Driving control methods, devices, and autonomous vehicles

Abstract

This application relates to the field of autonomous vehicle technology, and provides a driving control method, device, and autonomous vehicle. The method includes: determining the preset parking point type and the target area where the autonomous vehicle can park based on the target location input by the user and a pre-stored high-precision map; generating multiple candidate parking points within the target area; determining the target parking point from all candidate parking points based on the target location and the locations of each candidate parking point; and controlling the autonomous vehicle to travel from the current location to the target parking point. Using this method can improve the parking efficiency of autonomous vehicles.

Description

Technical Field

[0001] This application belongs to the field of unmanned vehicle technology, and in particular relates to a driving control method, device and unmanned vehicle. Background Technology

[0002] With the development of autonomous driving technology, driverless cars are widely used in various application scenarios (such as passenger transport). When used in passenger transport, driverless cars typically automatically drive to the destination location entered by the passenger after picking them up. However, since the destination location entered by the passenger may not allow for long-term parking, driverless cars often need to change parking areas after reaching the destination.

[0003] There are generally two ways for driverless cars to change parking areas: one is to manually control the driverless car to change parking areas remotely; the other is for the driverless car to automatically drive back to the preset parking lot to park. Both of these methods result in low parking efficiency for driverless cars. Summary of the Invention

[0004] This application provides a driving control method, device, and unmanned vehicle, which can solve the problem of low parking efficiency of unmanned vehicles.

[0005] In a first aspect, embodiments of this application provide a driving control method for an unmanned vehicle, the method comprising:

[0006] Based on the user-input target location and pre-stored high-precision maps, the system determines the preset parking point type and the target area where the autonomous vehicle can park.

[0007] Generate multiple candidate parking spots within the target area;

[0008] Based on the target location and the locations of each candidate parking spot, the target parking spot is determined from all candidate parking spots;

[0009] Control the unmanned vehicle to travel from its current location to the target parking point.

[0010] Secondly, embodiments of this application provide a driving control device for an unmanned vehicle, the device comprising:

[0011] The first determining module is used to determine the preset parking point type and the target area where the unmanned vehicle can park, based on the target location input by the user and the pre-stored high-precision map.

[0012] The parking spot generation module is used to generate multiple candidate parking spots within a target area;

[0013] The second determining module is used to determine the target parking point from all candidate parking points based on the target location and the locations of each candidate parking point;

[0014] The control module is used to control the unmanned vehicle to move from its current location to the target parking point.

[0015] Thirdly, embodiments of this application provide an unmanned vehicle, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method described in the first aspect above.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0017] Fifthly, embodiments of this application provide a computer program product that, when run on an unmanned vehicle, causes the unmanned vehicle to execute the method described in the first aspect.

[0018] The advantages of this application compared to existing technologies are as follows: Based on a preset parking spot type and the user-input target location, a target area for parking the autonomous vehicle is determined. Then, multiple candidate parking spots are generated within the target area, and the target parking spot is determined from these candidate spots based on the target location and the location of each candidate parking spot. Finally, the autonomous vehicle is controlled to move from its current location to the target parking spot. Therefore, when parking the autonomous vehicle, not only can a target parking area be automatically determined in the surrounding environment based on the selected preset parking spot type and target location, but multiple candidate parking spots can also be generated within the target area. In other words, this solution can automatically control the autonomous vehicle to park at a suitable candidate parking spot by combining multiple factors such as the user-input target location and the locations of candidate parking spots. Compared to methods that require manual remote control of the autonomous vehicle's parking or forcing the autonomous vehicle to return to a preset parking lot, this improves the parking efficiency of the autonomous vehicle. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the implementation of a driving control method for an unmanned vehicle according to an embodiment of this application.

[0021] Figure 2 This is a schematic diagram illustrating an application scenario for generating candidate parking points according to an embodiment of this application.

[0022] Figure 3 This is a schematic diagram of an application scenario for generating candidate parking points provided in another embodiment of this application;

[0023] Figure 4 This is a schematic diagram illustrating one implementation method for determining a target parking point in a driving control method for an unmanned vehicle provided in an embodiment of this application;

[0024] Figure 5 This is a schematic diagram of an application scenario for determining available parking spots provided in one embodiment of this application;

[0025] Figure 6 This is a schematic diagram of an application scenario for determining available parking spots provided in another embodiment of this application;

[0026] Figure 7 This is a schematic diagram of an application scenario provided in one embodiment of this application when driving to a target parking point;

[0027] Figure 8 This is a schematic diagram of the structure of a driving control device for an unmanned vehicle provided in one embodiment of this application;

[0028] Figure 9 This is a schematic diagram of the structure of an unmanned vehicle provided in one embodiment of this application. Detailed Implementation

[0029] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0030] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0031] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0032] Currently, for driverless vehicles used in passenger transport scenarios, there may be situations where the destination location input by the passenger cannot be used for extended periods. Therefore, driverless vehicles often need to change parking areas after reaching the destination. However, the methods for changing parking areas are usually either manually controlled remotely or the driverless vehicle automatically drives back to a pre-set parking lot, resulting in low parking efficiency for driverless vehicles.

