Map data processing and vehicle control method, equipment and medium
By collecting environmental information in segments during parking lots and updating the map, the problem of time-consuming map construction in the prior art is solved, and the convenience and accuracy of the autonomous driving function are improved.
Patent Information
- Application Number
- CN202310575626.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-19
- Publication Date
- 2024-11-26
AI Technical Summary
In the prior art, the realization of the automatic driving function of vehicles in the parking lot depends on high-precision maps, but due to the large amount of parking lot data collection and the data cannot be shared in some areas, it makes it difficult to update data. It takes time for users to manually drive to build the map, especially Time costs are high in parking lots that are not frequently visited.
Through the vehicle collecting environmental information in segments during the parking and out process, updating the parking lot map data, using the environmental information collected before and after the parking space, building a local path map to reduce the user's manual driving to build a map time.
It effectively reduces the user time cost of parking lot map construction, improves the convenience and accuracy of autonomous driving functions, especially in parking lots that are not frequently visited, which significantly reduces the time for building maps.
Smart Images

Figure CN119018159A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of vehicle technology, and in particular to a map data processing and vehicle control method, device, and medium. Background Art
[0002] With the development of vehicle technology, especially the development of automatic parking function, it can control the vehicle to automatically park from the parking space near the vacant parking space next to it, or automatically park out from the parking space. This function can help users park the vehicle in a narrow parking space more conveniently, or automatically park the vehicle out of a narrow parking space, reducing the difficulty of users getting on and off the vehicle in a narrow parking space.
[0003] In the related art, the user is still required to drive the vehicle to the vicinity of an empty parking space. After ensuring that the vehicle is parked in the parking space, the user needs to walk out of the parking space to the parking lot exit. When the user is ready to leave the parking lot, he needs to walk to the vicinity of the parking space, get in the car and drive the car out of the parking lot. These processes often require the user to walk in the parking lot for a long time.
[0004] In addition, most indoor parking lots lack positioning satellite signal coverage, resulting in inaccurate vehicle navigation. The related technology proposes the concept of using high-precision maps to guide vehicles to drive automatically in parking lots. By pre-storing high-precision maps of parking lots in vehicles, when the vehicle drives to an area covered by the map, it can match the environmental features acquired in real time with the environmental features recorded in the high-precision map, thereby determining the vehicle's own location information and then performing autonomous driving navigation. The map data needs to be updated accurately and in a timely manner to ensure the accuracy of autonomous driving navigation. However, due to the large number of parking lots and the large amount of data collected, the data of many parking lots cannot be effectively collected and maintained; in addition, some parking lots are located in private areas and are subject to data privacy supervision and cannot share map data, which increases the difficulty for vehicles to use high-precision maps of parking lots for autonomous driving.
[0005] In the related technology, users are usually required to drive their vehicles through all the paths in the parking lot completely and continuously. The paths here may include paths that users often use for parking, and may also include paths that are not often driven, but the driving trajectory is required to be continuous and uninterrupted. Based on the complete manual driving route, a high-precision map for autonomous driving in the parking lot is built. This way of building a map consumes a lot of user time. It takes half an hour to build a map once. For shopping malls and park parking lots that are not frequently visited, this time cost is not proportional to the number of times used, and the practicality is low. Summary of the invention
[0006] In view of the above problems, a map data processing and vehicle control method, device, and medium are proposed to overcome the above problems or at least partially solve the above problems, including:
[0007] A map data processing method, the method comprising:
[0008] Acquire stored parking lot map data of the vehicle, the parking lot map data being generated based on first environmental information collected while the vehicle is traveling along a first path, the first path comprising a path of the vehicle traveling from a first position to a target parking space;
[0009] After the vehicle is parked in the target parking space and restarted, obtaining second environmental information collected by the vehicle, the second environmental information being collected during the process of the vehicle traveling along a second path, the second path including a path of the vehicle traveling from the target parking space to a second location;
[0010] The parking lot map data is updated based on the second environmental information, and the parking lot map data is used to guide the vehicle to automatically travel on the first path and / or the second path.
[0011] A vehicle control method, the method comprising:
[0012] Acquire parking lot map data, wherein the parking lot map data is generated from environmental information collected by sensors of the vehicle during the historical driving process of the vehicle; wherein the historical driving process includes the driving process of the vehicle from a first position to a target parking space, and the driving process of the vehicle from the target parking space to a second position after the vehicle is parked at the target parking space and restarted;
[0013] The vehicle is controlled to automatically travel on the first path and / or the second path according to the parking lot map data.
[0014] A device comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the above method when executed by the processor.
[0015] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented. The embodiments of the present disclosure have the following advantages:
[0016] In the embodiment of the present disclosure, parking lot map data generated by acquiring first environmental information collected before the vehicle parks in a parking space, and acquiring second environmental information collected during the driving process after the vehicle drives out of the target parking space after the vehicle is parked in the target parking space and restarted, and updating the parking lot map data based on the second environmental information, in this way, environmental information collected in segments during the driving process on multiple local paths of the parking lot can be used to accumulate and construct a map, thereby reducing the user's time cost for constructing parking lot map data. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the technical solution of the present disclosure, the drawings required for use in the description of the present disclosure will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0018] Figure 1 is a flowchart of a method for processing map data provided by an embodiment of the present disclosure;
[0019] Figure 2 is a schematic diagram of a map display interface provided by an embodiment of the present disclosure;
[0020] Figure 3 It is a step flow chart of a vehicle control method provided by an embodiment of the present disclosure. DETAILED DESCRIPTION
[0021] In order to make the above-mentioned purposes, features and advantages of the present disclosure more obvious and easy to understand, the present disclosure is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.
