Vehicle path planning method, device, electronic device, and storage medium

Abstract

The present application discloses a vehicle path planning method, device, electronic device, and storage medium, the method comprising: obtaining basic path planning information of the vehicle, specifically including the start and end point information of the expected trajectory and the road network information of the high-precision map; using the basic path planning information and the cost function of the road-level path planning to perform road-level path planning, and obtain the road-level path planning result; segmenting the road-level path planning result according to the preset segmentation strategy to obtain multiple road segments; based on each road segment, using the cost function of the lane-level path planning to perform lane-level path planning, obtain the lane-level path planning result corresponding to each road segment, and thereby determine the final path planning result of the vehicle. The present application takes into account the cost of autonomous driving behavior, and sets cost functions for road-level path planning and lane-level path planning respectively, so as to obtain a lane-level driving path that meets the current expectations of the autonomous driving vehicle and is globally optimal.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a vehicle path planning method, device, electronic device, and storage medium. Background Art

[0002] In the field of autonomous driving, high-precision maps have become an increasingly important part of autonomous driving components with their rich map and road network information. However, rich map and road network information cannot directly meet the needs of autonomous driving. Most relevant personnel will perform secondary processing on the information provided by high-precision maps, such as path planning based on the road network information provided by high-precision maps.

[0003] However, the consideration of lane-level path planning in the prior art does not take into account whether the path is suitable for autonomous driving vehicles, or only performs lane-level path planning based on simple rules, which fails to obtain the optimal path planning result. Summary of the invention

[0004] Embodiments of the present application provide a vehicle path planning method, device, electronic device, and storage medium to improve the effect of lane-level path planning.

[0005] The present application embodiment adopts the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a vehicle path planning method, wherein the method comprises:

[0007] Obtaining basic path planning information for the vehicle, the basic path planning information including the start and end point information of the expected trajectory and the road network information of the high-precision map;

[0008] Using the path planning basic information of the vehicle and the cost function of the road-level path planning, the vehicle is subjected to road-level path planning to obtain a road-level path planning result;

[0009] Segmenting the road-level path planning result according to a preset segmentation strategy to obtain a plurality of road segments;

[0010] Based on each road segment, lane-level path planning is performed on the vehicle using a cost function of lane-level path planning to obtain a lane-level path planning result corresponding to each road segment;

[0011] The final path planning result of the vehicle is determined according to the lane-level path planning results corresponding to each road segment.

[0012] Optionally, the obtaining of basic path planning information of the vehicle includes:

[0013] Obtain the starting and ending point information of the vehicle's expected trajectory;

[0014] According to the starting and ending point information of the expected trajectory, the road network information of the corresponding high-precision map is obtained.

[0015] Optionally, the cost function of the road-level path planning is constructed in the following way:

[0016] Determining a first cost parameter corresponding to the cost function of the road-level path planning, the first cost parameter comprising at least one of a path distance, a road-level speed, and a driving direction;

[0017] Assigning a corresponding weight to each of the first cost parameters;

[0018] A cost function for the road-level path planning is constructed according to the first cost parameters and the weights corresponding to the first cost parameters.

[0019] Optionally, the road-level path planning result includes a plurality of target roads, and the road-level path planning result is segmented according to a preset segmentation strategy to obtain a plurality of road segments including:

[0020] The plurality of target roads are divided into a plurality of road segments according to preset separation areas between the plurality of target roads.

[0021] Optionally, the cost function of the lane-level path planning is constructed in the following manner:

[0022] Determining a second cost parameter corresponding to the cost function of the lane-level path planning, the second cost parameter comprising at least one of lane-changing difficulty, lane-changing feasibility, and lane-level speed;

[0023] assigning a corresponding weight to each of the second cost parameters;

[0024] A cost function for the lane-level path planning is constructed according to the second cost parameters and the weights corresponding to the second cost parameters.

[0025] Optionally, the lane-level path planning is performed on the vehicle based on each road segment using a cost function of the lane-level path planning to obtain a lane-level path planning result corresponding to each road segment, including:

[0026] Determine cost function values ​​of multiple lanes corresponding to a target road segment using a cost function of lane-level path planning, wherein the target road segment is any one of the multiple road segments;

[0027] A lane-level path planning result corresponding to the target road segment is determined according to cost function values ​​of multiple lanes corresponding to the target road segment.

