Vehicle passable area determination method, device, equipment and medium

Abstract

The present disclosure relates to a vehicle passable area determination method, device, equipment and medium. The vehicle passable area determination method comprises: determining a passable area in a road based on road environment information, wherein the passable area comprises a first passable area between target obstacles and / or a second passable area between the target obstacles and a road boundary; obtaining vehicle information of a host vehicle and passage information of the passable area; determining a passing cost of the passable area based on the vehicle information of the host vehicle and the passage information, wherein the passing cost is used to represent safety feasibility and / or driving convenience of vehicle passing; and determining the passable area with the minimum passing cost as an optimal passable area. The technical scheme of the present disclosure reduces the exploration direction of unnecessary passable areas, is simple to calculate and fast in calculation.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, and in particular to a method, apparatus, equipment and medium for determining a vehicle's passable area. Background Technology

[0002] With the development of vehicle intelligence technology, autonomous vehicle control technology has gradually become a hot topic in the field of vehicle research. Autonomous driving systems need to plan smooth, safe, and passable paths to ensure that vehicles do not collide with obstacles.

[0003] Currently, based on optimized path planning, the approach first explores the vehicle-accessible area, and then calculates the optimal path within that area that conforms to vehicle dynamics, kinematics, and road constraints. Exploring the vehicle-accessible area can utilize path search methods, including A* path search and greedy tree search. However, these methods are computationally complex and unsuitable for exploring accessible areas in road environments. Summary of the Invention

[0004] In order to solve the above-mentioned technical problems, or at least partially solve the above-mentioned technical problems, this disclosure provides a method, apparatus, equipment and medium for determining a vehicle passable area.

[0005] This disclosure provides a method for determining a vehicle-accessible area, including:

[0006] Based on road environment information, a passable area within the road is determined, wherein the passable area includes a first passable area between target obstacles and / or a second passable area between the target obstacles and the road boundary;

[0007] Obtain vehicle information and access information for the passable area;

[0008] Based on the vehicle information and the channel information, the passage cost of the passable area is determined, and the passage cost is used to characterize the safety feasibility and / or driving convenience of vehicle passage;

[0009] The passable area with the lowest passage cost is determined as the optimal passable area.

[0010] This disclosure provides a device for determining a vehicle passable area, including:

[0011] The passable area determination module is used to determine the passable area within the road based on road environment information, wherein the passable area includes a first passable area between target obstacles and / or a second passable area between the target obstacles and the road boundary;

[0012] The information acquisition module is used to acquire vehicle information and access information of the passable area;

[0013] The passage cost determination module is used to determine the passage cost of the passable area based on the vehicle information and the channel information. The passage cost is used to characterize the safety feasibility and / or driving convenience of vehicle passage.

[0014] The passable area selection module is used to determine the passable area with the lowest passage cost as the optimal passable area.

[0015] This disclosure provides an electronic device, including:

[0016] Memory and one or more processors;

[0017] The memory is communicatively connected to the one or more processors, and the memory stores instructions that can be executed by the one or more processors. When the instructions are executed by the one or more processors, the electronic device is used to implement the vehicle passable area determination method provided in any embodiment of this disclosure.

[0018] This disclosure provides a computer-readable storage medium storing computer-executable instructions thereon. When the computer-executable instructions are executed by a computing device, they can be used to implement the vehicle passable area determination method provided in any embodiment of this disclosure.

[0019] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0020] The technical solution provided in this disclosure is based on road environment information to determine passable areas within the road. This allows for the effective use of road environment information to explore passable areas in adjacent lanes or even adjacent lanes, thereby avoiding problems such as vehicles crossing or exiting the road, and reducing violations and traffic accidents. Furthermore, based on vehicle information and the passage information of passable areas, the passage cost of each passable area is determined. By comparing the passage costs of each passable area, the passable area with the lowest passage cost is selected as the optimal passable area. This enables the vehicle to plan an optimal passable route based on the optimal passable area. Thus, the calculation of the optimal passable area is simple and can be done quickly. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0022] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 The method for determining the passable area of ​​a vehicle provided in this embodiment of the disclosure;

[0024] Figure 2 A schematic diagram of an obstacle-corresponding bounding box provided in an embodiment of this disclosure;

[0025] Figure 3 This is a schematic diagram illustrating the distribution of actual obstacles within a lane, provided as an embodiment of the present disclosure.