[0033] Therefore, to improve the parking efficiency of autonomous vehicles, this application provides a driving control method for autonomous vehicles, which can be applied to the driving control device of an autonomous vehicle. The driving control device can be installed inside the autonomous vehicle or installed outside the autonomous vehicle and connected to it. In specific applications, for example, the driving control device of the autonomous vehicle can be a controller.

[0034] Please see Figure 1 , Figure 1 The following is a flowchart illustrating the implementation of a driving control method for an unmanned vehicle according to an embodiment of this application. The method includes the following steps:

[0035] S101. Based on the target location input by the user and the pre-stored high-precision map, determine the preset parking point type and the target area where the unmanned vehicle can park.

[0036] In one embodiment, the aforementioned user is typically the service recipient of the autonomous vehicle, such as a passenger riding in the vehicle. The target location is the location the autonomous vehicle needs to reach. It should be noted that this target location may not be suitable for parking; therefore, the autonomous vehicle typically parks in a parking area within a certain range from the target location, or initially parks in a temporary parking space, and then proceeds to a parking area after the user disembarks. Based on this, the parking area can be considered the aforementioned target area. The specific range of the target area can be determined in advance by staff and is not limited thereto.

[0037] In one embodiment, the aforementioned preset parking spot type can be determined in advance by the staff of the unmanned vehicle and input into the driving control device.

[0038] For example, after obtaining the target location, the driving control device can provide the staff with the parking spot types corresponding to various parking areas within the target range based on a pre-stored high-precision map. The staff then selects the preset parking spot type from among the multiple parking spot types. Alternatively, the driving control device can input the target location into a server, which then provides the staff with the parking spot types corresponding to various parking areas within the target range based on a pre-stored high-precision map. Finally, the staff selects the preset parking spot type from among the multiple parking spot types and sends it to the driving control device. This process is not limited.

[0039] In another embodiment, after obtaining the target location, the driving control device can also randomly select a preset parking spot type from the parking spot types corresponding to various parking areas within the target range at the target location, based on a pre-stored high-precision map; or, it can select the parking spot type corresponding to the nearest parking area within the target range at the target location as the preset parking spot type. Then, all parking areas within the target range that match the preset parking spot type are determined as the target area. In this embodiment, the method for determining the preset parking spot type is not limited.

[0040] In one embodiment, when the parking area is a roadside curb, the preset parking point type can be the type of parking on the curb; when the parking area is a roadside parking space or a parking space in a parking lot, the preset parking point type can be the type of parking in the parking space, and there is no limitation on this.

[0041] The high-precision map typically includes, but is not limited to, information such as lanes, lane curbs, and parking areas. Furthermore, when acquiring the preset parking point type, the driving control device can also simultaneously acquire the distance between the autonomous vehicle and reference points when parking. These reference points include, but are not limited to, lane boundaries, curbs, parking space boundaries, and obstacles.

[0042] S102. Generate multiple candidate parking spots within the target area.

[0043] In one embodiment, the target area can be a roadside area, which includes a curb. The curb can be a straight curb, or a curb with a corner or curvature; there is no limitation in this regard.

[0044] In one embodiment, the target area may also be a non-roadside area including at least one pre-planned parking area. Specifically, this parking area may be a parking space. It should be noted that this parking space may be a parking space within a parking lot or a parking space on the road; there is no limitation in this regard.

[0045] In one embodiment, the candidate parking spots are multiple parking locations within the target area. When generating candidate parking spots, different generation methods are typically used for target areas with different preset parking types.

[0046] For example, when the target area is a roadside area, the driving control device can generate multiple first candidate parking points along the roadside area and generate multiple second candidate parking points corresponding to the first candidate parking points respectively; wherein, there is a first preset distance between each two adjacent first candidate parking points, the line connecting each first candidate parking point and the corresponding second candidate parking point is perpendicular to the roadside, and there is a second preset distance between each first candidate parking point and the corresponding second candidate parking point.

[0047] When generating the first candidate parking spot, one first candidate parking spot can be generated at a first preset distance. Then, for any first candidate parking spot, a second candidate parking spot is generated at a second preset distance. Furthermore, the line connecting the generated first and second candidate parking spots should be perpendicular to the curb. The first and second preset distances can be pre-set by staff and are not limited in scope.

[0048] Specifically, refer to Figure 2 , Figure 2 This is a schematic diagram illustrating an application scenario for generating candidate parking points according to an embodiment of this application. Here, d1 can be considered as a first preset distance, and d2 can be considered as a second preset distance. It should be noted that... Figure 2 Only one set of second candidate parking spots is shown. In a real-world scenario, there can be multiple sets of second candidate parking spots, each set separated from its adjacent set by a second preset distance. Furthermore, from... Figure 2 It can be seen that the dashed line represented by d2 should be perpendicular to the curb.

[0049] In another embodiment, when the target area is a non-roadside area and includes at least one pre-planned parking area, for any parking area, the driving control device can generate multiple third candidate parking points along the first boundary line of the parking area, and generate multiple fourth candidate parking points corresponding to the third candidate parking points along the second boundary line parallel to the first boundary line, and generate multiple fifth candidate parking points between each third candidate parking point and its corresponding fourth candidate parking point; each pair of adjacent third candidate parking points is spaced by a third preset distance, the line connecting each third candidate parking point and its corresponding fourth candidate parking point is perpendicular to the first boundary line, and each pair of adjacent fifth candidate parking points is spaced by a fourth preset distance.

