of values Storage location ID uint64_t lane_id Storage location type uint8_t lane_type Unknown = 0, Solid white line = 1, Dashed white line = 2, Solid yellow line = 3, Dashed yellow line = 4, Double solid yellow line = 5 Parking direction connection lane ID std::vector<uint8_t> link_road_ids Parking direction connecting lane line ID uint8_t link_lane_id Does it connect to the intersection? bool link with junction No connection = 0; Connection = 1 Connecting intersection ID uint8_t link_junction_id

[0093] S3: Based on the constructed map, if there are multiple entrances, the driver selects the entrance where the current vehicle is located; if there is only one entrance, the global path is planned directly based on the entrance.

[0094] S4: Based on the established connection relationships, the planning module plans a route that passes through the most storage locations and has the fewest overlapping intersections. This can be calculated based on the number of storage locations associated with the intersections and lanes along the planned route. The module then extracts the intersections and their IDs, as well as the lanes and their IDs, and performs serialization processing according to the route.

[0095] For example Figure 3 The route map, the information after serialization and processing is as follows: <junction_id=1,road_id = 1,junction_id = 6,road_id = 3,junction_id = 7,road_id = 17,junction_id=8,road_id=8,junction_id = 5,road_id=6,junction_id = 2,road_id=19,junction_id=3,road_id = 9,junction_id = 4,road_id=11> .

[0096] Specifically: the traffic direction within junction_id=1 is left turn; the traffic direction within junction_id=6 is straight; the traffic direction within junction_id=7 is right turn; the traffic direction within junction_id=8 is right turn; the traffic direction within junction_id=2 is left turn; the traffic direction within junction_id=3 is left turn; and the traffic direction within junction_id=4 is straight.

[0097] S5: According to the planned route map, the vehicle moves forward. The perception module detects the environmental information around the vehicle. The local mapping module constructs a local map around the vehicle based on the pose calculated by the odometer and the information detected by the perception. When the first intersection information appears in the local map, it is matched with the intersection type in the planned route and the surrounding parking spaces, lane lines and other structures to confirm that the current vehicle is located at the intersection with junction_id 1. Based on the structural information, it is confirmed whether the intersection is associated with a parking space. If not, the vehicle needs to turn left into the lane with road_id 1. The planning module plans the local driving route.

[0098] S6: The control module controls the vehicle to turn left onto the lane with road_id 1 according to the planned local route, and controls the vehicle to continue driving in the current lane according to the lane lines on both sides of the lane to build a local map. At the same time, it detects the parking spaces on both sides of the lane around the vehicle, records the number of parking spaces, and detects whether there are any empty parking spaces.

[0099] S7: If there is an available parking space in the current lane, determine whether the parking space meets the parking conditions of the vehicle. If the parking conditions are met, plan the parking route based on the relative position of the parking space and the vehicle.

[0100] S8: If there are no available parking spaces in the current local map, the vehicle continues to move forward and compares the number of parking spaces recorded on both sides with the number of parking spaces associated with the current lane. If the recorded number of parking spaces is less than the number of associated parking spaces, the vehicle remains in the lane with road_id 1 and continues to move forward until the next intersection is detected. At this point, the number of parking spaces recorded in the current lane is compared with the number of parking spaces associated with the current lane. If the numbers are the same, it indicates that this lane has been traversed, and the vehicle needs to enter the next intersection with junction_id 6.

[0101] S9: Based on the information in the structure map, confirm that the intersection with junction_id 6 is associated with 2 parking spaces. When a vehicle enters the intersection, the surrounding parking space information is detected, and the number of parking spaces at the current intersection is recorded again. If there is an empty parking space between the two parking spaces, it is determined whether the conditions for parking the vehicle are met. If they are met, a parking route is planned.

[0102] S10: If neither of the two storage locations is available, then according to the globally planned path, if a straight path is required at the intersection with junction_id 6, the local map module will construct a local map near the intersection and plan a local route for the straight path.