[0026] Figure 4 This is a schematic diagram of a passable area provided in an embodiment of the present disclosure;

[0027] Figure 5 Functional block diagram of the vehicle passable area determination device provided in the embodiments of this disclosure;

[0028] Figure 6 This is a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of this disclosure. Detailed Implementation

[0029] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0030] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0031] Currently, when using A* path search and greedy tree search methods to explore passable areas, all passable areas within the explorable region ahead are explored. Therefore, in a road environment, using A* path search or greedy tree search methods to explore passable areas can easily lead to problems such as vehicles making U-turns, driving against traffic, crossing lanes, and illegally jaywalking, which can easily cause traffic accidents.

[0032] To address the aforementioned technical problems, this disclosure provides a method for determining a vehicle's passable area. This method is applicable to situations where autonomous vehicles identify passable areas in a road environment. It can be applied to autonomous vehicles, specifically to the intelligent driving system of autonomous vehicles, and can also be applied to cloud servers or terminals such as computers, laptops, and tablets. Based on the vehicle passable area determination method provided in this disclosure, the optimal passable area can be quickly calculated. The roads involved in this disclosure typically include at least two lanes. Based on road environment information, passable areas can be determined on all lanes, and then the optimal passable area can be determined based on the passage cost of the passable areas.

[0033] In some embodiments, autonomous vehicles can support both manual and intelligent driving. When in manual driving mode, the driver can operate the vehicle using devices that control its movement, such as the brake pedal, steering wheel, and accelerator pedal. When in intelligent driving mode, the intelligent driving system perceives the surrounding environment and locates the vehicle based on sensor information. Based on the perceived information and location results, it makes driving plans and generates control commands, which are then sent to the underlying execution system to control the vehicle. In intelligent driving mode, the vehicle is steered using an electric power steering system. In some embodiments, regardless of whether the autonomous vehicle is in manual or intelligent driving mode, the intelligent driving system determines the optimal passable area and plans the optimal route based on that area. The difference lies in the driving mode. When the autonomous vehicle is in manual driving mode, the best possible route is displayed on the screen, and the driver controls the autonomous vehicle to drive according to the best possible route. When the autonomous vehicle is in intelligent driving mode, the intelligent driving system generates control commands based on the best possible route and sends the control commands to the underlying execution system to control the autonomous vehicle to drive.

[0034] Figure 1 A method for determining a vehicle-accessible area provided in embodiments of this disclosure. For example... Figure 1 As shown, the method includes the following steps:

[0035] S110. Based on road environment information, determine the passable area within the road.

[0036] The passable area includes a first passable area between target obstacles and / or a second passable area between the target obstacle and the road boundary.

[0037] In some embodiments, road environment information may include road information and target obstacle information. The road information may be obtained from a high-precision map, and road boundaries can be determined based on this road information. Additionally, the target obstacle information may be acquired by a vehicle perception module, and this target obstacle information may include the size and location information of the target obstacle. Based on the road boundaries and the target obstacle information, target obstacles within the road can be identified. Further, a first passable area is determined based on the target obstacle information within the road; and / or, a second passable area is determined based on the road boundaries and the target obstacle information within the road. Specifically, when it is necessary to determine the first passable area between target obstacles, the minimum lateral distance between any two adjacent target obstacles is calculated based on the size and location information of the target obstacles. When this minimum lateral distance is greater than the passable width of the vehicle, the area between the corresponding two adjacent target obstacles is determined as the first passable area. When it is necessary to determine the second passable area between the road boundary and the target obstacle within the road, the minimum distance from the two road boundaries to the target obstacle within the road is determined based on the road information and the target obstacle information. When the minimum distance is greater than the passable width of the vehicle, the area between the corresponding road boundary and the target obstacle is determined as the second passable area.

[0038] In some embodiments, the target obstacle may include an obstacle sensed by a sensing module, i.e., an actual obstacle. In this case, a first passable area is determined directly based on the information of the actual obstacle, and a second passable area is determined based on the information of the actual obstacle and road information. For details, please refer to the method for determining the first and second passable areas of the target obstacle described above, which will not be repeated here.

[0039] In some embodiments, the target obstacle may further include an obstacle obtained after processing an actual obstacle. Optionally, the target obstacle includes a first obstacle and / or a second obstacle, and correspondingly, before determining the passable area within the road based on road environment information, the method further includes S11 to S13:

[0040] S11. Obtain information about the actual obstacles.

[0041] For example, establish a Frenet coordinate system, such as Figure 2 As shown, the S-axis represents the distance along the road travel direction, and the L-axis represents the distance perpendicular to the road travel direction. Based on the obstacle information collected by the perception module, the information of the actual obstacle 10 in the Frenet coordinate system is obtained, that is, the contour coordinates of the actual obstacle 10.