[0050] Specifically, for a pre-planned parking area, it is typically a rectangular parking area enclosed by four boundary lines. In this case, the driving control device can select any two parallel boundary lines as the first and second boundary lines, without limitation. When multiple fifth candidate parking points are generated between a third candidate parking point and its corresponding fourth candidate parking point, adjacent fifth candidate parking points are spaced apart by a fourth preset distance. Similarly, a fifth candidate parking point should also be spaced apart by a fourth preset distance from an adjacent third candidate parking point or an adjacent fourth candidate parking point.

[0051] Specifically, refer to Figure 3 , Figure 3 This is a schematic diagram illustrating an application scenario for generating candidate parking points, provided in another embodiment of this application. Here, d3 can be considered as the third preset distance, and d4 can be considered as the fourth preset distance. Figure 3 The boundary line where the third candidate parking spot is located is the first boundary line, and Figure 4 The boundary line where the fourth candidate parking point is located is the second boundary line, and the distance between it and the adjacent fifth candidate parking point should also be the fourth preset distance.

[0052] The third and fourth preset distances can be set in advance by staff, and the third and fourth preset distances can be the same or different, without limitation.

[0053] S103. Based on the target location and the locations of each candidate parking point, determine the target parking point from all candidate parking points.

[0054] In one embodiment, when determining the target parking point, the candidate parking point closest to the target location can be determined as the target parking point to reduce the distance that the autonomous vehicle needs to travel.

[0055] Specifically, refer to Figure 4 The driving control device can be specifically controlled through, for example... Figure 4 The S401-S403 diagram shows the target parking point, detailed below:

[0056] S401. Determine the type of each candidate parking spot based on the target location and target area.

[0057] In application, the above-mentioned candidate parking spot types include a first preset type where the candidate parking spot is located where there are no obstacles, and a second preset type where the candidate parking spot is located where there are obstacles.

[0058] Since the target area can be divided into roadside areas and off-road areas, the method for determining the type of candidate parking spot usually differs for different target areas.

[0059] Specifically, when the target area is a roadside area, the driving control device can determine the type of the candidate parking point as a first preset type when there is no first obstacle within the first preset range corresponding to the target location; and when there is a first obstacle within the first preset range corresponding to the target location, it can determine the type of the candidate parking point as a second preset type.

[0060] In one embodiment, the first preset range can be pre-set by staff according to the actual situation, and there is no limitation thereto. It should be noted that autonomous vehicles are typically equipped with sensing devices, and the sensing range of these devices is usually much larger than the first preset range. Therefore, the autonomous vehicle can also sense the first preset range corresponding to the target location even before reaching the target location. In this embodiment, there are no limitations on the sensing devices or the method by which they sense the first obstacle.

[0061] In one embodiment, the first obstacle may be a person, a parked vehicle, or other types of objects. In this embodiment, the type of the first obstacle is not limited.

[0062] It should be added that when the target area is a non-roadside area and the target area includes at least one pre-planned parking area, if it is determined that there is no first obstacle in the parking area closest to the target location, the driving control device can determine that the type of the candidate parking point is a first preset type; and if it is determined that there is a first obstacle in the parking area closest to the target location, the type of the candidate parking point is determined to be a second preset type.

[0063] In one embodiment, as described in S101 above, the driving control device can pre-store a high-precision map. Therefore, the driving control device can determine the parking area closest to the target location based on the location of each parking area in the high-precision map. Simultaneously, the autonomous vehicle's sensing devices detect whether a first obstacle exists within the parking area closest to the target location.

[0064] It should be added that when it is determined that there is no first obstacle in the parking area closest to the target location, the driving control device can determine that the type of each parking candidate point in all parking areas is the first preset type; otherwise, it determines that the type of all parking candidate points is the second preset type.

[0065] S402. Determine the first distance between the candidate parking spot and the target location.

[0066] S403. Determine the target parking point from all candidate parking points based on the type of candidate parking point and the first distance.

[0067] In one embodiment, after generating each candidate parking spot, the driving control device can determine the location of each candidate parking spot in the high-precision map based on the high-precision map, and then calculate a first distance between each candidate parking spot and the target location. Then, based on the type of the candidate parking spot and the first distance, the target parking spot is determined.

[0068] As explained above, candidate parking spots may be roadside parking spots or parking spots in pre-planned parking areas, and the types of candidate parking spots are also divided into a first preset type and a second preset type. Therefore, when determining the target parking spot, it can be divided into the following scenarios: the first case where the target area is a roadside area and the candidate parking spot type is also of the first preset type; the second case where the target area is a roadside area and the candidate parking spot type is also of the second preset type; the third case where the target area is a non-roadside area (pre-planned parking area) and the candidate parking spot type is also of the first preset type; and the fourth case where the target area is a non-roadside area and the candidate parking spot type is also of the second preset type. However, for the above multiple scenarios, the driving control device also needs to implement different strategies to determine the target parking spot.

