A method and system for cruising in a parking lot

Abstract

The application discloses a parking lot cruising method and system, and belongs to the technical field of automatic driving, wherein the implementation of the method comprises the following steps: acquiring a high-definition map of a target parking lot and a target parking space in the target parking lot, and planning a global path based on the high-definition map of the target parking lot and the target parking space in the target parking lot; acquiring relevant real-time environment information of a road where a vehicle is located which is sent by a road side unit (RSU) in the target parking lot; and based on the relevant real-time environment information and a BSM message sent by other vehicles, making a cruising decision and planning in the target parking lot in cooperation with the vehicle. The V2I and V2V messages received by the vehicle are used as over-distance sensor information, which can effectively help the vehicle to avoid collision, predict the time when the collision may occur, and help the vehicle to make effective driving decisions and path planning.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of automatic driving, and more particularly relates to a parking lot cruising method and system. BACKGROUND

[0002] In the autonomous valet parking application scenario, the vehicle needs to cruise autonomously in the parking lot from the entrance to the parking space. On the one hand, the environment in the parking lot is relatively complex because there is no strong traffic regulation and most parking lots do not realize separation of people and vehicles. In addition, the vision is not open in the parking lot, especially the intersection is seriously limited by the vision of the parking lot column. On the other hand, the vehicle drives at a relatively fast speed on the parking lot lane, and in the face of the scene of suddenly appearing vehicles and pedestrians at the intersection, it may be unsafe or unable to make efficient decisions to rely solely on the single vehicle intelligent technical solution to realize this autonomous cruising section. SUMMARY

[0003] In view of the above defects or improvement needs of the prior art, the present application provides a parking lot cruising method and system. For the intersection with severely limited vision in the parking lot, the vehicle itself sensor often cannot identify or identify the obstacles on the adjacent road in time. The present application uses the V2I and V2V messages received by the vehicle as an over-distance sensor information, which can effectively help the vehicle to avoid collision, predict the time when the collision may occur, and help the vehicle to make effective driving decisions and path planning.

[0004] To achieve the above purpose, according to one aspect of the present application, a parking lot cruising method is provided, comprising:

[0005] obtaining a high-definition map of a target parking lot and a target parking space in the target parking lot, and planning a global path based on the high-definition map of the target parking lot and the target parking space in the target parking lot;

[0006] obtaining relevant real-time environmental information of a road where the vehicle is located sent by a roadside unit RSU in the target parking lot;

[0007] based on the relevant real-time environmental information and the BSM messages sent by other vehicles, making cruising decisions and planning in the parking lot.

[0008] In some optional embodiments, the obtaining a high-definition map of a target parking lot and a target parking space in the target parking lot, and planning a global path based on the high-definition map of the target parking lot and the target parking space in the target parking lot, comprises:

[0009] after starting the AVP function, displaying a target area capable of performing the AVP autonomous valet parking function;

[0010] After the vehicle is in the target area capable of AVP function and the target parking lot is selected, a high-definition map of the target parking lot and a target parking space are acquired;

[0011] The vehicle is positioned in the high-definition map of the target parking lot according to the high-definition map of the target parking lot, and a global path is planned based on the position of the vehicle itself and the target parking space.

[0012] In some optional embodiments, the relevant real-time environmental information of the road where the vehicle is located and sent by the road side unit RSU in the target parking lot includes:

[0013] The position of the vehicle itself is acquired, the target road where the vehicle is located is determined, and the vehicle BSM message is sent outward at a fixed frequency, so that the RSU determines whether the real-time environmental information of the target road where the vehicle is located and the relevant road of the target road where the vehicle is located detected by the sensor connected with the RSU needs to be sent outward according to the vehicle BSM message;

[0014] The real-time environmental information of the target road where the vehicle is located and the relevant road of the target road where the vehicle is located detected by the RSU is acquired.

[0015] In some optional embodiments, the RSU determines whether the real-time environmental information of the target road where the vehicle is located and the relevant road of the target road where the vehicle is located detected by the sensor connected with the RSU needs to be sent outward according to the vehicle BSM message, including:

[0016] The position of the vehicle itself is parsed in the BSM message, the vehicle is positioned on the target road corresponding to the position of the vehicle itself in the high-definition map, the driving direction of the vehicle on the target road is determined according to the comparison between the heading angle of the vehicle and the heading angle of the target road, and the relevant road of the target road where the vehicle is located is determined according to the pre-stored road topological relationship in the RSU, wherein the relevant road of the target road where the vehicle is located is connected with the target road where the vehicle is located and is in the direction of the vehicle advancing.