[0028] Optionally, the road segment includes a current road segment and a next road segment, the lane-level path planning result corresponding to the current road segment includes a plurality of target lanes, and the lane-level path planning is performed on the vehicle based on each road segment using a cost function of the lane-level path planning, and the lane-level path planning result corresponding to each road segment is obtained, including:

[0029] Determine, by using the cost function of the lane-level path planning, a cost function value of entering each lane corresponding to the next road segment from each target lane corresponding to the current road segment;

[0030] According to the cost function values ​​of each target lane corresponding to the current road segment entering each lane corresponding to the next road segment, a final lane-level path planning result corresponding to the current road segment is determined.

[0031] In a second aspect, an embodiment of the present application further provides a path planning device for a vehicle, wherein the device comprises:

[0032] An acquisition unit, used to acquire basic path planning information of the vehicle, wherein the basic path planning information includes the start and end point information of the expected trajectory and the road network information of the high-precision map;

[0033] A road-level path planning unit, configured to perform road-level path planning on the vehicle by using the basic path planning information of the vehicle and a cost function of the road-level path planning to obtain a road-level path planning result;

[0034] A segmentation unit, used to segment the road-level path planning result according to a preset segmentation strategy to obtain a plurality of road segments;

[0035] A lane-level path planning unit, configured to perform lane-level path planning for the vehicle based on each road segment using a lane-level path planning cost function to obtain a lane-level path planning result corresponding to each road segment;

[0036] The determination unit is used to determine the final path planning result of the vehicle according to the lane-level path planning results corresponding to each road segment.

[0037] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0038] Processor; and

[0039] A memory arranged to store computer executable instructions which, when executed, cause the processor to perform any of the methods described above.

[0040] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes any of the aforementioned methods.

[0041] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the path planning method of the vehicle in the embodiments of the present application first obtains the basic path planning information of the vehicle, and the basic path planning information includes the start and end point information of the expected trajectory and the road network information of the high-precision map; then, the basic path planning information of the vehicle and the cost function of the road-level path planning are used to perform road-level path planning on the vehicle to obtain the road-level path planning result; then, according to the preset segmentation strategy, the road-level path planning result is segmented to obtain multiple road segments; then, based on each road segment, the lane-level path planning cost function is used to perform lane-level path planning on the vehicle to obtain the lane-level path planning result corresponding to each road segment; finally, the final path planning result of the vehicle is determined according to the lane-level path planning result corresponding to each road segment. The path planning method of the vehicle in the embodiments of the present application takes into account the cost of autonomous driving behavior, and sets corresponding cost functions for road-level path planning and lane-level path planning, respectively, so that a lane-level driving path that meets the current expectations of the autonomous driving vehicle and is globally optimal can be obtained, thereby improving the lane-level path planning effect of the autonomous driving vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0043] Figure 1 A schematic diagram of a process flow of a vehicle path planning method in an embodiment of the present application;

[0044] Figure 2 This is a schematic diagram of the structure of a vehicle path planning device according to an embodiment of the present application;

[0045] Figure 3 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0047] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0048] The present application embodiment provides a vehicle path planning method, such as Figure 1 As shown, a flow chart of a vehicle path planning method in an embodiment of the present application is provided, and the method at least includes the following steps S110 to S150:

[0049] Step S110, obtaining basic path planning information of the vehicle, wherein the basic path planning information includes the start and end point information of the expected trajectory and the road network information of the high-precision map.

[0050] When performing path planning for an autonomous driving vehicle, the embodiments of the present application need to first obtain basic path planning information for the vehicle, which may include the starting and ending point location information of the vehicle's expected travel as a basis for path planning, and may also include road network information provided by a high-precision map. The road network information here may specifically include the structure of the roads, the connectivity between the roads, and the lane information on each road.

[0051] Step S120, using the path planning basic information of the vehicle and the cost function of the road-level path planning, perform road-level path planning on the vehicle to obtain a road-level path planning result.

[0052] The cost function of road-level path planning can be defined in advance based on the driving expectations of the autonomous driving vehicle at the road level, and can be flexibly set according to the actual scenario, and is not specifically limited here.

[0053] By combining the cost function of the above-mentioned road-level path planning with the basic information of the vehicle's path planning, the preset road-level path planning algorithm can be used to solve and obtain the global optimal road-level path planning result. The road-level path planning result represents the minimum value of the cost function of the road-level path planning. The result should be unique and contain road-level driving information, such as going straight from road A to road B, turning right from road B to enter road C, etc.