[0069] Specifically, for the target area being a roadside area and the candidate parking spot being of the first preset type, the following scenario applies:

[0070] For any candidate parking spot, if there is no second obstacle in the target direction of the candidate parking spot that is less than a fifth preset distance from the candidate parking spot, the driving control device can determine the candidate parking spot as an available parking spot; the target direction is the same as the forward direction of the unmanned vehicle; then, the available parking spot with the smallest first distance from the target position is determined as the target parking spot.

[0071] In one embodiment, when the type of each candidate parking spot is determined to be a first preset type, it means that there is no first obstacle within a first preset range of the target location. Therefore, when the parking spot closest to the target location is chosen as the target parking spot, the required driving distance for the autonomous vehicle is usually the shortest. The aforementioned fifth preset distance can be set by staff and is not limited thereto.

[0072] It should be noted that, under normal circumstances, even if there is a second obstacle in the target direction of the candidate parking point that is less than the second preset distance from the candidate parking point, the autonomous vehicle can still park at the candidate parking point. However, it should be added that after the autonomous vehicle parks at the target parking point, the ease with which the autonomous vehicle leaves the target parking point should also be considered.

[0073] For example, when an autonomous vehicle is parked at a target parking spot, if there is a second obstacle in the target direction that is less than a second preset distance from the candidate parking spot, the autonomous vehicle needs to reverse to leave the target parking spot. Otherwise, if it moves forward to leave the target parking spot, it is easy to collide with the second obstacle in front, which will increase the difficulty for the autonomous vehicle to leave the target parking spot.

[0074] Therefore, when selecting a target parking spot, priority is given to available parking spots where there are no second obstacles in the target direction that are less than a fifth preset distance from the candidate parking spot. Then, if there are multiple available parking spots, the available parking spot with the smallest first distance from the target location is selected as the target parking spot. This not only reduces the driving distance of the autonomous vehicle when parking, but also reduces the difficulty for the autonomous vehicle when leaving the target parking spot.

[0075] Reference Figure 5 , Figure 5 This is a schematic diagram of an application scenario for determining available parking spots provided in one embodiment of this application. Figure 5 The arrows indicate the direction the autonomous vehicle is moving, the triangles represent the target location, the rectangles represent secondary obstacles, and the circles represent candidate parking spots. Figure 5 It can be seen that there is a second obstacle in the target direction of the first candidate parking point, while there is no second obstacle in the target direction of the second candidate parking point. Therefore, the second candidate parking point can be identified as a usable parking point.

[0076] It should be added that, in the first scenario, if multiple candidate parking points simultaneously include both available and unavailable parking points, the driving control device should first determine the target parking point from the available parking points. Then, during the autonomous vehicle's journey to the target parking point, if a second obstacle exists in the target direction that is less than a fifth preset distance from the candidate parking point, a new target parking point is determined from the available parking points. This process continues until a target parking point cannot be determined from the available parking points, at which point a target parking point is determined from the unavailable parking points. Unavailable parking points are defined as candidate parking points where a second obstacle exists in the target direction that is less than a fifth preset distance from the candidate parking point.

[0077] When determining the target parking spot from unavailable parking spots, the unavailable parking spot closest to the target location can be selected as the target parking spot based on the distance between the unavailable parking spot and the target location.

[0078] For the second case where the target area is a roadside area and the candidate parking spot is of the second preset type:

[0079] The driving control device can first identify candidate parking points located in the target direction of the first obstacle as available parking points; the target direction is the same as the forward direction of the unmanned vehicle; then, identify the available parking point with the smallest first distance from the target position as the target parking point.

[0080] The purpose of identifying candidate parking points in the target direction of the first obstacle as available parking points is that these available parking points are aligned with the autonomous vehicle's direction of travel, allowing the vehicle to park without reversing, thus reducing the difficulty of parking. Furthermore, identifying the available parking point with the smallest distance from the target location as the target parking point reduces the distance the autonomous vehicle needs to travel to park.

[0081] However, it's important to note that after identifying available parking spots, to further reduce the difficulty for the autonomous vehicle leaving the target parking spot, for any available parking spot, if it's determined that there is no second obstacle in the target direction that is less than a fifth preset distance from the available parking spot, then the available parking spot is designated as a candidate available parking spot. Then, the candidate available parking spot with the smallest first distance to the target location is designated as the target parking spot. This allows the autonomous vehicle to park without reversing when approaching the target parking spot, reducing the difficulty of parking; and similarly, it also eliminates the need to reverse when leaving the target parking spot, reducing the difficulty of leaving.

[0082] Reference Figure 6 , Figure 6 This is a schematic diagram of an application scenario for determining available parking spots provided in another embodiment of this application. Figure 6 The arrows indicate the direction the autonomous vehicle is moving, the triangles represent the target location, the rectangles represent the first obstacle, and the circles represent candidate parking spots. Figure 6 It can be seen that the first candidate parking spot is not located in the target direction of the first obstacle, while the second candidate parking spot is located in the target direction of the first obstacle. Therefore, if the autonomous vehicle parks at the first candidate parking spot, it will need to reverse to leave, which increases the difficulty for the autonomous vehicle to leave the candidate parking spot.

[0083] It should be added that, in the second scenario, if none of the candidate parking spots are located in the target direction of the first obstacle, the driving control device should determine the target parking spot from among the candidate parking spots located in the opposite target direction of the first obstacle. Alternatively, a new target area for parking can be selected; this will not be described in detail.