[0042] S12. Based on information about actual obstacles, determine whether the area between each actual obstacle is passable.

[0043] In some embodiments, to simplify the calculation of whether the area between each actual obstacle is passable, a bounding box 101 for each actual obstacle 10 can be generated based on the information of the actual obstacles 10. Whether the area between each bounding box 101 is passable is determined by judging whether the area between the actual obstacles is passable. For example, the bounding box 101 is the circumscribed quadrilateral of the actual obstacle 10, and two adjacent sides of the bounding box 101 are parallel to the S-axis and L-axis, respectively. If the area between the bounding boxes 101 is passable, then the area between the corresponding actual obstacles 10 is passable; otherwise, it is not passable.

[0044] In some embodiments, the area between each actual obstacle includes the area between actual obstacles laterally and the area between actual obstacles longitudinally. Specifically, determining whether the area between each actual obstacle is passable based on information about the actual obstacles includes:

[0045] When it is determined from the information of the actual obstacles that two adjacent actual obstacles meet the preset passage conditions, the area between the two adjacent actual obstacles is determined to be passable; otherwise, the area between the two adjacent actual obstacles is determined to be impassable.

[0046] The preset passage conditions include at least one of the following:

[0047] The longitudinal distance between two adjacent actual obstacles is greater than the safe length of the vehicle.

[0048] The lateral distance between two adjacent actual obstacles is greater than the first safe width of the vehicle;

[0049] The sum of the longitudinal and lateral distances between two adjacent actual obstacles is greater than the second safe width of the vehicle.

[0050] In the above technical solution, the vehicle's safe length, first safe width, and second safe width are all determined by the vehicle's actual dimensions and the passage area. Based on the above technical solution, in a specific embodiment of this disclosure, as follows... Figure 3As shown, the actual obstacles may include a first actual obstacle 11, a second actual obstacle 12, a third actual obstacle 13, a fourth actual obstacle 14, and a fifth actual obstacle 15. The lateral distance d1 between the first actual obstacle 11 and the second actual obstacle 12 is less than the first safe width of the vehicle, indicating that the first actual obstacle 11 and the second actual obstacle 12 do not meet the preset passage conditions, therefore the area between the first actual obstacle 11 and the second actual obstacle 12 is impassable. The lateral distance d2 between the second actual obstacle 12 and the third actual obstacle 13 is greater than the first safe width of the vehicle, indicating that the second actual obstacle 12 and the third actual obstacle 13 meet the preset passage conditions, therefore the area between the second actual obstacle 12 and the third actual obstacle 13 is passable. The longitudinal distance d3 between the third actual obstacle 13 and the fourth actual obstacle 14 is greater than the safe length of the vehicle, indicating that the longitudinal distance d3 between the third actual obstacle 13 and the fourth actual obstacle 15 is greater than the safe length of the vehicle, indicating that the longitudinal distance d3 between the third actual obstacle 13 and the fourth actual obstacle 15 is greater than the safe length of the vehicle. If the actual obstacle 14 meets the preset passage conditions, then the area between the third actual obstacle 13 and the fourth actual obstacle 14 is passable. In addition, the lateral distance d4 between the fourth actual obstacle 14 and the fifth actual obstacle 15 is less than the first safe width of the vehicle, and the longitudinal distance d5 between the fourth actual obstacle 14 and the fifth actual obstacle 15 is less than the safe length of the vehicle. However, the sum of the lateral distance d4 and the longitudinal distance d5 is greater than the second safe width of the vehicle, indicating that the vehicle can pass through the area between the fourth actual obstacle 14 and the fifth actual obstacle 15 at an angle. At this time, the fourth actual obstacle 14 and the fifth actual obstacle 15 still meet the preset passage conditions, and the area between the fourth actual obstacle 14 and the fifth actual obstacle 15 is passable.

[0051] S13. Merge the actual obstacles corresponding to the impassable areas to obtain at least one first obstacle, and use the unmerged actual obstacles as second obstacles. The areas between the first and second obstacles, the areas between the first obstacles, and the areas between the second obstacles are all passable.