[0022] The realization of automatic parking function usually relies on high-precision maps. High-precision maps can be constructed by the vehicle itself or provided by a third party, such as provided by suppliers or uploaded by other vehicles. However, maps provided by third parties may not cover some parking lots. In addition, since users usually use the automatic parking function in relatively fixed places, such as parking lots in residential areas and company parking lots, the method of constructing maps by the vehicle itself is more applicable.
[0023] In the way that the vehicle builds its own map, the user is usually required to manually drive from the parking lot entrance to the parking lot exit. Sometimes, the user is even required to completely drive through the seldom-visited areas of the parking lot. Only based on the complete manual driving route can a high-precision map for automatic parking be built. This way of building maps consumes a lot of user time. For example, it usually takes half an hour in a shopping mall. For parking lots that are not frequently visited, this time cost is not proportional to the number of times it is used, and its practicality is low.
[0024] Reference Figure 1 , shows a flowchart of a map data processing method provided by an embodiment of the present disclosure, which may specifically include the following steps:
[0025] S10, acquiring parking lot map data stored in the vehicle, wherein the parking lot map data is generated based on first environmental information collected during the vehicle's travel along a first path, wherein the first path includes a path of the vehicle from a first position to a target parking space.
[0026] Optionally, the parking lot map data may include feature information of scenery around the path, for example, architectural elements: columns, walls, door openings, pipes, etc.; traffic sign elements: lane lines, parking space lines, traffic signs, guide signs, etc.
[0027] Optionally, the first location may be the entrance to the parking lot. For example, the vehicle identifies information such as the parking lot gate, the down ramp, and the parking lot sign based on the collected environmental information, and determines the entrance to the parking lot. The first environmental information may be environmental information recorded starting from the time the vehicle identifies the parking lot entrance.
[0028] Optionally, the parking lot map data may include position information of the path in space, and position information of parking spaces around the path in space.
[0029] In an optional implementation, the first environmental information collected while the vehicle is traveling along the first path is obtained, and when the vehicle is parked in the target parking space, the computing unit of the vehicle does not need to perform motion control of the vehicle, and may not need to process human-computer interaction control, and is in a relatively idle state. At this time, the computing unit carried by the vehicle can be used to process the first environmental information and generate the parking lot map data.
[0030] For vehicles with autonomous driving capabilities, such as passenger cars equipped with autonomous driving systems or assisted driving systems, and unmanned logistics vehicles, the use of the automatic parking function requires reliance on high-precision maps. When it is detected that the vehicle has arrived at a parking lot, such as the vehicle is currently at the toll booth at the entrance of the parking lot, it can first be determined whether the vehicle has a map stored for the parking lot.
[0031] If a map for the parking lot is stored, the user can be prompted to use the automatic parking function, such as by a pop-up window in the human-machine interface (HMI) provided by the vehicle's display screen, or by a voice broadcast in the vehicle. The automatic parking function can be started in response to user instructions. After the automatic parking function is started, automatic parking can be performed directly according to the pre-stored map.
[0032] If no map for the parking lot is stored, the automatic parking function cannot be used and the user needs to drive manually in the parking lot. Relevant information can be recorded during the manual driving process, which may include driving trajectory information and environmental elements recorded along the driving trajectory, such as feature points, pillars, ground lane lines, traffic signs, arrows, etc., and then a map can be constructed based on the recorded relevant information.
[0033] For users, their normal driving process is to drive the vehicle from the parking lot entrance to the parking space and leave the vehicle after parking, return to the parking space after a period of time, such as returning to the parking space after get off work or after shopping in a mall, and then restart the vehicle and drive the vehicle from the parking space to the parking lot exit. Based on this, in order to avoid the need for users to manually drive from the parking lot entrance to the parking lot exit to build a complete map, the map can be built segment by segment along the user's normal driving process.
[0034] Specifically, after the vehicle enters the parking lot entrance (i.e., the first position), the vehicle needs to be driven manually by the user because the automatic parking function cannot be used. During the manual driving process, the vehicle system can record relevant information and automatically detect the surrounding available parking spaces to remind the user in real time.
[0035] After the user confirms in the vehicle system or the APP on the mobile terminal, the vehicle can automatically park in an available parking space (i.e. the target parking space). Of course, the user can also park in an available parking space manually. After parking in the parking space, the user can leave the vehicle after turning off the engine.
[0036] Since the first path from the parking lot entrance to the target parking space (i.e., the parked parking space) is recorded during the manual driving process, the trajectory information of the first path and the environmental elements recorded along the first path (i.e., the first environmental information) can be recorded. Then, the parking lot map data for the first path can be constructed based on the recorded relevant information. Specifically, the map can be constructed silently in the background after the user turns off the engine and leaves the car.
[0037] S20, after the vehicle is parked in the target parking space and restarted, obtaining second environmental information collected by the vehicle, the second environmental information is collected during the process of the vehicle traveling along a second path, and the second path includes the path of the vehicle traveling from the target parking space to a second position.
[0038] It is worth noting that when a vehicle is parked in a parking space, the power consumption of various systems is often reduced. At this time, the vehicle's sensors are not always collecting environmental information, but are in a state of stopping the collection of environmental information. Therefore, when the vehicle is parked in the target parking space and restarted, the second environmental information and the first environmental information collected by the sensor are not in a time-series continuous information collection action. This will make it difficult for the second environmental information to match the environmental features in the first environmental information, which in turn affects the accuracy of updating the parking lot map data by the second environmental information. The environmental information collected when the vehicle arrives near the target parking space can be matched with the environmental information collected after the vehicle is parked out of the target parking space. Although these two times are not time-series continuous, the difference in the position of the vehicle will not be too large, so the environmental information collected by the vehicle's sensor may include the same environmental features. That is, the second environmental information and the first environmental information include part of the same environmental information. As a result, the second environmental information and the parking lot map data established based on the first environmental information can be placed in the same coordinate system, thereby completing the update and construction of the parking lot map data.