[0017] After the relevant road of the target road where the vehicle is located is determined, the RSU determines whether there is a road side sensor connected with the RSU in the target road where the vehicle is located and the relevant road of the target road where the vehicle is located according to the position of the vehicle itself, the coordinates of the target road and the relevant road in the received BSM message and the coordinates of the road side sensor connected with the RSU.

[0018] If there is a road side sensor connected with the RSU in the target road where the vehicle is located and the relevant road of the target road where the vehicle is located, the real-time environmental information of the target road where the vehicle is located and the relevant road of the target road where the vehicle is located detected by the RSU is sent outward.

[0019] If the target road where the vehicle is located and the related road of the target road where the vehicle is located do not have a road side sensor coupled with the RSU, no message is sent.

[0020] In some optional embodiments, the cooperative vehicle cruising decision and planning in the parking lot based on the relevant real-time environmental information and the received BSM messages sent by other vehicles include:

[0021] The repeated information in the received BSM messages sent by other vehicles on the target road where the vehicle is located and the related road of the target road where the vehicle is located and the relevant real-time environmental information obtained from the RSU are filtered, and the real-time information of the vehicle obtained from the RSU is filtered, and the filtered information is fused with the information of other vehicles or obstacles detected by the vehicle sensor, and the fused filtered information is finally used as the perception input information.

[0022] The collision time TTC and the distance L between the vehicle and other vehicles or obstacles are calculated by the vehicle AVP controller using the vehicle's own position, vehicle size, acceleration, speed and heading angle in the perception input information, and the coordinates of other vehicles or obstacles, obstacle size, acceleration, speed and heading angle, and the cooperative vehicle cruising decision and planning in the parking lot are performed.

[0023] In some optional embodiments, the collision time TTC and the distance L between the vehicle and other vehicles or obstacles are calculated by the vehicle AVP controller, and the cooperative vehicle cruising decision and planning in the parking lot include:

[0024] When the distance L is less than or equal to the distance threshold L C , or the distance L is greater than the distance threshold L C , and the collision time TTC is less than or equal to the critical collision time TTC C , if the other vehicles or obstacles are in a moving state, the vehicle is controlled to slow down, move aside to avoid or re-plan the global path according to the coordinates of the other vehicles or obstacles, the obstacle size, the heading angle and the target parking lot high-precision map.

[0025] If the other vehicles or obstacles are in a stationary state, the vehicle is controlled to slow down or re-plan the global path according to the coordinates of the other vehicles or obstacles, the obstacle size, the heading angle and the target parking lot high-precision map.

[0026] In some optional embodiments, if the other vehicles or obstacles are in a moving state, the vehicle is controlled to slow down, move aside to avoid or re-plan the global path according to the coordinates of the other vehicles or obstacles, the obstacle size, the heading angle and the target parking lot high-precision map, including:

[0027] If the other vehicle or obstacle is in a moving state, the AVP controller sends a deceleration instruction to the vehicle control system, calculates whether the virtual local path planning of the other vehicle or obstacle conflicts with the current position of the vehicle according to the coordinates of the other vehicle or obstacle, the size of the obstacle, the heading angle, and the high-precision map of the target parking lot, and if there is no path conflict, the vehicle waits in place until the other vehicle or obstacle passes; if the virtual local path planning of the other vehicle or obstacle conflicts with the current position of the vehicle, the vehicle is controlled to move to the side until there is no path conflict, and then waits for the other vehicle or obstacle to pass; if the vehicle cannot be moved to the side to avoid the path conflict, or if the vehicle is moved to the side for a long time, the vehicle is re-planned for a global path.

[0028] In some optional embodiments, if the other vehicle or obstacle is in a stationary state, the vehicle is controlled to decelerate or re-planned for a global path according to the coordinates of the other vehicle or obstacle, the size of the obstacle, the heading angle, and the high-precision map of the target parking lot, including:

[0029] If the other vehicle or obstacle is in a stationary state, the AVP controller sends a deceleration instruction to the vehicle control system, calculates whether the local path planning of the vehicle conflicts with the current position of the other vehicle or obstacle, if there is no conflict, the vehicle is controlled to decelerate and continue to travel according to the current local path planning; if there is a conflict, the vehicle is re-planned for a local path, and the vehicle is controlled to decelerate and continue to travel to bypass the other vehicle or obstacle; if the re-planned local path fails, the vehicle is re-planned for a global path.