[0052] For example, please refer to... Figure 3As can be seen from the above embodiments, the area between the first actual obstacle 11 and the second actual obstacle 12 is impassable. In this case, the first actual obstacle 11 and the second actual obstacle 12 are merged to obtain an obstacle containing the first actual obstacle 11 and the second actual obstacle 12, namely the first obstacle 100. Specifically, a bounding box surrounding the first actual obstacle 11 and the second actual obstacle 12 can be generated based on the information of the first actual obstacle 11 and the second actual obstacle 12. This bounding box can also be a quadrilateral, with two adjacent sides parallel to the S-axis and the L-axis, respectively. In addition, the area between the third actual obstacle 13 and other adjacent actual obstacles is passable. In this case, the third actual obstacle 13 is not merged, and it is used as the second obstacle 200. It should be noted that a first obstacle 100 is obtained by merging actual obstacles at least once. For example, after the first actual obstacle 11 and the second actual obstacle 12 are merged, if the area between the merged obstacle and the third actual obstacle 13 is still impassable, the merged obstacle and the third actual obstacle 13 will continue to be merged. This process continues until the area between the newly merged obstacle and the adjacent actual obstacle is passable, or there is no adjacent actual obstacle. The obstacle after the last merger will then be used as the first obstacle 100.

[0053] In a specific embodiment of this disclosure, a CLOSED table is created. First, the CLOSED table is initialized to an empty table. Then, an actual obstacle is taken from the set of actual obstacles and added to the CLOSED table, while the actual obstacle is deleted from the set. Next, the set is traversed. If an actual obstacle in the set does not meet a preset passage condition with an actual obstacle in the CLOSED table, the actual obstacle in the set is added to the CLOSED table, and the corresponding actual obstacle in the set is deleted. This process is repeated until the set is empty. Finally, the actual obstacles in the CLOSED table that do not meet the preset passage condition are merged.

[0054] Understandably, if the area between any two adjacent actual obstacles is passable, there is no need to merge the actual obstacles. In this case, the target obstacle only includes the second obstacle, and the area between the second obstacles is passable. However, if there is an area between two adjacent actual obstacles that is not passable, and there is an area between one actual obstacle and an adjacent obstacle (including the actual obstacle and the first obstacle) that is passable, then the target obstacle includes both the first and second obstacles. In this case, when two first obstacles are adjacent, the area between the first obstacles is passable; when two second obstacles are adjacent, the area between the second obstacles is passable; and when both first and second obstacles are adjacent, the area between the first obstacle and the second obstacle is passable. Furthermore, if the actual obstacles eventually merge into a single first obstacle, then when determining the passable area within the road, only the second passable area between the first obstacle and the road boundary needs to be considered. It should be noted that to ensure vehicle passability, both the first and second passable areas should be determined, i.e., all passable areas within the current lane should be determined.

[0055] It should be noted that in the embodiments disclosed herein, the lateral direction is perpendicular to the road traffic direction, and the longitudinal direction is parallel to the road traffic direction.

[0056] S120. Obtain vehicle information and access information for the passable area.

[0057] In some embodiments, the vehicle information includes the vehicle's position and width, and the passage information includes the passage position (i.e., the position of the passable area) and the passage width (i.e., the lateral width of the passable area). The passage position and passage width can be defined by the position of the target obstacle.

[0058] S130. Based on the vehicle information and the passage information, determine the passage cost of the passable area.

[0059] The passage cost is used to characterize the safe feasibility and / or ease of vehicle passage. A lower passage cost indicates higher safe feasibility and / or ease of vehicle passage. Considering that the width of the passageway affects the safe feasibility and / or ease of vehicle passage, a wider passageway results in a lower passage cost. Furthermore, considering that for a passable area with the same passageway width, different vehicle poses (the angle between the vehicle and the passable area) and different lateral distances between the vehicle and the passable area result in different passage costs, this embodiment of the disclosure takes into account both the passageway width, vehicle pose, and the distance of lateral movement to determine the passage cost.

[0060] In some embodiments, the passage cost of a passable area is determined based on the vehicle information and the access information, including S31 to S34:

[0061] S31. Based on the width of the vehicle and the width of the passage, determine the first passage cost for the width of the passage.

[0062] In some embodiments, the first passage cost is calculated using the following cost function:

[0063]

[0064] Wherein, MAX_COST is the preset maximum value of the first passage cost, w0 is the width threshold where the first passage cost is 0, w is the channel width, and w_v is the sum of the vehicle width and the preset safety distance. MAX_COST can be a large value in the hundreds of thousands or millions, representing an instantiation of infinite passage cost. When the first passage cost is 0, the safety feasibility and / or driving convenience of vehicle passage are maximized; when the first passage cost is MAX_COST, the safety feasibility and / or driving convenience of vehicle passage are minimized.