[0103] S10: The control module guides the vehicle to proceed straight through the current intersection according to the planned local route, and enters the next lane with road_id 3. It then restarts recording the number of parking spaces detected during the current lane's travel and checks for available parking spaces.

[0104] S11: Following the planned global path, proceed through sequential intersections and lanes until an available parking space is found.

[0105] This invention provides an automated parking system based on a parking lot planar map. Addressing practical parking problems, it proposes an automated parking solution based on a parking lot planar map. By acquiring the parking lot planar map, a full-scene structure map of the parking lot is constructed. The global parking path planned based on this structure map can cruise throughout the entire parking lot. During this cruise, the vehicle constructs a local map of its surroundings. This local map is matched with the global structure map to determine the vehicle's position on the global map. The system also performs obstacle avoidance based on the local map and searches for available parking spaces. Once a parking space is found, the vehicle switches to parking mode and parks itself in the target space. This effectively solves the problem of automated parking in parking lots without requiring high-cost modifications at the parking lot level, thus improving the efficiency of automated parking.

[0106] Furthermore, this invention uses a full-scene structure map for cruise and coarse positioning, and relies on local maps to search for available parking spaces. As long as an available parking space is found, automatic parking can be performed. It does not rely heavily on the accuracy of global positioning, but mainly on the results of local perception. Moreover, there is no need to pre-set a target parking space or worry about the target parking space being occupied. This can effectively improve the success rate of automatic parking and provide a more human-like parking experience for customers.

[0107] Please see Figure 4 The present invention also provides an automated parking method based on a parking lot floor plan map. Applied to the automated parking system based on a parking lot floor plan map provided in the above embodiments, it specifically includes:

[0108] Obtain a two-dimensional plan of the parking lot.

[0109] Specifically, the system can interact with the parking lot's system via the network to confirm whether a floor plan (plan diagram or floor design drawing) exists for the parking lot. If it exists, the system obtains the floor plan of the parking lot and passes it to the structure map construction module to build a full-scene structure map. Once the map is built, the system prompts the driver to save the map. If the map has only one entrance, the system directly plans a global path based on the entrance to enter the cruise parking area. If the map has multiple entrances, the driver confirms the entrance and then plans a global path based on the confirmed entrance to enter the cruise parking area.

[0110] A global mapping relationship is constructed based on the two-dimensional planar diagram.

[0111] Specifically, after obtaining the planar map provided by the vehicle's infotainment module, the system can quickly extract parking information from the map, including entrances, exits, lanes, lane lines, intersections, and parking spaces. The extracted lanes are categorized, and lane index information is constructed. The extracted lane line information is categorized, lane line index information is constructed, and mapping is established between the extracted lanes and their corresponding lanes. The extracted intersections are categorized, intersection index information is constructed, and mapping relationships are established between the intersections and their associated lanes and lane lines. The extracted parking spaces are categorized, parking space index information is constructed, and mapping relationships are established between the parking spaces and their associated lane lines, intersections, and lanes.

[0112] Furthermore, the lane index information construction includes extracting lane information from the planar map, dividing the lanes into segments according to intersections, setting attributes and index numbers according to their direction relative to the entrance, constructing connection relationships to associate the incoming intersection index and the outgoing intersection index, as well as the lane line index, and associating the parking space index according to the parking space information on both sides.

[0113] Furthermore, the construction of the lane line index information includes extracting lane line information from the planar map, setting lane line attributes according to the type of lane line, and constructing a connection relationship between the lane index and the intersection index according to the lane to which the lane line belongs. The lane line attributes include white solid line, white dashed line, yellow solid line, yellow dashed line, and yellow double solid line.

[0114] Furthermore, the construction of the intersection index information includes extracting intersection information from the planar map, setting the attributes of the intersection according to the type of lane lines, and constructing a connection relationship between the lanes and lane lines connected by the intersection to associate the lane index and the intersection index. The types of lane lines include crossroads, T-junctions, and Y-junctions.