[0030] If the other vehicle or obstacle in a stationary state changes to a moving state, whether the local path planning of the vehicle conflicts with the virtual local path planning of the other vehicle or obstacle is calculated according to the coordinates of the vehicle and the other vehicle or obstacle, the heading angle, and the high-precision map of the parking lot: if there is no path conflict, the vehicle is decelerated according to the established local path planning; if there is a conflict, the vehicle waits for a preset time t1, and then re-calculates whether there is a path conflict: if there is no path conflict, the vehicle is decelerated according to the established local path planning; if there is a path conflict, the vehicle is re-planned for a global path.

[0031] In some optional embodiments, the local path of the vehicle refers to a lane-level path planned for the vehicle to bypass or avoid other vehicles or obstacles when the vehicle encounters the other vehicles or obstacles; and the virtual local path planning of the other vehicle or obstacle refers to a local path calculated by the vehicle controller according to the coordinates of the other vehicle or obstacle, the size of the obstacle, the heading angle, and the high-precision map of the parking lot, which is considered by the vehicle to be feasible for the other vehicle or obstacle.

[0032] According to another aspect of the present application, a parking lot cruising system is provided, including:

[0033] A parking lot management system is configured to send a target parking lot high-definition map and a target parking space to a vehicle terminal T-BOX or OBU in response to a vehicle AVP request.

[0034] A roadside sensor is configured to detect road-related real-time environmental information and send the information to an associated RSU.

[0035] An RSU is configured to receive vehicle OBU information and send road-related real-time environmental information about a road where a vehicle is located.

[0036] A single-vehicle intelligent system is configured to complete adaptive cruise control and autonomous lane changing in a parking lot.

[0037] A vehicle terminal decision planning system is configured to calculate a global planning path and a local planning path of a vehicle based on target parking lot high-definition map information and received related real-time environmental information.

[0038] A T-BOX or OBU is configured to send and receive OBU messages.

[0039] A vehicle control system is configured to control vehicle deceleration or acceleration based on instructions from a vehicle terminal decision planning system.

[0040] Overall, the above technical solutions conceived by the present application can achieve the following beneficial effects compared to the prior art:

[0041] (1) The vehicle terminal controller is used for path planning, effectively utilizing the computing power of the vehicle terminal controller, and sending road-related real-time environmental information about a road where a vehicle is located to the vehicle terminal through an RSU, rather than sending all detected real-time messages at all times, thereby reducing the power consumption of the RSU.

[0042] (2) At intersections in a parking lot where the field of view is severely limited, the vehicle can effectively avoid collisions and predict the time when a collision may occur, helping the vehicle make effective driving decisions and path planning. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 is a flowchart of a parking lot cruising method provided by an embodiment of the present application;

[0044] Figure 2 is a related road diagram of a road where a vehicle is located, wherein (a) is a first road condition, (b) is a second road condition, and (c) is a third road condition;

[0045] Figure 3 is a flowchart of intersection collision prediction and decision planning in a parking lot;

[0046] Figure 4 is a schematic diagram of a parking lot cruising system provided by an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not used to limit the present application. In addition, the technical features involved in the various embodiments of the present application described below can be combined with each other as long as there is no conflict.

[0048] In the examples of the present application, "first", "second", and the like are used to distinguish different objects, rather than to describe a specific order or sequence.

[0049] In the embodiments of the present application, the terms are explained as follows:

[0050] T-BOX / OBU-vehicle end communication device

[0051] RSU-roadside unit

[0052] AVP-autonomous valet parking

[0053] V2I-Vehicle to Infrastructure vehicle-to-infrastructure message

[0054] V2V-Vehicle to Vehicle vehicle-to-vehicle communication

[0055] SLAM-simultaneous localization and mapping simultaneous mapping and localization

[0056] BSM-Basic Safety Message basic safety message

[0057] As shown in Figure 1 is a flowchart of a parking lot cruising method provided by an embodiment of the present application, and in the method shown in Figure 1 includes the following steps:

[0058] S1: obtaining a high-precision map of a target parking lot and a target parking space in the target parking lot, and planning a global path based on the high-precision map of the target parking lot and the target parking space in the target parking lot;

[0059] S2: obtaining relevant real-time environmental information of a road where the vehicle is located sent by a roadside unit RSU in the target parking lot;

[0060] S3: based on the relevant real-time environmental information and the received BSM messages sent by other vehicles, making a cruising decision and planning in the parking lot.