[0039] In another optional implementation, the environmental information collection time can be extended, for example, the environmental information collected during the process of parking the vehicle into the parking space is included in the first environmental information. The environmental information collected during the process of parking the vehicle out of the parking space is included in the second environmental information. When the vehicle parks into and out of the parking space, it experiences the same short track. In this case, there are more observations of the same environmental objects in the two environmental information collections, which can facilitate the matching of the second environmental information with the first environmental information, thereby facilitating the map generation operation.
[0040] According to the normal driving process, the user will return to the target parking space after a period of time, restart the vehicle, drive the vehicle out of the target parking space manually or automatically, and then need to use manual driving to drive the vehicle from the target parking space to the parking lot exit (ie, the second position).
[0041] During manual driving, a second path from the target parking space to the parking lot exit (ie, the second location) may be recorded. Specifically, trajectory information of the second path and environmental elements recorded along the first route (ie, the second environmental information) may be recorded.
[0042] S30: Update the parking lot map data based on the second environment information, where the parking lot map data is used to guide the vehicle to automatically travel on the first path and / or the second path.
[0043] After obtaining the second environment information, the previously constructed parking lot map data may be updated using the second environment information, so that the parking lot map data may include the first path and the second path.
[0044] In an optional implementation, a section of parking lot map data can be constructed based on the first environmental information of the first path, and a section of parking lot map data can be constructed based on the second environmental information of the second path. Then, the two nodes of the entrance (i.e., the first position) and the exit (i.e., the second position) of the parking lot can be determined, and then the two sections of data can be matched and spliced based on the two nodes to obtain complete parking lot map data from the parking lot entrance through the first parking space to the parking lot exit. Specifically, the map can be constructed silently in the background after the user turns off the engine and leaves the car.
[0045] Optionally, the parking lot map data may include location information of a plurality of parking spaces around the first path and / or the second path, and the parking lot map may also be used to guide the vehicle to automatically drive to the vicinity of any one of the plurality of parking spaces.
[0046] When it is detected that the vehicle arrives at the parking lot again, the automatic parking function can be turned on at the entrance of the parking lot in response to user operation, and automatic parking can be performed according to the parking lot map data. The vehicle can be controlled to drive automatically from the entrance of the parking lot, find a parking space along the way, control the vehicle to automatically drive to the vicinity of any parking space among multiple parking spaces, and park in the space after finding a parking space that can be parked.
[0047] In an optional implementation, the method further includes: generating a map display interface based on the parking lot map data, wherein the map display interface is used for displaying on a user terminal device and / or a vehicle display device of the vehicle.
[0048] Optionally, the map display interface includes one or more of the following identification information: a path identification of a mapped path; parking space indication identification around the path; a vehicle position indication identification of the vehicle's location; and a mapping completion identification of any path segment of the path.
[0049] The above-mentioned signs can be displayed as an overlay on the map interface. For example, the signs of the mapped paths and the parking space signs around them can be displayed on the map, and the completion of the mapped paths can be displayed through the map completion signs.
[0050] The map completion indicator can be set based on the richness of the collected environmental information. The richer the environmental information, the more conducive it is to building a detailed map. Therefore, when driving on a certain path for the first time, the collected environmental information may only reach 50% of the preset map requirements; the second time, the newly collected environmental information may make the map completion closer to the preset map requirements, for example, reaching 70% of the preset map requirements. A map completion indicator can be set, and as the environmental information used for mapping becomes more complete, users can understand the growth of this completion based on the map completion indicator.
[0051] It is worth noting that the above one or more identification information can be reflected in the interface as an independent identification area or a combination of interface elements that can express some identification meanings. In some cases, the mapped path identification and the mapping completion identification of any path segment of the path can be integrated into the same interface element. Optionally, different degrees of completion can be reflected based on the color of the path. It can also be based on the pixel area occupied by the path identification, for example, the mapping completion can be reflected by the thickness of the path.
[0052] After the parking lot map data is constructed, the parking lot map data can be visualized in the human-machine interface of the user terminal device and / or the vehicle display device to present a map display interface, such as Figure 2 To display the route in the map and the parking spaces along the route.
[0053] In an optional embodiment, the method further includes: obtaining an interface position selected by a user in the map display interface; marking a key area in the parking lot map data based on the interface position, wherein the key area is used to guide the vehicle to trigger a parking operation when driving to the key area.
[0054] In the existing automatic parking function, the vehicle can only automatically drive from the parking lot entrance to the parking space. A stop will cause the automatic parking function to exit and the driver will be required to stay in the car. After the driver gets off the car in the parking space, he or she will also need to return to pedestrian entrances such as the elevator entrance or stairs.
[0055] Based on this, key areas, i.e., passenger boarding and alighting areas, such as elevator entrances and stairwells, can be marked in the constructed parking lot map data according to user operations. During automatic parking according to the parking lot map data, when the vehicle reaches the key area, the vehicle is controlled to stop and the driver can get off in the key area.
[0056] When the driver leaves the vehicle, the vehicle can continue to park automatically according to the parking lot map data without anyone driving until it finds a available parking space and parks in it. This means that the driver does not need to stay in the vehicle throughout the entire automatic parking process, and can choose to get off in an area other than the parking space during the automatic parking process, which can better meet user needs.
[0057] In one example, when it is time to leave the parking lot, the driver does not need to return to the parking space to start the vehicle. Instead, the driver can use the APP in the mobile terminal to control the vehicle to automatically drive to the key area according to the parking lot map data. The driver only needs to walk to the key area such as the boarding point.
[0058] In an optional implementation, in order to ensure the safety of unmanned driving, the vehicle's driving conditions can be uploaded to the cloud when no one is driving. The cloud can convey it to the APP in the user's mobile terminal, and the user can then learn about the vehicle's driving conditions through the APP in the mobile terminal.
[0059] In an optional embodiment, the method further includes: determining a path that the vehicle has not reached based on the environmental information, the path that has not been reached is connected to the path that the vehicle has traveled; and the map display interface also includes an identifier of the path that has not been reached.