[0054] The above-mentioned preset road-level path planning algorithm can be implemented, for example, by using the A* algorithm, which is a commonly used path finding and graph traversal algorithm with good performance and accuracy. Of course, those skilled in the art can also flexibly select other road-level path planning algorithms according to actual needs, such as the D* algorithm or the LPA* (Life Planning A*) algorithm, etc., which are not specifically limited here.

[0055] Step S130, segmenting the road-level path planning result according to a preset segmentation strategy to obtain a plurality of road segments.

[0056] After obtaining the road-level path planning result, the embodiment of the present application also needs to segment the global optimal road-level path planning result according to a certain segmentation strategy to obtain multiple road segments. The setting of the segmentation strategy should, on the one hand, facilitate the realization that the path planning result of each segment is optimal, and on the other hand, ensure the overall efficiency of the path planning. Of course, those skilled in the art can flexibly set the specific segmentation strategy according to actual needs, and no specific limitation is made here.

[0057] Step S140, based on each road segment, lane-level path planning is performed on the vehicle using a cost function of lane-level path planning to obtain a lane-level path planning result corresponding to each road segment.

[0058] The cost function of lane-level path planning can also be defined in advance based on the expected driving conditions of the autonomous vehicle at the lane level, and can also be flexibly set according to the actual scenario.

[0059] Since each road segment often contains multiple lanes, it is necessary to further perform lane-level path planning based on the road-level path planning results to determine the best lane for the vehicle to travel. Specifically, for each road segment, the cost function of the lane-level path planning defined above is used to solve the optimal lane-level path planning result for each road segment. The lane-level path planning result represents the minimum value of the cost function values ​​of all lane-level path planning corresponding to the road segment.

[0060] Step S150, determining a final path planning result of the vehicle according to the lane-level path planning results corresponding to each road segment.

[0061] Through the above steps, the best driving lane corresponding to each road segment can be determined respectively. Finally, the best driving lanes of each road segment are spliced ​​together in sequence to obtain the final lane-level path planning result of the vehicle. The lane-level path planning result can be expressed as: going straight from lane a3 of road A to lane b3 of road B, changing lanes from lane b3 of road B to lane b1, turning right from lane b1 of road B to lane c1 of road C, etc.

[0062] It should be noted that the vehicle path planning method of the embodiment of the present application can be used in any road network model that describes the connection relationship of the road network. Only the road-level connection relationship is required for road-level planning, and only the lane boundary information is required for lane-level planning, and no directed boundary information is required. Therefore, the versatility and applicability will be wider.

[0063] The vehicle path planning method of the embodiment of the present application takes into account the cost of autonomous driving behavior, and sets corresponding cost functions for road-level path planning and lane-level path planning, respectively, so as to obtain a lane-level driving path that meets the current expectations of the autonomous driving vehicle and is globally optimal, thereby improving the lane-level path planning effect of the autonomous driving vehicle.

[0064] In one embodiment of the present application, the obtaining of basic information for path planning of the vehicle includes: obtaining the starting and ending point information of the expected trajectory of the vehicle; and obtaining the road network information of the corresponding high-precision map based on the starting and ending point information of the expected trajectory.

[0065] When acquiring the basic information for the vehicle's path planning, the embodiment of the present application may first acquire the start and end point information of the vehicle's expected trajectory, that is, the vehicle's departure position and arrival position. Based on the start and end point information of the expected trajectory, the area that the vehicle's driving path may pass through may be roughly determined, and based on this, the road network information provided by the local high-precision map corresponding to the area may be further acquired. Of course, it should be noted that in order to ensure the effect of path planning, the area covered by the road network information may be appropriately larger than the area covered by the start and end point information of the expected trajectory.

[0066] For example, based on the expected starting and ending point position coordinates of the vehicle, a circular area is determined in the high-precision map, and the circular area should at least pass through or cover the starting and ending point position coordinates of the vehicle.

[0067] In one embodiment of the present application, the cost function of the road-level path planning is constructed in the following manner: determining a first cost parameter corresponding to the cost function of the road-level path planning, the first cost parameter including at least one of path distance, road-level speed and driving direction; assigning a corresponding weight to each of the first cost parameters; and constructing the cost function of the road-level path planning based on the first cost parameter and the weights corresponding to each of the first cost parameters.

[0068] The cost function of the road-level path planning of the embodiment of the present application can be constructed based on the expected driving of the autonomous driving vehicle at the road level. Specifically, when performing global planning at the road level, the factors that need to be considered generally include path distance, road-level speed, and driving direction. Of course, those skilled in the art can also flexibly set the first cost parameters of other dimensions according to actual needs, which are not listed here one by one.