[0065] S32. Based on the vehicle's position and the passage's position, determine the first horizontal distance and the second vertical distance between the vehicle at the starting point and the passable area.

[0066] The first distance can be the distance from the center point of the vehicle to the center line of the passable area via a curve that passes through the vehicle's center point and is parallel to the direction of traffic. The second distance is the distance from the vehicle's starting point to the starting point of the passable area along the direction of traffic.

[0067] S33. Based on the first distance and the second distance, determine the vehicle pose and the second passage cost for lateral movement.

[0068] In some embodiments, the second passage cost is calculated using the following cost function:

[0069]

[0070] Where K is the balance coefficient between the second and first passage costs, ensuring that the orders of magnitude of the second and first passage costs are not significantly different, l is the first distance, and s is the second distance. This cost function shows that the adjustment of the vehicle's pose is related to the distance the vehicle travels along the road direction. The longer the distance between the two obstacles along the road direction, the better the vehicle can adjust its pose before entering the next passable area, and the lower the corresponding passage cost.

[0071] S34. The sum of the first passage cost and the second passage cost is determined as the passage cost.

[0072] Based on the above embodiments, the passage cost is cost1(w) + cost2(s,l).

[0073] It should be noted that in some scenarios, only the first passage cost needs to be considered based on the vehicle's pose and its lateral offset relative to the passable area. For example, when the vehicle's heading is determined to be parallel to the passage direction of the passable area based on its pose, and the vehicle has no lateral offset relative to the passable area (first distance is 0), the first passage cost is determined as the passage cost (second passage cost is 0). In other scenarios, both the first and second passage costs need to be considered based on the vehicle's pose and / or its lateral offset relative to the passable area. For example, when the angle between the vehicle's heading and the passage direction of the passable area is greater than 0 based on its pose, and / or when there is a lateral offset relative to the passable area, the vehicle needs to adjust a certain distance before entering the passable area to enter with a better pose (e.g., heading parallel to the passage direction of the passable area). In this case, the sum of the first and second passage costs is determined as the passage cost.

[0074] S140. Determine the passable area with the minimum passage cost as the optimal passable area.

[0075] After calculating the passage cost of all passable areas, the passable area with the lowest passage cost is selected as the optimal passable area. The best route can then be planned based on this optimal passable area, thereby improving the safety and convenience of vehicle passage.

[0076] The vehicle passable area determination method provided in this disclosure determines passable areas within a road based on road environment information. This effectively utilizes road environment information to explore passable areas in adjacent lanes or even adjacent lanes under road environment constraints, thereby avoiding problems such as vehicles crossing or exiting the road, reducing violations and traffic accidents. Furthermore, based on vehicle information and the passage information of passable areas, the method determines the passage cost of each passable area. By comparing the passage costs of each passable area, the method selects the passable area with the lowest passage cost as the optimal passable area. This allows the vehicle to plan an optimal passable route based on the optimal passable area. Thus, the calculation of the optimal passable area is simple and can be performed quickly.

[0077] Based on the above embodiments, in some embodiments, by grouping the target obstacles or passable areas along the road travel direction, for each group of target obstacles or passable areas, the optimal passable area is determined one by one along the road travel direction, thereby determining an optimal area for vehicles to pass along the road travel direction.

[0078] Accordingly, in some embodiments, obtaining passage information for passable areas includes S51 to S53:

[0079] S51. Based on information about the road boundary and target obstacles within the road, identify target obstacles whose lateral projections on the road boundary overlap.

[0080] In some embodiments, obstacle projection can be used to project target obstacles within the road onto a defined road boundary, determining the projection range of each target obstacle on the road boundary (the S-axis coordinate range in the Frenet coordinate system). Based on the overlap of the projection ranges on the road boundary, target obstacles with overlapping lateral projections on the road boundary are identified. For example, refer to... Figure 4 The first passable area, the second passable area, the third passable area, and the fourth passable area form one group of passable areas, and the fifth passable area, the sixth passable area, and the seventh passable area form another group of passable areas.

[0081] S52, the first passable area and the corresponding second passable area between overlapping target obstacles projected laterally on the road boundary are taken as a set of passable areas.

[0082] S53. Obtain the passage information of the above-mentioned set of passable areas.

[0083] Based on the above embodiments, in some embodiments, the passage cost of each group of passable areas is determined along the road travel direction using the above grouping method.