[0061] In the embodiment of the present application, in step S1, after the user starts the vehicle AVP function and gets off the vehicle, the vehicle controller sends an information request through the T-BOX or OBU and receives the parking lot high-precision map and the target parking space issued by the parking lot, and the vehicle controller plans an available optimal global path according to the self-coordinate, the target parking space coordinate and the high-precision map, which specifically includes the following steps:

[0062] S11: Target parking lot selection;

[0063] After the vehicle starts the AVP function, the car machine should display the target area where the AVP autonomous valet parking function can be started, and the vehicle can perform the AVP parking after driving into the target area range;

[0064] After the vehicle starts the AVP function, the user can manually select the target parking lot nearby on the mobile phone, or can select the target parking lot recommended by the AVP system by default, and the target parking lot recommended by the AVP system by default can consider the parking fee and the time spent to reach as the cost function;

[0065] When the vehicle is in the target area where the AVP function can be performed, and after the parking lot is selected, the vehicle requests the target parking lot to send the high-precision map and the target parking space, and the corresponding parking lot management system receives the request, registers the vehicle, and issues the target parking lot high-precision map and the target parking space, and the vehicle receives the target parking lot high-precision map through the T-BOX or OBU, and by default caches the high-precision map, and locates the vehicle in the target parking lot high-precision map according to the GNSS or SLAM positioning technology, wherein the target parking lot high-precision map should include the target parking lot area and the target area where the AVP function can be started;

[0066] When the vehicle is in the target area where the AVP function can be performed, and after the parking lot is selected, the vehicle AVP system can also automatically search for the high-precision map of the selected target parking lot in the cache area, and if the high-precision map of the target parking lot is searched, the high-precision map version information is verified with the parking lot management system, and it is judged whether it needs to be updated;

[0067] The user can also manually select to delete the target parking lot high-precision map in the cache area to release the cache space;

[0068] When the vehicle obtains the target parking lot high-precision map, the parking lot management system issues the available target parking space.

[0069] S12: Target parking space selection;

[0070] The target parking space is issued by the parking lot management system according to the target parking lot space occupation situation, and the vehicle owner can also select the target parking space according to the optional parking space provided by the parking lot management system on the mobile phone, and the selected target parking space contains the target parking space coordinate, and the vehicle can automatically drive to the vicinity of the coordinate to complete the subsequent automatic parking operation.

[0071] S13: The vehicle plans a global path;

[0072] The vehicle controller can plan a drivable global path according to the self coordinates, the target parking space coordinates and the high-definition map.

[0073] In the embodiments of the present application, any algorithm for global path planning can be selected for global path planning, and the embodiments of the present application do not limit the global path planning algorithm. For example, the vehicle can determine whether the planned global path is available by means of the obstacle occupancy road information sent by the RSU, and if the global path is not available, the vehicle re-plans another global path.

[0074] In the embodiments of the present application, in step S2, during the process of starting the AVP function of the vehicle, the laser SLAM or visual SLAM technology is used to position the vehicle itself, the vehicle BSM message is sent to the outside through the T-BOX or OBU, and the RSU determines whether to send the real-time environmental information detected by the sensor connected thereto to the outside according to the vehicle BSM information, which includes the following steps:

[0075] S21: Obtain self positioning of the vehicle;

[0076] During the process of starting the AVP function of the vehicle, the laser SLAM or visual SLAM technology is used to position the vehicle itself in real time, and the vehicle BSM message is sent to the outside through the T-BOX at a fixed frequency. The receiving party can be other vehicles loaded with the T-BOX or OBU or the RSU. The BSM information at least includes the vehicle positioning information, the vehicle size, the acceleration, the speed, the heading angle and the like.

[0077] S22: The RSU sends the related real-time environmental information of the target road where the vehicle is located to the outside;

[0078] If the RSU receives the BSM message sent by the vehicle, the BSM message is analyzed to determine whether to send the related real-time environmental information of the target road where the vehicle is located to the outside. The vehicle can receive the related real-time environmental information of the target road where the vehicle is located sent by the RSU through the T-BOX or OBU. If the RSU does not receive any BSM message sent by the vehicle, the related real-time environmental information of the target road where the vehicle is located does not need to be sent to the outside to reduce power consumption. The related real-time environmental information of the target road where the vehicle is located refers to the real-time environmental information detected by the roadside sensor on the target road where the vehicle is located and the related road of the target road where the vehicle is located. The roadside sensor is not limited to the laser radar, camera, millimeter wave radar and the like.