[0069] The path distance can be understood as the total length traveled from the expected starting position along each planned road. For road-level driving expectations, the shorter the path distance, the better. The road-level speed can be understood as the average speed that can be achieved by driving on each planned road. For road-level driving expectations, the higher the road-level speed, the better. The driving direction can include straight, right turn, left turn, and U-turn. For road-level driving expectations, the priority order of several situations is: straight > right turn > left turn > U-turn. The higher the priority, the easier it is for the vehicle to execute this driving strategy, and therefore the smaller the cost. Of course, it should be noted that the above priority order can be flexibly adjusted according to the actual scenario.

[0070] Based on the first cost parameters of the above-mentioned dimensions, the cost function of the road-level path planning in the embodiment of the present application can be specifically expressed as:

[0071] Gloabl Road Cost

[0072] =w1*distance+w2*go straight+w3*go left+w4*go right+w5*u turn+w5*roadspeed, (1)

[0073] Among them, distance represents the path distance, go straight represents going straight, go left represents turning left, go right represents turning right, u turn represents turning around, road speed represents the road-level speed, and w1-w5 are the weights corresponding to each first cost parameter.

[0074] The cost function of the above road-level path planning takes into account the cost of autonomous driving behavior at the road level. The specific route and road passing difficulty can be achieved by adjusting the corresponding weights.

[0075] In one embodiment of the present application, the road-level path planning result includes multiple target roads, and the road-level path planning result is segmented according to a preset segmentation strategy to obtain multiple road segments, including: dividing the multiple target roads into multiple road segments according to preset separation areas between the multiple target roads.

[0076] A segmentation strategy adopted in the embodiment of the present application can be to segment or group multiple target roads included in the road-level path planning result based on a preset separation area to obtain multiple road segments [1, N]. The preset separation area can be defined as an intersection area, and the intersection area can divide the road into multiple road segments in a geometric separation manner. For example, if there is one intersection in road A, then road A will be divided into two road segments. If there are two intersections in road A, then it will be divided into three road segments, and so on.

[0077] Since the division of roads in high-precision maps is more detailed, each road segment obtained by the above-mentioned intersection division may include multiple small road segments defined in the high-precision map. Therefore, a road segment in the embodiment of the present application can also be regarded as a road combination.

[0078] In one embodiment of the present application, the cost function of the lane-level path planning is constructed in the following manner: determining a second cost parameter corresponding to the cost function of the lane-level path planning, the second cost parameter including at least one of lane changing difficulty, lane changing feasibility, and lane-level speed; assigning a corresponding weight to each of the second cost parameters; and constructing the cost function of the lane-level path planning based on the second cost parameters and the weights corresponding to each of the second cost parameters.

[0079] The cost function of lane-level path planning in the embodiment of the present application can be constructed based on the driving expectations of the autonomous driving vehicle at the lane level. Specifically, when performing lane-level path planning, the factors that need to be considered mainly include lane change difficulty, lane change feasibility, and lane-level speed. Of course, those skilled in the art can also flexibly set the second cost parameters of other dimensions according to actual needs, which are not listed here one by one.

[0080] Lane changing difficulty can be understood as the difficulty of switching from the current lane to another lane. It can be specifically measured based on the length of the path before changing lanes. If the length of the path taken when switching from the current lane to another lane is shorter, it means that it is not easy to change lanes within this shorter distance. Therefore, the lane changing difficulty is greater. Conversely, the lane changing difficulty is less. For lane-level driving expectations, the smaller the lane changing difficulty, the smaller the cost.

[0081] The feasibility of lane change can be understood as whether it is allowed to switch from the current lane to another lane. For example, vehicles are prohibited from crossing the solid lane line, while vehicles are allowed to cross the dashed lane line to overtake. Therefore, the feasibility of lane change can be determined based on the real and virtual conditions of the lane lines on both sides of the vehicle. Allowing lane change has a lower cost than not allowing lane change.

[0082] The lane-level speed can be understood as the maximum driving speed that each lane can reach. For lane-level driving expectations, the higher the lane-level speed, the lower the cost.