[0115] Furthermore, the construction of the storage location index information includes extracting storage location information from the planar map, determining the storage location type based on the vertical relationship between the storage location and the lane, constructing a connection relationship between the lane and lane line based on the lane to which the storage location belongs, and associating the lane index and lane line index. The storage location type includes vertical storage location, parallel storage location, and diagonal storage location.

[0116] Plan the global cruise path based on the mapping relationship.

[0117] Understandably, a global path can be planned based on the constructed full-scene structure map, since the target parking space is unknown, and the planned route can cover as many parking spaces as possible. Local routes can also be planned based on the constructed local map for vehicle cruising.

[0118] Cruise according to the planned global cruise route.

[0119] During the cruise, a local map is constructed based on the keyframe information and pose information detected. The vehicle's position in the global structure map and the surrounding environment information are determined based on the information in the local map in order to perform local path planning and obstacle avoidance.

[0120] Specifically, a forward-facing camera can perceive road information ahead of the vehicle, including road structure, lane lines, intersections, etc.; a surround-view camera can collect environmental information around the vehicle and perform distortion correction, coordinate transformation, and image stitching to form a surround-view mosaic map of the vehicle's surroundings. This mosaic map is then input into a deep learning model to extract road marking information, which is used to construct a local map around the vehicle. The road marking information includes parking spaces, arrows, and speed bumps; and ultrasonic radar can perceive obstacle information around the vehicle for obstacle avoidance and maneuvering during vehicle cruise.

[0121] Furthermore, by integrating the wheel speed or wheel pulse signals provided by the wheels and the acceleration and angular velocity information provided by the IMU, the current position and attitude are calculated for local positioning.

[0122] It is understandable that a local map of the vehicle's surroundings is constructed based on keyframe information (such as road information and road markings) and pose information calculated from the odometer, using inter-frame matching. The local map includes information such as parking spaces, lane lines, and intersections around the vehicle.

[0123] The system searches for available parking spaces around the vehicle and their distance from the vehicle. Once a parking space that meets the parking requirements is detected, the system executes the parking procedure to park the vehicle in the space.

[0124] This invention provides an automated parking method based on a parking lot planar map. Addressing practical parking problems, it proposes an automated parking solution based on a parking lot planar map. By acquiring the parking lot planar map, a full-scene structure map of the parking lot is constructed. The global parking path planned based on this structure map can cruise throughout the entire parking lot. During this cruise, the vehicle constructs a local map of its surroundings, performs obstacle avoidance based on the local map, and searches for available parking spaces. Once a suitable parking space is found, the vehicle switches to parking mode and parks itself in the target space. This effectively solves the problem of automated parking in parking lots without requiring high-cost modifications at the parking lot level, thus improving the efficiency of automated parking.

[0125] Based on the same inventive concept, embodiments of the present invention also provide an electronic device. Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Figure 5 As shown, an embodiment of the present invention provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, which, when executed by the one or more processors, enable the one or more processors to implement any of the automatic parking methods based on parking lot floor maps described in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory, configured to enable information interaction between the processor and the memory.

[0126] The processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read / write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus).

[0127] In some embodiments, the processor 101, memory 102, and I / O interface 103 are interconnected via bus 104, and thus connected to other components of the computing device.

[0128] In some embodiments, the one or more processors 101 include a field-programmable gate array.

[0129] This invention also provides a computer-readable medium. The computer-readable medium stores a computer program, which, when executed by a processor, implements the steps of any of the automated parking methods based on parking lot floor maps described above. The computer-readable storage medium can be volatile or non-volatile.

[0130] This invention also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code is run in the processor of an electronic device, the processor in the electronic device executes the above-described automatic parking method based on a parking lot floor map.

[0131] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0132] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0133] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0134] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0135] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0136] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0137] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0138] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0139] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0140] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of the invention as set forth in the appended claims.