[0060] Since the constructed map is constructed in sections, it is not a complete map of the parking lot. There are paths that the vehicle has not reached, that is, unexplored areas. If the vehicle reaches the end of the path, the area is considered to have been explored. If there is still a road ahead, it means that there is an unexplored area ahead. The unreached path identification can be displayed on the map display interface, for example, the area identification of the area where the path is located, or the identification of the extension direction of the path. Optionally, while the vehicle is traveling along the first path or the second path, the vehicle can collect environmental information around the current path and identify other feasible areas for the vehicle from the environmental information, such as the passable areas indicated by ground signs. These passable areas can also be identified in the map.
[0061] In an optional implementation, in the map display interface, auxiliary perception elements may be added for unreached paths, such as blurring the unexplored areas, for example, adding a "fog" filter, to indicate to users that the area is unexplored.
[0062] Optionally, the boundary of the area in the parking lot, such as a wall, may also be displayed in the map display interface.
[0063] In an optional embodiment, the method further includes: obtaining newly collected environmental information by sensors of the vehicle when the vehicle is traveling on a new path, the new path including the path of the trajectory of the vehicle during the vehicle's automatic driving process; and updating the parking lot map data based on the newly collected environmental information.
[0064] In the existing automatic parking function, it can usually only control the vehicle to travel along the recorded route. In some scenarios, the user does not have a fixed parking space, and the parking space in the pre-recorded route may be occupied, then the existing automatic parking function will not be able to park.
[0065] Based on this, during the process of automatic parking according to the parking lot map data, when no parking space is found along the route recorded in the parking lot map data, such as no parking space is found when the vehicle is automatically driven to a position less than a preset distance from the parking lot exit, such as 5 meters, it is possible to seamlessly switch to the exploration mode, explore the parking space in the parking lot, and control the vehicle to automatically drive to a new path. The new path section is not recorded in the navigation map data, that is, the unmapped area, and then a parking space can be found for parking during the automatic driving process of the new path.
[0066] Specifically, in the process of searching for parking spaces on a new path, a local perception strategy can be used. On the one hand, the recorded parking lot map data is used as a benchmark, combined with the visual mileage calculation method, to estimate the positioning information of the vehicle itself. On the other hand, the perception vision algorithm configured on the vehicle is used to monitor the drivable area, obstacles on the road, and vacant parking spaces in real time.
[0067] In the process of searching for a parking space along a new path, the trajectory information of the new path and the environmental elements recorded along the new path (i.e., the newly collected environmental information) may be recorded. Then, based on the recorded relevant information, the pre-constructed parking lot map data may be updated and the new path may be added thereto, so that the parking lot map data includes the location information of the new path and the location information of multiple parking spaces around the new path segment.
[0068] In an optional implementation, after the parking lot map data is constructed, the parking lot map data may be uploaded to the cloud, and the cloud may share the uploaded parking lot map data with other vehicles that need to enter the parking lot.
[0069] In an optional implementation, since the parking lot map data may only include a portion of the map of the parking lot, or some of the parking lot map data may be erroneous, the parking lot map data shared by other vehicles may be obtained from the cloud, and the shared parking lot map data may be used to update the constructed parking lot map data.
[0070] Specifically, part of the map data that does not exist in the parking lot map data may be added, and part of the map data that is different from the parking lot map data may be calibrated.
[0071] In the embodiment of the present disclosure, parking lot map data generated by acquiring first environmental information collected before the vehicle parks in a parking space, and acquiring second environmental information collected during the driving process after the vehicle drives out of the target parking space after the vehicle is parked in the target parking space and restarted, and updating the parking lot map data based on the second environmental information, in this way, environmental information collected in segments during the driving process on multiple local paths of the parking lot can be used to accumulate and construct a map, thereby reducing the user's time cost for constructing parking lot map data.
[0072] Reference Figure 3 , shows a flow chart of a vehicle control method provided by an embodiment of the present disclosure, which may specifically include the following steps:
[0073] S40, acquiring parking lot map data, wherein the parking lot map data is generated by environmental information collected by sensors of the vehicle during the historical driving process of the vehicle; wherein the historical driving process includes the driving process of the vehicle from a first position to a target parking space, and the driving process of the vehicle from the target parking space to a second position after the vehicle is parked at the target parking space and restarted;
[0074] Optionally, the parking lot map data may include feature information of scenery around the path, for example, architectural elements: columns, walls, door openings, pipes, etc.; traffic sign elements: lane lines, parking space lines, traffic signs, guide signs, etc.
[0075] Optionally, the first location may be the entrance to the parking lot. For example, the vehicle identifies information such as the parking lot gate, the down ramp, and the parking lot sign based on the collected environmental information, and determines the entrance to the parking lot. The first environmental information may be environmental information recorded starting from the time the vehicle identifies the parking lot entrance.
[0076] Optionally, the parking lot map data may include position information of the path in space, and position information of parking spaces around the path in space.
[0077] In an optional implementation, the first environmental information collected while the vehicle is traveling along the first path is obtained, and when the vehicle is parked in the target parking space, the computing unit of the vehicle does not need to perform motion control of the vehicle, and may not need to process human-computer interaction control, and is in a relatively idle state. At this time, the computing unit carried by the vehicle can be used to process the first environmental information and generate the parking lot map data.
[0078] For vehicles with autonomous driving capabilities, such as passenger cars equipped with autonomous driving systems or assisted driving systems, and unmanned logistics vehicles, the use of the automatic parking function requires reliance on high-precision maps. When it is detected that the vehicle has arrived at a parking lot, such as the vehicle is currently at the toll booth at the entrance of the parking lot, it can first be determined whether the vehicle has a map stored for the parking lot.