[0084] Specifically, along the vehicle's direction of travel, the passable areas are sorted into groups. For the first group of passable areas, the passage cost is determined using the vehicle's current position as the starting point. For the Nth group of passable areas, the passage cost is determined using the endpoint of the optimal passable area in the (N-1)th group as the starting point, where N is an integer greater than 1. The calculation of the passage cost for each group of passable areas can be referred to the above embodiment, and will not be repeated here.

[0085] Figure 5 This is a functional block diagram of the vehicle passable area determination device provided in an embodiment of this disclosure. Figure 5 As shown, the vehicle passable area determination device includes a passable area determination module 201, an information acquisition module 202, a passage cost determination module 203, and a passable area selection module 204.

[0086] The passable area determination module 201 is used to determine the passable area within the road based on road environment information. The passable area includes a first passable area between target obstacles and / or a second passable area between the target obstacle and the road boundary.

[0087] Information acquisition module 202 is used to acquire vehicle information and access information of passable areas;

[0088] The passage cost determination module 203 is used to determine the passage cost of the passable area based on the vehicle information and the channel information. The passage cost is used to characterize the safety feasibility and / or driving convenience of the vehicle passage.

[0089] The passable area selection module 204 is used to determine the passable area with the lowest passage cost as the optimal passable area.

[0090] In some embodiments, the road environment information includes road information and information about target obstacles, and the passable area determination module 201 is specifically used for:

[0091] Determine road boundaries based on road information;

[0092] Based on information about road boundaries and target obstacles, identify target obstacles within the road;

[0093] Based on information about target obstacles within the road, a first passable area is determined; and / or, based on information about road boundaries and target obstacles within the road, a second passable area is determined.

[0094] In some embodiments, the information acquisition module 202 is specifically used for:

[0095] Based on information about road boundaries and target obstacles within the road, target obstacles with overlapping lateral projections on the road boundaries are identified, wherein the lateral projection is perpendicular to the road traffic direction.

[0096] The first passable area and the corresponding second passable area between overlapping target obstacles projected laterally on the road boundary are considered as a set of passable areas.

[0097] Obtain access information for a set of passable areas.

[0098] In some embodiments, the apparatus further includes:

[0099] The passable area sorting module is used to sort the passable areas in each group along the direction of travel of the vehicle.

[0100] The passage cost determination module 203 is specifically used for:

[0101] For the first group of passable areas, the passage cost for the first group of passable areas is determined from the current position of the vehicle.

[0102] For the Nth group of passable regions, take the endpoint of the optimal passable region in the (N-1)th group of passable regions as the starting point, and determine the passage cost of the Nth group of passable regions, where N is an integer greater than 1.

[0103] In some embodiments, the target obstacle includes a first obstacle and / or a second obstacle, and the device further includes:

[0104] The actual obstacle information acquisition module is used to acquire information about actual obstacles before determining the passable area within the road based on road environment information;

[0105] The passability determination module is used to determine whether the area between each actual obstacle is passable based on information about the actual obstacles.

[0106] The obstacle merging module is used to merge the actual obstacles corresponding to the impassable area to obtain at least one first obstacle, and to use the unmerged actual obstacles as second obstacles. The areas between the first and second obstacles, the areas between the first obstacles, and the areas between the second obstacles are all passable.

[0107] In some embodiments, the passability determination module is specifically used for:

[0108] When it is determined, based on information about the actual obstacles, that two adjacent actual obstacles meet the preset passage conditions, the area between the two adjacent actual obstacles is deemed passable; otherwise, the area between the two adjacent actual obstacles is deemed impassable.

[0109] The preset passage conditions include at least one of the following:

[0110] The longitudinal distance between two adjacent actual obstacles is greater than the safe length of the vehicle.

[0111] The lateral distance between two adjacent actual obstacles is greater than the first safe width of the vehicle;

[0112] The sum of the longitudinal and lateral distances between two adjacent actual obstacles is greater than the second safe width of the vehicle, wherein the longitudinal distance is parallel to the direction of road traffic and the lateral distance is perpendicular to the longitudinal distance.

[0113] In some embodiments, the passability determination module is specifically used for:

[0114] Based on information about the actual obstacles, determine the bounding box of each actual obstacle;

[0115] Determine whether the areas between each bounding box are passable.

[0116] In some embodiments, the vehicle information includes the vehicle's position and width, and the passage information includes the passage's position and width; the passage cost determination module 203 is specifically used for:

[0117] Based on the vehicle width and the passage width, determine the first passage cost for the passage width;

[0118] Based on the vehicle's position and the passage's position, determine the first lateral distance and the second longitudinal distance between the vehicle and the passable area at the starting point, wherein the longitudinal distance is parallel to the road's direction of travel, and the lateral distance is perpendicular to the longitudinal distance.