Claims

1. An automated parking system based on a parking lot floor plan, characterized in that, It includes: The vehicle-mounted system module, structural map building module, planning module, control module, local map building module, and perception module; The vehicle-mounted module is used to acquire a two-dimensional plan view of the parking lot and transmit the acquired two-dimensional plan view to the structure map construction module; The structure map construction module constructs a global mapping relationship based on the two-dimensional planar map; The planning module plans a global cruise path based on the mapping relationship; The control module cruises according to the planned global cruise path and controls the vehicle and avoids obstacles based on the local path. The local map building module constructs a local map around the vehicle during the cruise process to perform local route planning. The sensing module is used to sense the environmental information around the vehicle and to detect whether there are any vacant parking spaces around the vehicle.

2. The automatic parking system based on a parking lot floor plan according to claim 1, characterized in that, The vehicle-mounted module interacts with the parking lot system via the network to obtain a two-dimensional plan view of the parking lot, and then transmits it to the structure map building module to construct a full-scene structure map; If the full-scene structure map has only one entrance, then the global path is planned directly based on the entrance to enter the cruise berth; When the full-scene structure map has multiple entrances, the driver confirms the entrance and then plans a global path to enter the cruise parking area based on the confirmed entrance.

3. The automatic parking system based on a parking lot floor plan according to claim 1, characterized in that, The structure map building module obtains the two-dimensional plan view provided by the vehicle system and then extracts the parking information from the map. The parking information includes entrance, exit, lane, lane line, intersection and parking space. The extracted lanes are categorized and lane index information is constructed; The extracted lane line information is classified and lane line index information is constructed, and then mapped to the lane it belongs to; The extracted intersections are classified and intersection index information is constructed, and a mapping relationship is established between them and the lanes and lane lines they are linked to. The extracted storage locations are categorized and storage location index information is constructed. Furthermore, a mapping relationship is established between the associated lane lines, intersections, and lanes.

4. The automatic parking system based on a parking lot floor plan according to claim 3, characterized in that, The process of classifying the extracted lanes and constructing lane index information includes: The lanes are divided into segments based on the intersection, and attributes and index numbers are set according to their direction relative to the entrance. Establish connections to link intersection index information, lane line index information, and parking space index information.

5. The automatic parking system based on a parking lot floor plan according to claim 3, characterized in that, The construction of the lane line index information includes extracting lane line information from the planar map, setting lane line attributes according to the type of lane line, and constructing connection relationships to associate lane index information and intersection index information according to the lane to which the lane line belongs. The construction of the intersection index information includes extracting intersection information from the planar map, setting the attributes of the intersection according to the type of lane lines, and constructing a connection relationship between the lanes and lane lines connected to the intersection to associate the lane index information and the intersection index information. The construction of the storage location index information includes extracting storage location information from the planar map, determining the storage location type based on the vertical relationship between the storage location and the lane, constructing a connection relationship between the lane and lane line based on the lane to which the storage location belongs, and associating the lane index information and lane line index information.

6. The automatic parking system based on a parking lot floor plan according to claim 1, characterized in that, The sensing module detects whether there are any vacant parking spaces around the vehicle and determines whether the parking conditions are met. If the conditions are met, the parking space is pushed to the planning module as the target parking space to plan the parking route. The control module then controls the vehicle to park in the parking space according to the planned parking route.

7. The automatic parking system based on a parking lot floor plan according to claim 1, characterized in that, It also includes an odometer module, used to calculate the vehicle's current position and attitude, and to perform local positioning.

8. The automatic parking system based on a parking lot floor plan according to claim 1, characterized in that, The local mapping module uses the keyframe information around the vehicle provided by the perception module and the pose information calculated by the odometer to construct a local map around the vehicle based on inter-frame matching. The local map includes information on parking spaces, lane lines and intersections around the vehicle. The local map is matched with the structure map to locate the vehicle's position in the global map.

9. An automatic parking method based on a parking lot floor plan, characterized in that, For implementing the system according to any one of claims 1-8, comprising: Obtain a two-dimensional floor plan of the parking lot; Construct a global mapping relationship based on the two-dimensional planar diagram; Plan the global cruise path based on the mapping relationship; Cruise driving according to the planned global cruise route; During the cruise, a local map is constructed based on the detection data; The vehicle automatically parks itself by finding available parking spaces around it using a local map.

10. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in claim 9.

Images