[0079] If a map for the parking lot is stored, the user can be prompted to use the automatic parking function, such as by a pop-up window in the human-machine interface provided by the vehicle's display screen, or by a voice broadcast in the vehicle. The automatic parking function can be activated in response to user instructions. After the automatic parking function is activated, automatic parking can be performed directly according to the pre-stored map.
[0080] If no map for the parking lot is stored, the automatic parking function cannot be used and the user needs to drive manually in the parking lot. Relevant information can be recorded during the manual driving process, which may include driving trajectory information and environmental elements recorded along the driving trajectory, such as feature points, pillars, ground lane lines, traffic signs, arrows, etc., and then a map can be constructed based on the recorded relevant information.
[0081] For users, their normal driving process is to drive the vehicle from the parking lot entrance to the parking space and leave the vehicle after parking, return to the parking space after a period of time, such as returning to the parking space after get off work or after shopping in a mall, and then restart the vehicle and drive the vehicle from the parking space to the parking lot exit. Based on this, in order to avoid the need for users to manually drive from the parking lot entrance to the parking lot exit to build a complete map, the map can be built segment by segment along the user's normal driving process.
[0082] Specifically, after the vehicle enters the parking lot entrance, the vehicle needs to be driven manually by the user because the automatic parking function cannot be used. During the manual driving process, the vehicle system can record relevant information, and can automatically detect the surrounding parking spaces and remind the user in real time.
[0083] After the user confirms in the vehicle system or the APP on the mobile terminal, the vehicle can automatically park in the designated parking space. Of course, the user can also park in the parking space manually. After parking in the parking space, the user can leave the vehicle after turning off the engine.
[0084] Since the first path from the parking lot entrance to the target parking space is recorded during the manual driving process, specifically the trajectory information of the first path and the environmental elements recorded along the first path can be recorded, the parking lot map data for the first path can be constructed based on the recorded relevant information. Specifically, the map can be constructed silently in the background after the user turns off the engine and leaves the car.
[0085] It is worth noting that when a vehicle is parked in a parking space, the power consumption of various systems is often reduced. At this time, the vehicle's sensors are not always collecting environmental information, but are in a state of stopping the collection of environmental information. Therefore, when the vehicle is parked in the target parking space and restarted, the second environmental information and the first environmental information collected by the sensor are not in a time-series continuous information collection action. This will make it difficult for the second environmental information to match the environmental features in the first environmental information, which in turn affects the accuracy of updating the parking lot map data by the second environmental information. The environmental information collected when the vehicle arrives near the target parking space can be matched with the environmental information collected after the vehicle is parked out of the target parking space. Although these two times are not time-series continuous, the difference in the position of the vehicle will not be too large, so the environmental information collected by the vehicle's sensor may include the same environmental features. That is, the second environmental information and the first environmental information include part of the same environmental information. As a result, the second environmental information and the parking lot map data established based on the first environmental information can be placed in the same coordinate system, thereby completing the update and construction of the parking lot map data.
[0086] According to the normal driving process, the user will return to the target parking space after a period of time, restart the vehicle, drive the vehicle out of the target parking space manually or automatically, and then need to use manual driving to drive the vehicle from the target parking space to the parking lot exit.
[0087] During manual driving, a second path from the target parking space to the parking lot exit may be recorded, and specifically, trajectory information of the second path and environmental elements recorded along the first route may be recorded.
[0088] After obtaining the second environment information, the previously constructed parking lot map data may be updated using the second environment information, so that the parking lot map data may include the first path and the second path.
[0089] In an optional implementation, a section of parking lot map data can be constructed based on the first environmental information of the first path, and a section of parking lot map data can be constructed based on the second environmental information of the second path. Then, the two nodes of the entrance and exit of the parking lot can be determined therefrom, and then the two sections of data can be matched and spliced based on the two nodes to obtain complete parking lot map data from the parking lot entrance through the first parking space to the parking lot exit. Specifically, the map can be constructed silently in the background after the user turns off the engine and leaves the car.
[0090] Optionally, the parking lot map data may include location information of a plurality of parking spaces around the first path and / or the second path, and the parking lot map may also be used to guide the vehicle to automatically drive to the vicinity of any one of the plurality of parking spaces.
[0091] S50: Control the vehicle to automatically travel on the first path and / or the second path according to the parking lot map data.
[0092] In an optional embodiment, the method further includes:
[0093] During the automatic driving of the vehicle according to the path recorded by the parking lot map data, environmental information around the path is acquired, and an empty parking space among the plurality of parking spaces around the path is identified based on the environmental information; and the vehicle is controlled to drive to the empty parking space.
[0094] In an optional embodiment, the method further includes:
[0095] A request for parking in the vacant parking space is sent to a user; and in response to a parking confirmation instruction sent by the user, the vehicle is controlled to park in the vacant parking space.
[0096] When it is detected that the vehicle arrives at the parking lot again, the automatic parking function can be turned on at the entrance of the parking lot in response to user operation, and automatic parking can be performed according to the parking lot map data. The vehicle can be controlled to drive automatically from the entrance of the parking lot, find a parking space along the way, control the vehicle to automatically drive to the vicinity of any parking space among multiple parking spaces, and park in the space after finding a parking space that can be parked.
[0097] In an optional implementation, the method further includes: generating a map display interface based on the parking lot map data, wherein the map display interface is used for displaying on a user terminal device and / or a vehicle display device of the vehicle.
[0098] Optionally, the map display interface includes one or more of the following identification information: a mapped path identification; a parking space indication identification around the path; a vehicle position indication identification of the vehicle's location; and a mapping completion identification of any path segment of the path.
[0099] After the parking lot map data is constructed, the parking lot map data can be visualized in the human-machine interface of the user terminal device and / or the vehicle display device to present a map display interface, such as Figure 2 To display the route in the map and the parking spaces along the route.