[0119] Based on the first distance and the second distance, determine the vehicle's pose and the second passage cost for lateral movement;

[0120] The sum of the first passage cost and the second passage cost is determined as the passage cost.

[0121] In some embodiments, a first passage cost for the passage width is determined based on the vehicle width and the passage width, including:

[0122] The first passage cost is calculated using the following cost function:

[0123]

[0124] Wherein, MAX_COST is the preset maximum value of the first passage cost, w0 is the width threshold when the first passage cost is 0, w is the channel width, and w_v is the sum of the vehicle width and the preset safety distance.

[0125] In some embodiments, determining the vehicle pose and a second passage cost for lateral movement based on a first distance and a second distance includes:

[0126] The second passage cost is calculated using the following cost function:

[0127]

[0128] Where K is the balance coefficient between the second passage cost and the first passage cost, l is the first distance, and s is the second distance.

[0129] The vehicle passable area determination device disclosed in the above embodiments can execute the vehicle passable area determination method disclosed in the above embodiments and has the same or corresponding beneficial effects. To avoid repetition, it will not be described again here.

[0130] This disclosure also provides an electronic device, including: a memory and one or more processors; wherein the memory is communicatively connected to the one or more processors, and the memory stores instructions that can be executed by the one or more processors. When the instructions are executed by the one or more processors, the electronic device is used to implement the vehicle passable area determination method described in any embodiment of this disclosure.

[0131] Figure 6 This is a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure. For example... Figure 6As shown, the electronic device 300 includes a central processing unit (CPU) 301, which can execute various processes described in the foregoing embodiments according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage section 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0132] The following components are connected to I / O interface 305: an input section 306 including a keyboard, mouse, etc.; an output section 307 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card, modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to I / O interface 305 as needed. A removable medium 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 310 as needed so that computer programs read from it can be installed into storage section 308 as needed.

[0133] In particular, according to embodiments of this disclosure, the methods described above can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program tangibly contained on a readable medium thereof, the computer program containing program code for performing the aforementioned obstacle avoidance method. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311.

[0134] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0135] The units or modules described in the embodiments of this disclosure can be implemented in software or hardware. The described units or modules can also be located in a processor, and the names of these units or modules do not necessarily constitute a limitation on the unit or module itself.

[0136] In addition, this disclosure also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the apparatus described in the above embodiments; or it may be a standalone computer-readable storage medium not assembled into the device. The computer-readable storage medium stores computer-executable instructions, which, when executed by a computing device, can be used to implement the vehicle passable area determination method described in any embodiment of this disclosure.

[0137] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0138] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining a vehicle-accessible area, characterized in that, include: Based on road environment information, a passable area within the road is determined, wherein the passable area includes a first passable area between target obstacles and / or a second passable area between the target obstacles and the road boundary; Obtain vehicle information and access information for the passable area; Based on the vehicle information and the channel information, the passage cost of the passable area is determined, and the passage cost is used to characterize the safety feasibility and / or driving convenience of vehicle passage; The passable area with the lowest passage cost is determined as the optimal passable area; The vehicle information includes the vehicle's position and width, and the passage information includes the passage's position and width. Based on the vehicle information and the passage information, the passage cost of the passable area is determined, including: Based on the vehicle width and the passage width, determine the first passage cost of the passage width; Based on the vehicle's position and the passage's position, determine the first lateral distance and the second longitudinal distance between the vehicle's starting point and the passable area, wherein the longitudinal direction is parallel to the road's direction of travel, and the lateral direction is perpendicular to the longitudinal direction. Based on the first distance and the second distance, determine the vehicle pose and the second passage cost for lateral movement; The sum of the first passage cost and the second passage cost is determined as the passage cost.

2. The method according to claim 1, characterized in that, The road environment information includes road information and target obstacle information. Based on the road environment information, the passable area within the road is determined, including: Based on the road information, the road boundaries are determined; Based on the information of the road boundary and the target obstacle, the target obstacle within the road is determined; Based on information about target obstacles within the road, a first passable area is determined; and / or, based on information about the road boundary and target obstacles within the road, a second passable area is determined.

3. The method according to claim 2, characterized in that, Obtaining the access information of the passable area includes: Based on the information of the road boundary and the target obstacles within the road, it is determined that the target obstacles have overlapping lateral projections on the road boundary, wherein the lateral projection is perpendicular to the road traffic direction. The first passable area and the corresponding second passable area between the overlapping target obstacles projected laterally on the road boundary are considered as a set of passable areas. Obtain the passage information of the set of passable areas.