[0084] For the aforementioned non-roadside areas (including at least one pre-planned parking area), and the third case where the candidate parking spot is of the first preset type:

[0085] As explained in S102 above, when the target area is a non-roadside area and includes at least one pre-planned parking area, the driving control device will generate multiple candidate parking spots within each parking area. Therefore, for pre-planned parking areas, the driving control device should first select the optimal target parking area from among the multiple pre-planned parking areas. Then, using the methods described in the first or second case above, the final target parking spot is determined from the multiple candidate parking spots within the target parking area.

[0086] Specifically, when the target area is a non-roadside area and includes at least one pre-planned parking area, if the candidate parking point is of the first preset type, the driving control device can determine the center point of each parking area; then, for any center point, if there is no third obstacle in the target direction of the center point that is less than a sixth preset distance from the center point, the parking area corresponding to the center point is determined as an available parking area; the target direction is the same as the direction of travel of the autonomous vehicle; the available parking area closest to the target location is determined as the target parking area; and the target parking point is determined from each candidate parking point in the target parking area.

[0087] In one embodiment, the center point of the parking area can be the center of the parking area or a candidate parking spot located at the center of the boundary line within the parking area. Specifically, the boundary line can be the boundary line near the rear wheels when the autonomous vehicle is parked in the parking area.

[0088] In one embodiment, the aforementioned sixth preset distance can be set by staff, and this is not limited. It is understood that if there is no third obstacle in the target direction of the center point whose distance from the center point is less than the sixth preset distance, then the autonomous vehicle can leave the parking area without reversing after parking in the parking area corresponding to the center point, reducing the difficulty of the autonomous vehicle leaving the parking area. This situation is similar to the first situation in the roadside area, and will not be described in detail here.

[0089] After identifying all available parking areas, the autonomous vehicle can determine the target parking area based on the closest available parking area to the target location, and then select the target parking spot from among the candidate parking spots within the target parking area. The method for determining the target parking spot from the target parking area is similar to that from the roadside area, and will not be described in detail here.

[0090] It should be added that, in the third scenario, if the parking area corresponding to the center point includes both available and unavailable parking areas, the driving control device should first determine the target parking area from the available parking spots. Specifically, this determination method is similar to the method used in the first scenario, and will not be described in detail here.

[0091] For the target area mentioned above that is not a roadside area (including at least one pre-planned parking area), and the candidate parking spot type is also divided into the second preset type, fourth case:

[0092] The driving control device can identify the parking area located in the target direction of the first obstacle as an available parking area; the target direction is the same as the forward direction of the unmanned vehicle.

[0093] When the target area is a non-roadside area, the first obstacle is the obstacle located within the parking area closest to the target location. Therefore, the first obstacle may be in the target direction of the nearest parking area (located in front of the nearest parking area) or it may not be in the target direction of the nearest parking area (located behind the nearest parking area). In this case, even if the first obstacle is not in the target direction of the nearest parking area, the nearest parking area should still be considered a usable parking area.

[0094] It is understandable that if an autonomous vehicle parks in a parking area not located in the target direction of the first obstacle, it may collide with the first obstacle when it moves away in the forward direction. Therefore, when determining available parking areas, priority should be given to parking areas located in the target direction of the first obstacle.

[0095] After identifying all available parking areas, the autonomous vehicle can determine the target parking area by selecting the closest available parking area, and then choose the target parking spot from among the candidate parking spots within that target parking area. The method for determining the target parking spot from the target parking area is similar to that from the roadside area, and will not be described in detail here.

[0096] S104. Control the unmanned vehicle to move from its current location to the target parking point.

[0097] In one embodiment, after determining the location of the target parking spot, the driving control device can directly control the autonomous vehicle to travel from its current location to the target parking spot. It should be noted that, as described above, after identifying multiple available parking spots, the available parking spot closest to the target location is determined as the target parking spot. Therefore, it can be assumed that the target location and the target parking spot are relatively close.

[0098] It should be added that if temporary parking is possible at the target location, the driving control device can guide the autonomous vehicle to reach the target location first, and then proceed to the target parking spot. However, parking may not usually be possible at the target location. Therefore, the driving control device can directly guide the autonomous vehicle from its current location to the target parking spot. This can prevent the autonomous vehicle from parking illegally.

[0099] Furthermore, it should be noted that if parking at the target location is permitted for an extended period, and the parking spot type at the target location matches the preset parking spot type, then the target area in step S101 above should also include the target location. In this case, the driving control device also needs to process the target location using steps S102-S103 above to determine whether the target location is the optimal target parking spot.

[0100] In this embodiment, a target area where the autonomous vehicle can park is determined based on a preset parking spot type and the target location input by the user. Then, multiple candidate parking spots are generated within the target area, and the target parking spot is determined from these candidate spots based on the target location and the location of each candidate parking spot. Finally, the autonomous vehicle is controlled to move from its current location to the target parking spot. Based on this, when the autonomous vehicle parks, not only can a target area be automatically determined in the surrounding environment based on the selected preset parking spot type and target location, but multiple candidate parking spots can also be generated within the target area. That is, this solution can automatically control the autonomous vehicle to park at a suitable candidate parking spot by combining multiple factors such as the target location input by the user and the locations of candidate parking spots. Compared to solutions that require manual remote control of the autonomous vehicle's parking or forcing the autonomous vehicle to return to a preset parking lot, this improves the parking efficiency of the autonomous vehicle.