[0100] In an optional embodiment, the method further includes: obtaining a key area determined in the parking lot map data, wherein the key area is determined based on an interface position selected by a user in the map display interface; if it is determined based on the parking lot map data that the vehicle has reached the key area, a parking operation is triggered.
[0101] In the existing automatic parking function, the vehicle can only automatically drive from the parking lot entrance to the parking space. A stop will cause the automatic parking function to exit and the driver will be required to stay in the car. After the driver gets off the car in the parking space, he or she will also need to return to pedestrian entrances such as the elevator entrance or stairs.
[0102] Based on this, key areas, i.e., passenger boarding and alighting areas, such as elevator entrances and stairwells, can be marked in the constructed parking lot map data according to user operations. During automatic parking according to the parking lot map data, when the vehicle reaches the key area, the vehicle is controlled to stop and the driver can get off in the key area.
[0103] When the driver leaves the vehicle, the vehicle can continue to park automatically according to the parking lot map data without anyone driving until it finds a available parking space and parks in it. This means that the driver does not need to stay in the vehicle throughout the entire automatic parking process, and can choose to get off in an area other than the parking space during the automatic parking process, which can better meet user needs.
[0104] In one example, when it is time to leave the parking lot, the driver does not need to return to the parking space to start the vehicle. Instead, the driver can use the APP in the mobile terminal to control the vehicle to automatically drive to the key area according to the parking lot map data. The driver only needs to walk to the key area such as the boarding point.
[0105] In an optional implementation, in order to ensure the safety of unmanned driving, the vehicle's driving conditions can be uploaded to the cloud when no one is driving. The cloud can convey it to the APP in the user's mobile terminal, and the user can then learn about the vehicle's driving conditions through the APP in the mobile terminal.
[0106] In an optional embodiment, the method further includes: determining a path that the vehicle has not reached based on the environmental information, the path that has not been reached is connected to the path that the vehicle has traveled; and the map display interface also includes an identifier of the path that has not been reached.
[0107] Since the constructed map is constructed in sections, it is not a complete map of the parking lot. There are paths that the vehicle has not reached, that is, unexplored areas. If the vehicle reaches the end of the path, the area is considered to have been explored. If there is still a road ahead, it means that there is an unexplored area ahead. The unreached path mark can be displayed on the map display interface, for example, the area mark of the area where the path is located, or the mark of the extension direction of the path.
[0108] In an optional implementation, in the map display interface, auxiliary perception elements may be added for unreached paths to indicate to the user that the area is unexplored. Optionally, the boundaries of the area in the parking lot, such as walls, may also be displayed in the map display interface.
[0109] In an optional embodiment, the method further includes: acquiring environmental information newly collected by sensors of the vehicle when the vehicle travels on a new path section, the new path not being stored in the generated parking lot map data; updating the parking lot map data based on the newly collected environmental information so that the parking lot map data includes location information of the new path and location information of multiple parking spaces around the new path section.
[0110] In the existing automatic parking function, it can usually only control the vehicle to travel along the recorded route. In some scenarios, the user does not have a fixed parking space, and the parking space in the pre-recorded route may be occupied, then the existing automatic parking function will not be able to park.
[0111] Based on this, during the process of automatic parking according to the parking lot map data, when no parking space is found along the route recorded in the parking lot map data, such as no parking space is found when the vehicle is automatically driven to a position less than a preset distance from the parking lot exit, such as 5 meters, it is possible to seamlessly switch to the exploration mode, explore the parking space in the parking lot, and control the vehicle to automatically drive to a new path. The new path section is not recorded in the navigation map data, that is, the unmapped area, and then a parking space can be found for parking during the automatic driving process of the new path.
[0112] Specifically, in the process of searching for parking spaces on a new path, a local perception strategy can be used. On the one hand, the recorded parking lot map data is used as a benchmark, combined with the visual mileage calculation method, to estimate the positioning information of the vehicle itself. On the other hand, the perception vision algorithm configured on the vehicle is used to monitor the drivable area, obstacles on the road, and vacant parking spaces in real time.
[0113] In the process of searching for a parking space along a new path, the trajectory information of the new path and the environmental elements recorded along the new path (i.e., the newly collected environmental information) may be recorded. Then, based on the recorded relevant information, the pre-constructed parking lot map data may be updated and the new path may be added thereto, so that the parking lot map data includes the location information of the new path and the location information of multiple parking spaces around the new path segment.
[0114] In an optional implementation, after the parking lot map data is constructed, the parking lot map data may be uploaded to the cloud, and the cloud may share the uploaded parking lot map data with other vehicles that need to enter the parking lot.
[0115] In an optional implementation, since the parking lot map data may only include a portion of the map of the parking lot, or some of the parking lot map data may be erroneous, the parking lot map data shared by other vehicles may be obtained from the cloud, and the shared parking lot map data may be used to update the constructed parking lot map data.
[0116] Specifically, part of the map data that does not exist in the parking lot map data may be added, and part of the map data that is different from the parking lot map data may be calibrated.
[0117] In the disclosed embodiment, parking lot map data is obtained, and the parking lot map data is generated by environmental information collected by sensors of the vehicle during the historical driving process of the vehicle; wherein the historical driving process includes the driving process of the vehicle from a first position to a target parking space, and the driving process of the vehicle from the target parking space to a second position after the vehicle is parked and restarted at the target parking space, and then the vehicle is controlled to automatically drive on the first path and / or the second path according to the parking lot map data. In this way, the vehicle can be controlled to automatically drive on the basis of accumulating and constructing a parking lot map by using the environmental information of the parking lot collected in segments, thereby improving the convenience of using the automatic driving function of the vehicle.
[0118] The present disclosure provides another embodiment comprising the following steps:
[0119] Step 1: Detect whether the vehicle has reached the entrance of the parking lot.