[0079] Wherein, in order to facilitate the description of the relevant road of the target road where the vehicle is located, as an illustration: the vehicle is located on the target road corresponding to the vehicle's own position in the high-definition map, and then according to the comparison between the heading angle and the road heading angle, the driving direction of the vehicle on the target road is judged, and according to the simple road topological relationship stored in the RSU, it can be judged which road is the relevant road of the target road where the vehicle is located: connected with the target road where the vehicle is located, and in the direction of vehicle advancement, defined as the relevant road of the target road where the vehicle is located, such as Figure 2 As shown, including Figure 2 (a) in the first road condition, (b) in the second road condition, (c) in the third road condition, three conditions. After determining the relevant road of the target road where the vehicle is located, the RSU can judge whether there is a roadside sensor connected with the RSU on the target road where the vehicle is located and the relevant road of the target road where the vehicle is located according to the vehicle positioning message received in the BSM message, the stored target road and relevant road coordinates, and the roadside sensor coordinates connected with the RSU, and if there is a roadside sensor connected with the RSU on the target road where the vehicle is located and the relevant road of the target road where the vehicle is located, the relevant real-time environmental information of the target road where the vehicle is located is sent out; if not, no message is sent, which can further reduce the power consumption of the RSU, wherein the method for judging whether there is a roadside sensor connected with the RSU on the target road where the vehicle is located and the relevant road of the target road where the vehicle is located includes: each RSU stores the coordinate information of the roadside sensor connected with the RSU, and only needs to calculate whether the coordinates of the roadside sensor connected with the RSU coincide with the target road where the vehicle is located and the relevant road of the target road where the vehicle is located, that is, whether there is a roadside sensor connected with the RSU on the target road where the vehicle is located and the relevant road of the target road where the vehicle is located.

[0080] Wherein, the real-time environmental information at least includes obstacle information, and the obstacle information at least includes obstacle coordinates, obstacle size, acceleration, speed, heading angle and other information, and the obstacles include vehicles, pedestrians or other obstacles on the relevant road.

[0081] In the embodiment of the application, in step S3, at the intersection in the parking lot where the field of view is severely limited, the vehicle itself often cannot identify or identify the approaching vehicles, pedestrians and other obstacles on the adjacent road in time, and the V2I and V2V messages received by the vehicle as over-distance sensor information can effectively help the vehicle to avoid collision and predict the time when the collision may occur, help the vehicle to make effective driving decisions and path planning, and the target intersection in the parking lot is mainly Figure 2 The intersection type shown in the figure, the V2V message is the BSM message sent by the vehicle to the vehicle, and the V2I message is the relevant real-time environmental information of the target road where the vehicle is located sent by the RSU to the vehicle, which specifically includes the following steps:

[0082] S31: Filtering V2I and V2V messages, which can be achieved by the following steps:

[0083] S311: When there are other vehicles sending BSM messages on the target road where the vehicle is located and the related roads of the target road where the vehicle is located, and the vehicle receives the BSM messages of the other vehicles, if the sensors on the target road where the vehicle is located and the related roads of the target road where the vehicle is located also detect the other vehicles, the RSU will also send the real-time information of the other vehicles to the outside, and the vehicle receives the real-time message. At this time, the two messages are duplicate information, and need to be filtered first. For example, by calculating the coordinates and heading angles of the vehicles in the two message contents, if they are both less than a certain small threshold, it is judged that they are the same other vehicle, and only the average of the two messages is taken for the next step of calculation;

[0084] S312: When there are other vehicles or obstacles that do not send BSM messages on the target road where the vehicle is located and the related roads of the target road where the vehicle is located, the sensors on the target road where the vehicle is located and the related roads of the target road where the vehicle is located will detect the other vehicles or obstacles. The RSU will send the real-time information of the other vehicles or obstacles to the outside, and the vehicle receives the real-time message. At this time, the message is unique and does not need to be filtered;

[0085] S313: The sensors on the target road where the vehicle is located will also detect the vehicle, and the vehicle will receive the real-time information of the vehicle sent by the RSU to the outside. Filtering calculation is needed to filter the vehicle. For example, by calculating the coordinates and heading angles of the vehicles in the V2I message content and comparing them with the coordinates and heading angles of the vehicle, if they are both less than a certain small threshold, it is judged that they are the same vehicle, and the V2I message is ignored and the next step of calculation of the V2I message is not performed.

[0086] The filtered V2I and V2V messages need to be fused with the other vehicle or obstacle information detected by the single-vehicle intelligent sensor of the vehicle for final fusion and filtering of the messages as the perception input information of step S32.