[0083] Based on the second cost parameters of the above-mentioned dimensions, the cost function of the road-level path planning in the embodiment of the present application, Gloabl lane Cost, can be specifically expressed as:

[0084] Gloabl lane Cost=g1*change lane difficulty+g2*can change lane+g3*lane speed limit, (2)

[0085] Among them, change lane difficulty indicates the difficulty of lane changing, can change lane indicates the feasibility of lane changing, lane speed limit indicates the lane-level speed, and g1-g3 are the weights corresponding to each second cost parameter.

[0086] The cost function of the lane-level path planning mentioned above takes into account the cost of lane-level autonomous driving behavior. The specific route and lane passing difficulty can be achieved by adjusting the corresponding weights, thereby avoiding problems such as low traffic efficiency, urgent lane changes, and complex scenarios such as too many turning scenarios.

[0087] In one embodiment of the present application, lane-level path planning is performed on the vehicle based on each road segment using a cost function of lane-level path planning to obtain lane-level path planning results corresponding to each road segment, including: using the cost function of lane-level path planning to determine cost function values ​​of multiple lanes corresponding to a target road segment, where the target road segment is any one of the multiple road segments; and determining the lane-level path planning result corresponding to the target road segment based on the cost function values ​​of the multiple lanes corresponding to the target road segment.

[0088] As mentioned above, a road segment may correspond to multiple lanes. The ultimate goal of lane-level path planning is to determine the optimal driving lane in each road segment. Therefore, for any target road segment, when performing lane-level path planning, the cost function of the above lane-level path planning can be used to first calculate the cost function value of each lane contained in the target road segment, and then the optimal target lane is selected according to the size of the cost function value corresponding to each lane as the lane-level path planning result corresponding to the target road segment.

[0089] For example, road segment A includes lane a1, lane a2, and lane a3. The cost function of lane-level path planning is used to calculate the cost function values ​​of lane a1, lane a2, and lane a3, which are 5, 8, and 10 respectively. Then lane a1 can be used as the optimal lane for road segment A.

[0090] In addition, it should be noted that the cost function value of the lane-level path planning in the embodiment of the present application represents the cost required to enter another lane from one lane, and the cost function value will be assigned to the lane being entered. For example, after comprehensively considering the second cost parameters of various dimensions such as lane change difficulty, lane change feasibility, and lane-level speed, it is calculated that the cost required to enter lane b1 from lane a1 is 5, then the corresponding cost function value of lane b1 can be determined to be 5.

[0091] In one embodiment of the present application, the road segment includes a current road segment and a next road segment, the lane-level path planning result corresponding to the current road segment includes multiple target lanes, and the lane-level path planning is performed on the vehicle based on each road segment using a cost function of the lane-level path planning to obtain the lane-level path planning results corresponding to each road segment, including: using the cost function of the lane-level path planning, determining the cost function value of entering each lane corresponding to the next road segment from each target lane corresponding to the current road segment; and determining the final lane-level path planning result corresponding to the current road segment according to the cost function value of entering each lane corresponding to the next road segment from each target lane corresponding to the current road segment.

[0092] In actual applications, the optimal lane determined in a road segment may not be unique. For example, road segment A contains lane a1, lane a2, and lane a3, and the corresponding cost function values ​​are 5, 5, and 8, respectively. It can be seen that the cost function values ​​of lane a1 and lane a2 are the same, indicating that for road segment A, lane a1 and lane a2 are both target lanes, that is, they can both be regarded as feasible optimal lanes.

[0093] For the above situation, the cost function of lane-level path planning can be used to further determine the cost function values ​​of entering each lane [b1, b2, b3] corresponding to the next road segment such as road segment B from each target lane [a1, a2] corresponding to the road segment A. As shown in Table 1 below, the cost function values ​​of entering each lane [b1, b2, b3] from each target lane [a1, a2] are given. It can be seen that the cost function value of entering lane b1 of road segment B from lane a1 of road segment A is the smallest, and then the optimal lane of road segment A can be determined to be a1, and the optimal lane of road segment B can also be determined to be b1, that is, lane a1→lane b1 is the best lane-level driving path for road segment A and road segment B.

[0094] Table 1

[0095]

[0096] Through the above method, the optimal lane-level path planning result corresponding to each road segment can be determined. Of course, there is also an extreme case where no unique lane-level path planning result is determined when reaching the destination, which means that all the lane-level path planning results currently obtained meet the requirements, so any lane that meets the requirements can be selected for driving.

[0097] The above description only takes the case where the cost function values ​​of two lanes are the same as an example. In actual application, the above embodiment can be applied to the case where the cost function values ​​of more lanes are the same, which will not be repeated here.