[0120] Specifically, in response to the user's navigation setting operation, the target navigation route determined by the user is displayed, and the user drives manually or the vehicle drives automatically to reach the navigation target location. Specifically, the vehicle can further detect whether there are gate facilities at the entrance of the parking lot or parking lot signs around the navigation target location. If these facilities and signs exist, it is determined that the entrance location of the parking lot has been reached. In addition, it can also be combined with ground navigation operations such as GPS to determine whether the entrance location of the parking lot has been reached.
[0121] Step 2: Check whether a map of the current parking lot has been stored.
[0122] Step 3: If the map data of the parking lot has been stored, a prompt message is issued to indicate that the vehicle can use the automatic parking function in the parking lot.
[0123] Step 4: If the map data of the parking lot is not stored, the vehicle's sensors are controlled to collect surrounding environment information.
[0124] That is to say, if a high-precision map has been built for the parking lot before, a pop-up window will appear to remind you that automatic parking can be used. However, if no map has been built before, the autonomous driving system will start to automatically record the vehicle's driving trajectory. For example, when the vehicle enters a parking lot for the first time, the vehicle user needs to manually drive to the parking space. At this time, the autonomous driving system will record the surrounding environment elements (feature points in the environment, or elements with special semantic information in the environment, such as pillars, ground lane lines, traffic signs, arrows, etc.).
[0125] Step 5: Based on the collected environmental information, the parking spaces around the vehicle's current driving path are detected, and a prompt message is sent to the user.
[0126] During manual driving, the system will still automatically detect vacant parking spaces and remind users in real time. After the user confirms in the vehicle system / mobile phone APP, the vehicle will enable automatic parking and drive the vehicle from the parking lot path into the detected vacant parking space.
[0127] Step 6: Build a map of the parking lot based on the collected environmental information.
[0128] After the vehicle is parked in the target parking space, the user gets off and the vehicle is turned off. The vehicle can control the background processor to silently build a map after the user leaves the vehicle. At this time, the vehicle only records the first path map from the parking lot entrance to the parking space.
[0129] When the user returns to the vehicle again, the vehicle can automatically exit the parking space after the user confirms through the vehicle system / mobile phone APP.
[0130] Step 7: Detecting that the vehicle is moving out of the parking space, controlling the vehicle's sensors to collect new environmental information.
[0131] Step 8: Based on the collected environmental information, if it is detected whether the vehicle has reached the exit position of the parking lot, a map of the parking lot is constructed based on the environmental information collected from the parking space to the exit position.
[0132] That is to say, after the vehicle leaves the parking space, the vehicle starts to record the surrounding environmental elements and driving trajectory. However, since the map constructed by the environmental information collected before parking in the parking space only includes the map of the driving path from the parking lot entrance to the parking space, and does not include the map from the parking space to the parking lot exit, the user still needs to manually drive the vehicle to the parking lot exit after parking. At this time, the vehicle has completed the information collection from the parking space to the parking lot exit.
[0133] In an optional implementation, a map of the second path from the parking space to the parking lot exit can be constructed. By splicing the map of the first path with the map of the second path, a parking lot map from the parking lot entrance to the target parking space, and then from the target parking space to the parking lot exit can be obtained.
[0134] In another optional implementation, the environmental information collected during the driving process of the second path from the parking space to the parking lot exit can be used to update the already generated first path map, thereby obtaining a parking lot map from the parking lot entrance to the target parking space and then from the target parking space to the parking lot exit.
[0135] The map generation process such as map construction, updating or splicing may not be completed immediately after the environmental information collection of the second path is completed. Instead, the environmental information collected during the driving of the second path is temporarily stored. After the vehicle arrives at a new parking space and the occupants leave the vehicle, the vehicle's processor executes the map generation operation.
[0136] In the above steps, the parking lot entrance is identified through navigation positioning, environmental information recognition, etc., and the start and end nodes of the parking lot map are recorded to form a complete trajectory route of "parking lot entrance - parking space - parking lot exit". This is mainly done by matching and splicing the two segments of data when entering and exiting the parking space. In addition, the entire map is built at the user's leisure time (after the customer turns off the engine and leaves the vehicle).
[0137] After that, if the vehicle arrives at the entrance of the parking lot, the automatic parking mode can be turned on at the entrance of the parking lot to find a parking space according to the trajectory route in the previously recorded parking lot map.
[0138] In an optional implementation, some parking lots are all public parking spaces, and the parking spaces are not fixed. When the vehicle is driving according to the historical trajectory, if no vacant parking spaces are found, it will enter the exploration mode when approaching the exit of the parking lot. In the exploration mode, the vehicle can go to previously unrecorded areas according to the lane lines and ground arrows. At this time, a local perception strategy is used. On the one hand, the positioning information of the vehicle is estimated based on the recorded map trajectory combined with the visual mileage calculation method. On the other hand, the perception visual algorithm is used to monitor the drivable area, obstacles on the road and vacant parking spaces in real time. Similarly, after finding an empty parking space, the vehicle can prompt the information of the empty parking space on the vehicle system, or send this information to other user terminals to recommend parking the vehicle in the parking space. The user can confirm on the vehicle system / other user terminal, and the vehicle will automatically park in the recommended parking space after receiving the confirmation command. Optionally, the trajectory and environmental elements of the vehicle in the new exploration area will also be recorded to update the existing parking lot map.
[0139] In an optional implementation, the user can mark the area where the floor elevator is located in the created map track. After the vehicle drives to the elevator entrance, the user can choose to get off, and then the vehicle automatically drives to the parking space and automatically parks. After getting off the vehicle, the user can view the vehicle status through a user terminal such as a mobile phone.
[0140] It should be noted that, for the method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present disclosure are not limited by the order of the actions described, because according to the embodiments of the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present disclosure.
[0141] An embodiment of the present disclosure also provides a device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the above-mentioned map data processing method and / or vehicle control method is implemented.