[0087] S32: Intersection collision prediction and decision planning in the target parking lot;

[0088] After filtering the V2I and V2V messages and finally fusing the information detected by the single-vehicle intelligent sensor of the vehicle, the AVP controller computing unit of the vehicle can calculate the time-to-collision TTC and the distance L between the vehicle and other vehicles or obstacles, using the information such as the coordinates, size, acceleration, speed, and heading angle of the vehicle and the information such as the coordinates, size, acceleration, speed, and heading angle of other vehicles or obstacles. Generally, the vehicle only needs to start the adaptive cruise function and the autonomous lane-changing function, and use the single-vehicle intelligent technology to complete most of the cruising in the parking lot, such as Figure 3 When the vehicle is at an intersection, as shown in Figure 2 If one of the following two conditions occurs:

[0089] I. The distance L is less than or equal to the distance threshold L C ;

[0090] II. The distance L is greater than the distance threshold L C , and the time-to-collision TTC is less than or equal to the critical time-to-collision TTC C , then:

[0091] (1) If the other vehicle or obstacle is in a moving state: the AVP controller sends a deceleration instruction to the vehicle control system to control the vehicle to decelerate or brake to a stop. According to the coordinates, size, heading angle of the other vehicle or obstacle, and high-precision map of the parking lot, the AVP controller calculates whether the virtual local path planning of the other vehicle or obstacle conflicts with the current position of the vehicle. If there is no path planning conflict, the vehicle waits in place for the other vehicle or obstacle to pass; if there is a conflict between the virtual local path planning of the other vehicle or obstacle and the current position of the vehicle, the vehicle moves to the side until there is no path conflict, and then waits for the other vehicle or obstacle to pass. If the vehicle cannot move to the side to avoid the path conflict, or if the vehicle moves to the side and times out, the vehicle re-plans a global path.

[0092] (2) If the other vehicle or obstacle is in a stationary state, the AVP controller sends a deceleration instruction to the vehicle control system to control the vehicle to decelerate. The AVP controller calculates whether the local path planning of the vehicle conflicts with the current position of the other vehicle or obstacle. If there is no conflict, the vehicle continues to travel at a lower speed according to the planned local path. If there is a conflict, the vehicle re-plans a local path and continues to travel at a lower speed to bypass the other vehicle or obstacle. If the re-planned local path fails, the vehicle re-plans a global path.

[0093] If the other vehicles or obstacles in static state change to static state, according to the information of the vehicle and the other vehicles or obstacles coordinates, heading angle, parking lot high-precision map, etc., whether the local path planning of the vehicle and the virtual local path planning of the other vehicles or obstacles conflict is calculated: if there is no path conflict, the vehicle continues to travel at low speed according to the established local planning path; if there is conflict, wait for a preset time t1, and re-calculate whether there is path conflict, if there is no path conflict, the vehicle continues to travel at low speed according to the established local planning path, if there is path conflict, the vehicle re-plans the global path.

[0094] Wherein, the global path refers to a path with a navigation route planned between the vehicle and the destination; and the local path refers to a lane-level path planned to bypass or avoid other vehicles or obstacles when the vehicle encounters other vehicles or obstacles.

[0095] Wherein, the virtual local path planning of the other vehicles or obstacles refers to a local path calculated by the vehicle controller according to the coordinates of the other vehicles or obstacles, the size of the obstacles, the heading angle, the parking lot high-precision map and other information, which is considered feasible by the vehicle.

[0096] Wherein, the moving state refers to a speed exceeding a certain speed threshold, and the static state refers to a speed lower than a certain speed threshold, and the speed threshold can be calibrated to a certain decimal value, and the above threshold L C , the critical collision time TTC C and the waiting time t1 are all calibrated values.

[0097] As another embodiment, as Figure 4 shown is a schematic diagram of a parking lot cruising system provided by an embodiment of the application, which comprises:

[0098] Parking lot management system: in response to the vehicle AVP request, sends the target parking lot high-precision map and the target parking space to the vehicle end T-BOX or OBU;

[0099] Roadside sensor: detects the real-time environmental information related to the road and sends it to the associated RSU;

[0100] RSU: receives the vehicle OBU information and sends the real-time environmental information related to the target road where the vehicle is located;

[0101] Single vehicle intelligent system: completes adaptive cruise function, autonomous lane changing function, etc. in the target parking lot;

[0102] Vehicle end decision planning system: calculates the global planning path and the local planning path of the vehicle according to the target parking lot high-precision map information and the received real-time environmental information;

[0103] T-BOX or OBU: send and receive OBU messages;

[0104] Vehicle control system: control the vehicle to decelerate or accelerate according to the instruction of the vehicle end decision planning system.