[0101] In one embodiment, when driving towards a target parking spot, the driving control device can plan an initial path from the current position of the autonomous vehicle to the target parking spot based on vehicle dynamics constraints. Then, it controls the autonomous vehicle to drive along the initial path towards the target parking spot.

[0102] In another embodiment, in order to enable the autonomous vehicle to avoid obstacles during driving and to make its actual driving route coincide with the planned initial path as much as possible, the driving control device can first divide the initial path into segments to obtain multiple segmented paths; then, the driving control device can replan the target driving path from the current position to the end of the segmented path, and when the autonomous vehicle reaches the end of the segmented path, it can replan the target driving path to the end of the next segmented path, until the target parking point is reached.

[0103] The initial path planning method includes, but is not limited to, heuristic search (A*) and Dijkstra's algorithm, and is not limited thereto. The algorithm for replanning the journey from the current position to the end of the segmented path can be a smoothing optimization algorithm, including but not limited to graph optimization, linear optimization, and nonlinear optimization algorithms, and is not limited thereto.

[0104] Reference Figure 7 , Figure 7 This is a schematic diagram of an application scenario provided in one embodiment of this application, depicting a vehicle driving to a target parking spot. Figure 7 The rectangle formed by the dashed line can be considered the autonomous vehicle, and the black circle can be considered the target parking point. It should be noted that the driving control device can represent the overall position of the autonomous vehicle by the center position between its two rear wheels. Therefore, when controlling the autonomous vehicle to park at the target parking point, it means aligning the center position between the two rear wheels of the autonomous vehicle with the target parking point.

[0105] In another embodiment, after determining the target parking point, if the autonomous vehicle senses a second obstacle with a distance less than a fifth preset distance in the target direction of the target parking point while driving towards the target parking point, the driving control device should re-determine the target parking point. The re-determination of the target parking point should also be performed according to steps S101-S104 described above.

[0106] Please see Figure 8 , Figure 8 This is a structural block diagram of a driving control device for an unmanned vehicle provided in an embodiment of this application. The driving control device for the unmanned vehicle in this embodiment includes modules for executing... Figure 1 and Figure 4 The steps in the corresponding embodiments. Please refer to the details. Figure 1 and Figure 4 as well as Figure 1 and Figure 4 The relevant descriptions in the corresponding embodiments are shown below. For ease of explanation, only the parts relevant to this embodiment are shown. See also... Figure 8 The driving control device 800 of the unmanned vehicle may include: a first determining module 810, a parking point generating module 820, a second determining module 830, and a control module 840, wherein:

[0107] The first determining module 810 is used to determine the preset parking point type and the target area where the unmanned vehicle can park, based on the target location input by the user and the pre-stored high-precision map.

[0108] The parking spot generation module 820 is used to generate multiple candidate parking spots within the target area.

[0109] The second determining module 830 is used to determine the target parking point from all candidate parking points based on the target location and the locations of each candidate parking point.

[0110] The control module 840 is used to control the unmanned vehicle to move from its current location to the target parking point.

[0111] In one embodiment, the parking spot generation module 820 is further configured to:

[0112] If the target area is a roadside area, multiple first candidate parking spots are generated along the roadside edge of the roadside area, and multiple second candidate parking spots corresponding to the first candidate parking spots are generated respectively. A first preset distance separates each pair of adjacent first candidate parking spots. The line connecting each first candidate parking spot and its corresponding second candidate parking spot is perpendicular to the roadside edge, and a second preset distance separates each first candidate parking spot and its corresponding second candidate parking spot. If the target area is not a roadside area, and the target area includes at least one pre-planned parking area, multiple third candidate parking spots are generated along the first boundary line of any parking area, and multiple fourth candidate parking spots corresponding to the third candidate parking spots are generated along a second boundary line parallel to the first boundary line. Multiple fifth candidate parking spots are generated between each third candidate parking spot and its corresponding fourth candidate parking spot. A third preset distance separates each pair of adjacent third candidate parking spots. The line connecting each third candidate parking spot and its corresponding fourth candidate parking spot is perpendicular to the first boundary line, and a fourth preset distance separates each pair of adjacent fifth candidate parking spots.

[0113] In one embodiment, the second determining module 830 is further configured to:

[0114] Determine the type of each candidate parking spot based on the target location and target area; determine the first distance between the candidate parking spots and the target location; and determine the target parking spot from all candidate parking spots based on the type of the candidate parking spots and the first distance.

[0115] In one embodiment, the second determining module 830 is further configured to:

[0116] If the target area is a roadside area and there is no first obstacle within the first preset range corresponding to the target location, then the candidate parking spot type is determined to be the first preset type; if the target area is a roadside area and there is a first obstacle within the first preset range corresponding to the target location, then the candidate parking spot type is determined to be the second preset type; if the target area is not a roadside area and includes at least one pre-planned parking area, and there is no first obstacle within the parking area closest to the target location, then the candidate parking spot type is determined to be the first preset type; if the target area is not a roadside area and includes at least one pre-planned parking area, and there is a first obstacle within the parking area closest to the target location, then the candidate parking spot type is determined to be the second preset type.