[0142] An embodiment of the present disclosure also provides a vehicle, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor, and when the computer program is executed by the processor, the above-mentioned map data processing method and / or vehicle control method are implemented. For example, the vehicle may include a controller for automatic driving, including a sensor for collecting information about the environment surrounding the vehicle body, and a sensor for collecting information about the occupants inside the vehicle. The controller is connected to one or more sensors to obtain data collected by the sensors. In addition, the controller is connected to the vehicle body controller to send the generated automatic driving control instructions to the body controller, so that the body controller can respond to the control instructions and perform corresponding control operations such as forward movement and steering. Among them, the controller for automatic driving may store a computer program, and when the computer program is executed by the processor of the controller, the above-mentioned map data processing method and / or vehicle control method are implemented.
[0143] An embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned map data processing method and / or vehicle control method is implemented.
[0144] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0145] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0146] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0147] Those skilled in the art will appreciate that the disclosed embodiments may be provided as methods, devices, or computer program products. Therefore, the disclosed embodiments may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the disclosed embodiments may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0148] The embodiments of the present disclosure are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0149] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0150] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0151] Although the preferred embodiments of the present disclosure have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present disclosure.
[0152] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.
[0153] The map data processing and vehicle control method, device, and medium provided are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present disclosure. The description of the above embodiments is only used to help understand the method of the present disclosure and its core idea. At the same time, for those skilled in the art, according to the idea of the present disclosure, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present disclosure.
Claims
1. A map data processing method, characterized in that: The method comprises: Acquire stored parking lot map data of the vehicle, the parking lot map data being generated based on first environmental information collected while the vehicle is traveling along a first path, the first path comprising a path of the vehicle traveling from a first position to a target parking space; After the vehicle is parked in the target parking space and restarted, obtaining second environmental information collected by the vehicle, the second environmental information being collected during the process of the vehicle traveling along a second path, the second path including a path of the vehicle traveling from the target parking space to a second location; The parking lot map data is updated based on the second environmental information, and the parking lot map data is used to guide the vehicle to automatically travel on the first path and / or the second path.
2. The method according to claim 1 is characterized in that The parking lot map data includes location information of a plurality of parking spaces around the first path and / or the second path, and the parking lot map is also used to guide the vehicle to automatically drive to the vicinity of any parking space among the plurality of parking spaces.
3. The method according to claim 1, characterized in that Also includes: Generating a map display interface based on the parking lot map data, wherein the map display interface is used for displaying on a user terminal device and / or a vehicle display device of the vehicle; The map display interface includes one or more of the following identification information: Path identifier of the mapped path; Parking space signage around the path; A vehicle position indicator indicating the location of the vehicle; The mapping completion indicator for any path segment of the path.
4. The method according to claim 3, characterized in that Also includes: Obtaining the interface position selected by the user on the map display interface; A key area is marked in the parking lot map data based on the interface position, and the key area is used to guide the vehicle to trigger a parking operation when driving to the key area.
5. The method according to claim 3, characterized in that: Also includes: Determining a path that the vehicle has not reached according to the environmental information, wherein the path that the vehicle has not reached is connected to a path that the vehicle has traveled; The map display interface also includes a path identifier of the unreached path.
6. The method according to any one of claims 1 to 5, characterized in that: Also includes: Acquire new environmental information collected by the sensor of the vehicle when the vehicle travels on a new path, wherein the new path includes a path of the trajectory of the vehicle during the process of the vehicle performing automatic driving; The parking lot map data is updated based on the newly collected environmental information.
7. A vehicle control method, characterized in that: The method comprises: Acquire parking lot map data, wherein the parking lot map data is generated from environmental information collected by sensors of the vehicle during the historical driving process of the vehicle; wherein the historical driving process includes the driving process of the vehicle from a first position to a target parking space, and the driving process of the vehicle from the target parking space to a second position after the vehicle is parked at the target parking space and restarted; The vehicle is controlled to automatically travel on the first path and / or the second path according to the parking lot map data.
8. The method according to claim 7, characterized in that Also includes: During the process of the vehicle automatically driving along the path recorded by the parking lot map data, environmental information around the path is acquired, and a vacant parking space among the plurality of parking spaces around the path is identified based on the environmental information; The vehicle is controlled to travel to the vacant parking space.
9. The method according to claim 8, characterized in that: The method further comprises: Sending a request to the user to park in the vacant parking space; In response to a parking confirmation instruction sent by a user, the vehicle is controlled to park in the vacant parking space.
10. The method according to any one of claims 7 to 9, characterized in that: Also includes: Generating a map display interface based on the parking lot map data, wherein the map display interface is used for displaying on a user terminal device and / or a vehicle display device of the vehicle; The map display interface includes one or more of the following identification information: Path identifier of the mapped path; Parking space signage around the path; A vehicle position indicator indicating the location of the vehicle; The mapping completion indicator for any path segment of the path.
11. The method according to claim 10, characterized in that Also includes: Acquire a key area determined in the parking lot map data, where the key area is determined based on an interface position selected by a user on the map display interface; If it is determined based on the parking lot map data that the vehicle has reached the key area, a parking operation is triggered.
12. The method according to claim 10, characterized in that Also includes: Determining a path that the vehicle has not reached according to the environmental information, wherein the path that the vehicle has not reached is connected to a path that the vehicle has traveled; The map display interface also includes a path identifier of the unreached path.
13. The method according to any one of claims 7 to 9, characterized in that: Also includes: Acquiring new environmental information collected by the sensor of the vehicle when the vehicle travels in a new path section, wherein the new path is not stored in the generated parking lot map data; The parking lot map data is updated based on the newly collected environmental information, so that the parking lot map data includes the location information of the new path and the location information of a plurality of parking spaces around the new path segment.
14. A device, characterized in that The method comprises a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the method according to any one of claims 1 to 13 when executed by the processor.
15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 13 is implemented.
Citation Information
Cited By
Method for picking up passenger indoor in an autonomous vehicle
TWI928600B