[0105] The specific implementation of each component can refer to the description of the above method embodiments, and the embodiments of the present application will not be repeated.

[0106] It should be noted that, according to the needs of implementation, each step / component described in the present application can be split into more steps / components, or two or more steps / components or part of the operation of the steps / components can be combined into a new step / component, to achieve the purpose of the present application.

[0107] Those skilled in the art can easily understand that the above description is only a preferred embodiment of the present application, and is not intended to limit the present application, and any modification, equivalent replacement and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method of patrolling a parking lot, characterized by, The application relates to a method for planning a global path for a vehicle in a parking lot, and the method comprises the following steps: acquiring a high-definition map of a target parking lot and a target parking space in the target parking lot, and planning a global path based on the high-definition map of the target parking lot and the target parking space in the target parking lot; acquiring relevant real-time environmental information of a road where the vehicle is located and which is sent by a road side unit (RSU) in the target parking lot; based on the relevant real-time environmental information and a basic safety message (BSM) message sent by other vehicles, making a cooperative cruise decision and planning for the vehicle in the parking lot; the step of acquiring the relevant real-time environmental information of the road where the vehicle is located and which is sent by the RSU in the target parking lot comprises the following steps: acquiring a vehicle position, determining a target road where the vehicle is located, and sending a BSM message of the vehicle outward at a fixed frequency, so that the RSU parses the vehicle position in the BSM message, positions the vehicle on the target road corresponding to the vehicle position in the high-definition map, compares a heading angle of the vehicle with a heading angle of the target road to determine a driving direction of the vehicle on the target road, determines relevant roads of the target road based on a pre-stored road topology relationship in the RSU, wherein the relevant roads are connected with the target road and are in a driving direction of the vehicle, determines whether the target road and the relevant roads of the target road have a road side sensor connected with the RSU based on the vehicle position, the target road and the relevant road coordinates in the received BSM message and a road side sensor coordinate connected with the RSU, and sends real-time environmental information detected by the target road and the relevant roads of the target road to the outside if the target road and the relevant roads of the target road have the road side sensor connected with the RSU, and does not send any message if the target road and the relevant roads of the target road do not have the road side sensor connected with the RSU; acquiring the real-time environmental information detected by the target road and the relevant roads of the target road and sent by the RSU.

2. The method of claim 1, wherein, the step of acquiring the high-definition map of the target parking lot and the target parking space in the target parking lot, and planning the global path based on the high-definition map of the target parking lot and the target parking space in the target parking lot comprises the following steps: after starting an AVP function, displaying a target area where the AVP autonomous guest parking function can be performed; after the vehicle is in the target area where the AVP function can be performed and a target parking lot is selected, acquiring the high-definition map of the target parking lot and the target parking space; positioning the vehicle to the high-definition map of the target parking lot according to the high-definition map of the target parking lot, and then planning the global path based on the vehicle position and the target parking space.

3. The method of claim 2, wherein, the step of making the cooperative cruise decision and planning for the vehicle in the parking lot based on the relevant real-time environmental information and the BSM message sent by other vehicles comprises the following steps: Filtering repeated information in the received BSM messages sent by other vehicles on the target road where the vehicle is located and the related road of the target road where the vehicle is located and the related real-time environmental information obtained from the RSU, filtering real-time information of the vehicle obtained from the RSU, and fusing the filtered information with other vehicle or obstacle information detected by the vehicle sensor to obtain perception input information; Using the vehicle's own position, vehicle size, acceleration, speed and heading angle in the perception input information, and the coordinates, obstacle size, acceleration, speed and heading angle of other vehicles or obstacles, the vehicle AVP controller calculates the collision time TTC and the distance L between the vehicle and other vehicles or obstacles, and cooperates with the vehicle to make decisions and plan the cruise in the parking lot.

4. The method of claim 3, wherein, The TTC and the distance L between the vehicle and other vehicles or obstacles calculated by the vehicle AVP controller, and the cruise decision and planning of the vehicle in the parking lot, comprise: When the separation distance L is less than or equal to the distance threshold L C , or the separation distance L is greater than the distance threshold L C , and the collision time TTC is less than or equal to the critical collision time TTC C , if the other vehicle or the obstacle is in a moving state, the vehicle is controlled to decelerate, move away to avoid, or re-plan a global path according to the other vehicle or obstacle coordinates, the obstacle size, the heading angle, and the target parking lot high-definition map. If the other vehicle or obstacle is in a static state, the vehicle is controlled to slow down or re-plan a global path according to the coordinates, obstacle size, heading angle and target parking lot high-precision map of the other vehicle or obstacle.