[0117] In one embodiment, the second determining module 830 is further configured to:

[0118] When the target area is a roadside area, for any candidate parking spot, if the type of the candidate parking spot is the first preset type, and there is no second obstacle in the target direction of the candidate parking spot that is less than the fifth preset distance from the candidate parking spot, then the candidate parking spot is determined as an available parking spot; the target direction is the same as the direction of travel of the unmanned vehicle; the available parking spot with the smallest first distance from the target location is determined as the target parking spot.

[0119] In one embodiment, the second determining module 830 is further configured to:

[0120] If the target area is a roadside area, and the candidate parking point is of the second preset type, then the candidate parking point located in the target direction of the first obstacle is determined as an available parking point; the target direction is the same as the direction of travel of the unmanned vehicle; and the available parking point with the smallest first distance from the target location is determined as the target parking point.

[0121] In one embodiment, the driving control device 800 of the unmanned vehicle further includes:

[0122] The third determining module is used to determine the center point of each parking area if the candidate parking point is of the first preset type, when the target area is a non-roadside area and the target area includes at least one pre-planned parking area.

[0123] The fourth determination module is used to determine the parking area corresponding to any center point as an available parking area if there is no third obstacle in the target direction of the center point that is less than the sixth preset distance from the center point; the target direction is the same as the forward direction of the unmanned vehicle.

[0124] The fifth determination module is used to determine the target parking area by identifying the available parking area closest to the target location.

[0125] The sixth determination module is used to determine the target parking point from among the candidate parking points in the target parking area.

[0126] In one embodiment, the driving control device 800 of the unmanned vehicle further includes:

[0127] The seventh determination module is used to determine the parking area located in the target direction of the first obstacle as an available parking area if the candidate parking point is of the second preset type, when the target area is a non-roadside area and the target area includes at least one pre-planned parking area; the target direction is the same as the direction of travel of the unmanned vehicle.

[0128] The eighth determination module is used to determine the nearest available parking area to the target location as the target parking area.

[0129] The ninth determination module is used to determine the target parking point from among the candidate parking points in the target parking area.

[0130] When it is understood that, Figure 8 The block diagram of the driving control device for the autonomous vehicle shown illustrates that each module is used to perform... Figure 1 and Figure 4 The steps in the corresponding embodiments, and for Figure 1 and Figure 4 The steps in the corresponding embodiments have been explained in detail in the above embodiments. Please refer to them for details. Figure 1 and Figure 4 as well as Figure 1 and Figure 4 The relevant descriptions in the corresponding embodiments will not be repeated here.

[0131] Figure 9 This is a structural block diagram of an unmanned vehicle provided in one embodiment of this application. Figure 9 As shown, the unmanned vehicle 900 of this embodiment includes: a processor 910, a memory 920, and a computer program 930 stored in the memory 920 and executable by the processor 910, such as a program for a driving control method for an unmanned vehicle. When the processor 910 executes the computer program 930, it implements the steps of the various embodiments of the driving control methods for unmanned vehicles described above, for example... Figure 1 S101 to S104 are shown. Alternatively, the processor 910 implements the above when executing the computer program 930. Figure 8 The functions of each module in the corresponding embodiments, for example, Figure 8 For details on the functions of modules 810 to 840 shown, please refer to [link / reference]. Figure 8 The relevant descriptions in the corresponding embodiments.

[0132] For example, the computer program 930 can be divided into multiple modules, which are stored in the memory 920 and executed by the processor 910 to implement the driving control method for the unmanned vehicle provided in this embodiment. One or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 930 in the unmanned vehicle 900. For example, the computer program 930 can implement the driving control method for the unmanned vehicle provided in this embodiment.

[0133] The autonomous vehicle 900 may include, but is not limited to, a processor 910 and a memory 920. Those skilled in the art will understand that... Figure 9 This is merely an example of an autonomous vehicle 900 and does not constitute a limitation on the autonomous vehicle 900. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, an autonomous vehicle may also include a chassis, power system, perception system, control system, input / output devices, network access devices, bus, etc.

[0134] The processor 910 may be a central processing unit, or it may be other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0135] The memory 920 can be an internal storage unit of the autonomous vehicle 900, such as the hard drive or memory of the autonomous vehicle 900. The memory 920 can also be an external storage device of the autonomous vehicle 900, such as a plug-in hard drive, smart memory card, flash memory card, etc., equipped on the autonomous vehicle 900. Furthermore, the memory 920 can include both internal storage units and external storage devices of the autonomous vehicle 900.

[0136] This application provides a computer-readable storage medium, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the driving control method for the unmanned vehicle as described in the above embodiments.

[0137] This application provides a computer program product that, when run on an unmanned vehicle, causes the unmanned vehicle to execute the driving control methods of the unmanned vehicle in the above embodiments.