4. The method according to claim 3, characterized in that, The method further includes: Arrange the passable areas of each group according to the direction of travel of this vehicle; For the first group of passable areas, the passage cost of the first group of passable areas is determined from the current position of the vehicle. For the Nth group of passable areas, the passage cost of the Nth group of passable areas is determined by taking the end point of the optimal passable area in the (N-1)th group of passable areas as the starting point, where N is an integer greater than 1.

5. The method according to claim 1, characterized in that, The target obstacle includes a first obstacle and / or a second obstacle. Before determining the passable area within the road based on road environment information, the method further includes: Obtain information about actual obstacles; Based on the information of the actual obstacles, determine whether the area between each actual obstacle is passable; The actual obstacles corresponding to the impassable areas are merged to obtain at least one first obstacle, and the unmerged actual obstacles are used as the second obstacles. The areas between the first obstacle and the second obstacle, the areas between the first obstacles, and the areas between the second obstacles are all passable.

6. The method according to claim 5, characterized in that, Based on the information about the actual obstacles, determine whether the area between each actual obstacle is passable, including: When it is determined, based on the information of the actual obstacles, that two adjacent actual obstacles meet the preset passage conditions, the area between the two adjacent actual obstacles is determined to be passable; otherwise, the area between the two adjacent actual obstacles is determined to be impassable. The preset passage conditions include at least one of the following: The longitudinal distance between two adjacent actual obstacles is greater than the safe length of the vehicle. The lateral distance between two adjacent actual obstacles is greater than the first safe width of the vehicle; The sum of the longitudinal and lateral distances between two adjacent actual obstacles is greater than the second safe width of the vehicle, wherein the longitudinal distance is parallel to the road traffic direction and the lateral distance is perpendicular to the longitudinal distance.

7. The method according to claim 5, characterized in that, Based on the information about the actual obstacles, determine whether the area between each actual obstacle is passable, including: Based on the information of the actual obstacles, the bounding box of each actual obstacle is determined; Determine whether the areas between the bounding boxes are passable.

8. The method according to claim 1, characterized in that, Based on the vehicle width and the passage width, the first passage cost for the passage width is determined, including: The first passage cost is calculated using the following cost function: ； in, This is the preset maximum value of the first passage cost. The width threshold where the first passage cost is 0. For channel width, It is the sum of the width of the vehicle and the preset safety distance.

9. The method according to claim 1, characterized in that, Based on the first distance and the second distance, the vehicle pose and the second passage cost for lateral movement are determined, including: The second passage cost is calculated using the following cost function: ； in, This is the balance coefficient between the second passage cost and the first passage cost. For the first distance, This is the second distance.

10. A device for determining a vehicle passable area, characterized in that, include: The passable area determination module is used to determine the passable area within the road based on road environment information, wherein the passable area includes a first passable area between target obstacles and / or a second passable area between the target obstacles and the road boundary; The information acquisition module is used to acquire vehicle information and access information of the passable area; The passage cost determination module is used to determine the passage cost of the passable area based on the vehicle information and the channel information. The passage cost is used to characterize the safety feasibility and / or driving convenience of vehicle passage. The passable area selection module is used to determine the passable area with the lowest passage cost as the optimal passable area; The vehicle information includes the vehicle's position and width, and the passage information includes the passage's position and width. Based on the vehicle information and the passage information, the passage cost of the passable area is determined, including: Based on the vehicle width and the passage width, determine the first passage cost of the passage width; Based on the vehicle's position and the passage's position, determine the first lateral distance and the second longitudinal distance between the vehicle's starting point and the passable area, wherein the longitudinal direction is parallel to the road's direction of travel, and the lateral direction is perpendicular to the longitudinal direction. Based on the first distance and the second distance, determine the vehicle pose and the second passage cost for lateral movement; The sum of the first passage cost and the second passage cost is determined as the passage cost.

11. An electronic device, characterized in that, include: Memory and one or more processors; The memory is communicatively connected to the one or more processors, and the memory stores instructions that can be executed by the one or more processors. When the instructions are executed by the one or more processors, the electronic device is used to implement the vehicle passable area determination method as described in any one of claims 1-9.

12. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that, When the computer-executable instructions are executed by a computing device, they can be used to implement the method for determining the vehicle passable area as described in any one of claims 1-9.

Images