5. The method of claim 4, wherein, If the other vehicle or obstacle is in a static state, the vehicle is controlled to slow down or re-plan a global path according to the coordinates, obstacle size, heading angle and target parking lot high-precision map of the other vehicle or obstacle. If the other vehicle or obstacle is in a static state, the vehicle is controlled to slow down or re-plan a global path according to the coordinates, obstacle size, heading angle and target parking lot high-precision map of the other vehicle or obstacle.

6. The method of claim 5, wherein, If the other vehicle or obstacle is in a static state, the vehicle is controlled to slow down or re-plan a global path according to the coordinates, obstacle size, heading angle and target parking lot high-precision map of the other vehicle or obstacle. If the other vehicle or obstacle is in a static state, the vehicle is controlled to slow down or re-plan a global path according to the coordinates, obstacle size, heading angle and target parking lot high-precision map of the other vehicle or obstacle. If the other vehicle or obstacle is in a static state, the vehicle is controlled to slow down or re-plan a global path according to the coordinates, obstacle size, heading angle and target parking lot high-precision map of the other vehicle or obstacle. If the other vehicle or obstacle in static state is in moving state and becomes static state, according to the coordinates, heading angle and high-precision parking lot map of the vehicle and the other vehicle or obstacle, it is calculated whether the local path planning of the vehicle and the virtual local path planning of the other vehicle or obstacle conflict: if there is no path conflict, the vehicle travels at a predetermined speed according to the planned local path; if there is a conflict, the vehicle waits for a preset time t1, and then re-calculates whether there is a path conflict: if there is no path conflict, the vehicle travels at a predetermined speed according to the planned local path; if there is a path conflict, the vehicle re-plans a global path.

7. The method according to claim 5 or 6, characterized in that, The local path of the vehicle refers to the lane-level path planned by the vehicle to bypass or avoid other vehicles or obstacles when the vehicle encounters other vehicles or obstacles; the virtual local path planning of the other vehicle or obstacle refers to the local path calculated by the vehicle controller according to the coordinates, size, heading angle and high-precision parking lot map of the other vehicle or obstacle, which is considered feasible by the vehicle.

8. A parking lot cruising system characterized by comprising: Comprise: A parking lot management system for sending target parking lot high-precision map and target parking space to vehicle terminal T-BOX or OBU in response to vehicle AVP request; A roadside sensor for detecting road-related real-time environmental information and sending it to an associated RSU; An RSU for receiving vehicle OBU information and sending road-related real-time environmental information where the vehicle is located; A single-vehicle intelligent system for completing adaptive cruise control and autonomous lane changing in a parking lot; A vehicle terminal decision planning system for calculating a global planning path and a local planning path of a vehicle according to target parking lot high-precision map information and received related real-time environmental information; A T-BOX or OBU for sending and receiving OBU messages; A vehicle control system for controlling the vehicle to slow down or speed up according to the instructions of the vehicle terminal decision planning system; The RSU for receiving vehicle OBU information and sending road-related real-time environmental information where the vehicle is located, specifically comprising: The vehicle's own position is acquired, a target road where the vehicle is located is determined, and vehicle BSM messages are sent out at a fixed frequency, so that the RSU parses the vehicle's own position in the BSM messages, positions the vehicle on the target road corresponding to the vehicle's own position in the high-precision map, compares the vehicle heading angle with the target road heading angle to determine the driving direction of the vehicle on the target road, determines the related road of the target road where the vehicle is located according to the pre-stored road topological relationship in the RSU, wherein the related road is connected with the target road where the vehicle is located and is in the driving direction of the vehicle; after the related road of the target road where the vehicle is located is determined, the RSU determines whether there is a roadside sensor connected with the RSU on the target road where the vehicle is located and the related road of the target road where the vehicle is located according to the vehicle's own position, the target road and the related road coordinates in the received BSM messages and the roadside sensor coordinates connected with the RSU; if there is a roadside sensor connected with the RSU on the target road where the vehicle is located and the related road of the target road where the vehicle is located, real-time environmental information detected by the target road where the vehicle is located and the related road of the target road where the vehicle is located is sent out; if there is no roadside sensor connected with the RSU on the target road where the vehicle is located and the related road of the target road where the vehicle is located, no message is sent.

Images