[0138] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for controlling the driving of an unmanned vehicle, characterized in that, The method includes: Based on the target location input by the user and the pre-stored high-precision map, the preset parking point type and the target area where the unmanned vehicle can park are determined. Multiple candidate parking spots are generated within the target area; Based on the target location and the locations of each of the candidate parking spots, the target parking spot is determined from all the candidate parking spots; Control the unmanned vehicle to move from its current location to the target parking point; The step of determining the target parking point from all the candidate parking points based on the target location and the locations of each candidate parking point includes: The type of each candidate parking spot is determined based on the obstacle, the target location, and the target area; Determine a first distance between the candidate parking spot and the target location; The target parking spot is determined from all the candidate parking spots based on the target direction, the type of the candidate parking spot, and the first distance; the target direction is the same as the forward direction of the unmanned vehicle.

2. The method according to claim 1, characterized in that, The generation of multiple candidate parking spots within the target area includes: If the target area is a roadside area, then multiple first candidate parking spots are generated along the roadside edge of the roadside area, and multiple second candidate parking spots are generated respectively corresponding to the first candidate parking spots; there is a first preset distance between each two adjacent first candidate parking spots, the line connecting each first candidate parking spot and the corresponding second candidate parking spot is perpendicular to the roadside edge, and there is a second preset distance between each first candidate parking spot and the corresponding second candidate parking spot; If the target area is a non-roadside area, and the target area includes at least one pre-planned parking area, then for any parking area, multiple third candidate parking points are generated along the first boundary line of the parking area, and multiple fourth candidate parking points corresponding to the third candidate parking points are generated along the second boundary line parallel to the first boundary line. Multiple fifth candidate parking points are generated between each third candidate parking point and its corresponding fourth candidate parking point. A third preset distance is spaced between each pair of adjacent third candidate parking points, the line connecting each third candidate parking point and its corresponding fourth candidate parking point is perpendicular to the first boundary line, and a fourth preset distance is spaced between each pair of adjacent fifth candidate parking points.

3. The method according to claim 1, characterized in that, Determining the type of each candidate parking spot based on the obstacle, the target location, and the target area includes: If the target area is a roadside area and there is no first obstacle within the first preset range corresponding to the target location, then the type of the candidate parking spot is determined to be the first preset type; If the target area is a roadside area, and the first obstacle exists within the first preset range corresponding to the target location, then the type of the candidate parking spot is determined to be the second preset type; If the target area is a non-roadside area, and the target area includes at least one pre-planned parking area, and the first obstacle is not present in the parking area closest to the target location, then the candidate parking spot is determined to be of the first preset type. If the target area is a non-roadside area, and the target area includes at least one pre-planned parking area, and there is a first obstacle in the parking area closest to the target location, then the candidate parking spot is determined to be of the second preset type.

4. The method according to claim 3, characterized in that, Determining the target parking spot from all the candidate parking spots based on the target direction, the type of the candidate parking spot, and the first distance includes: When the target area is a roadside area, for any candidate parking spot, if the type of the candidate parking spot is a first preset type, and there is no second obstacle in the target direction of the candidate parking spot that is less than a fifth preset distance from the candidate parking spot, then the candidate parking spot is determined as an available parking spot. The available parking spot with the smallest first distance from the target location is determined as the target parking spot.

5. The method according to claim 3, characterized in that, Determining the target parking spot from all the candidate parking spots based on the target direction, the type of the candidate parking spot, and the first distance includes: If the target area is a roadside area, and the candidate parking spot is of the second preset type, then the candidate parking spot located in the target direction of the first obstacle is determined as an available parking spot. The available parking spot with the smallest first distance from the target location is determined as the target parking spot.

6. The method according to claim 3, characterized in that, Before determining the target parking spot from all the candidate parking spots based on the target direction, the type of the candidate parking spot, and the first distance, the method further includes: If the target area is a non-roadside area and the target area includes at least one pre-planned parking area, and the type of the candidate parking point is a first preset type, then the center point of each of the parking areas is determined. For any of the center points, if there is no third obstacle in the target direction of the center point that is less than a sixth preset distance from the center point, then the parking area corresponding to the center point is determined as an available parking area. The target parking area is determined by the available parking area closest to the target location. The target parking spot is determined from each of the candidate parking spots in the target parking area.

7. The method according to claim 3, characterized in that, Before determining the target parking spot from all the candidate parking spots based on the target direction, the type of the candidate parking spot, and the first distance, the method further includes: If the target area is a non-roadside area and the target area includes at least one pre-planned parking area, and the type of the candidate parking spot is a second preset type, then the parking area located in the target direction of the first obstacle is determined as an available parking area. The available parking area closest to the target location is identified as the target parking area; The target parking spot is determined from each of the candidate parking spots in the target parking area.

8. A driving control device for an unmanned vehicle, characterized in that, The device includes: The first determining module is used to determine the target area where parking is possible based on the target location input by the user and the preset parking point type of the unmanned vehicle. A parking spot generation module is used to generate multiple candidate parking spots within the target area; The second determining module is used to determine the target parking point from all the candidate parking points based on the target location and the locations of each of the candidate parking points; The control module is used to control the unmanned vehicle to move from its current position to the target parking point. The second determining module also includes functions for: The type of each candidate parking spot is determined based on the obstacle, the target location, and the target area; Determine a first distance between the candidate parking spot and the target location; The target parking spot is determined from all the candidate parking spots based on the target direction, the type of the candidate parking spot, and the first distance; the target direction is the same as the forward direction of the unmanned vehicle.

9. An unmanned vehicle, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method of any one of claims 1 to 7.

Images