[0098] The above-mentioned embodiment of the present application divides the road into multiple road segments when performing lane-level path planning, and plans from beginning to end based on the adjacency relationship of multiple road segments, so as to obtain the optimal solution in each road segment, and then obtain the global optimal solution of lane-level path planning.

[0099] In addition, it should be noted that the above embodiment mainly uses the multiple optimal target lanes corresponding to the current road segment as the basis for lane-level path planning for the next road segment. However, there is another situation where, for road segment A, although the cost function value of lane a3 is relatively large, it can only indicate the cost of entering lane a3 from the optimal lane of the previous road segment, and cannot represent the situation of entering the next road segment from lane a3.

[0100] Taking the above situation into consideration, when conducting specific planning, it is not necessary to consider the optimal lane planned for each road segment, but to plan as a whole, that is, to use the cost function of lane-level path planning to calculate the possible cost function values ​​of each lane in all road segments from the starting point to the end point, and then calculate the sum of the cost function values ​​of the corresponding lanes based on all possible lane-level driving paths, and finally select the lane-level driving path composed of lanes with the smallest sum of cost function values ​​as the final lane-level path planning result.

[0101] For example, suppose there are three road segments [A, B, C] from the starting point to the end point. Road segment A corresponds to lanes [a1, a2, a3], road segment B corresponds to lanes [b1, b2, b3], and road segment C corresponds to lanes [c1, c2, c3]. When a vehicle enters road segment A from road segment B, the cost function values ​​of the nine lane combinations {(a1, b1), (a2, b1), (a3, b1), ..., (a3, b3)} can be calculated. When a vehicle enters road segment B from road segment A, the cost function values ​​of the nine lane combinations {(a1, b1), (a2, b1), (a3, b1), ..., (a3, b3)} can be calculated. When segment B enters road segment C, the cost function values ​​of 9 lane combinations {(b1,c1), (b2,c1), (b3,c1), ..., (b3,c3)} can also be calculated. Finally, the cost function values ​​of these two lane combinations are added based on the common lane, such as (a1,b1) + (b1,c1), (a1,b1) + (b1,c2), (a2,b2) + (b2,c1) ... Finally, the optimal lane-level driving path is selected according to the minimum value after the addition of the cost function values.

[0102] Although this solution can ensure the overall optimality of the cost function value of lane-level path planning, compared with the aforementioned method of solving the optimal lane-level path planning result for each road segment, when there are many road segments, this solution for overall planning of the lane-level path requires a higher time cost and has a lower planning efficiency. In addition, for autonomous driving vehicles, when the cost function value of the lane-level planning result of one or some road segments is higher than the cost function value of other lanes in the road segment, it is necessary to face the risk of entering a lane with a relatively higher driving cost, so the stability and safety of the autonomous driving process are relatively poor. Of course, technical personnel in this field can flexibly choose which specific method to use for lane-level path planning according to actual needs.

[0103] The present application also provides a vehicle path planning device 200, such as Figure 2 As shown, a schematic diagram of the structure of a vehicle path planning device according to an embodiment of the present application is provided, wherein the device 200 includes: an acquisition unit 210, a road-level path planning unit 220, a segmentation unit 230, a lane-level path planning unit 240, and a determination unit 250, wherein:

[0104] An acquisition unit 210 is used to acquire basic path planning information of the vehicle, wherein the basic path planning information includes the start and end point information of the expected trajectory and the road network information of the high-precision map;

[0105] A road-level path planning unit 220 is used to perform road-level path planning on the vehicle by using the path planning basic information of the vehicle and the cost function of the road-level path planning to obtain a road-level path planning result;

[0106] A segmentation unit 230, configured to segment the road-level path planning result according to a preset segmentation strategy to obtain a plurality of road segments;

[0107] A lane-level path planning unit 240 is used to perform lane-level path planning for the vehicle based on each road segment using a lane-level path planning cost function to obtain a lane-level path planning result corresponding to each road segment;

[0108] The determination unit 250 is used to determine the final path planning result of the vehicle according to the lane-level path planning results corresponding to each road segment.

[0109] In one embodiment of the present application, the acquisition unit 210 is specifically used to: acquire the start and end point information of the expected trajectory of the vehicle; and acquire the road network information of the corresponding high-precision map based on the start and end point information of the expected trajectory.

[0110] In one embodiment of the present application, the cost function of the road-level path planning is constructed in the following manner: determining a first cost parameter corresponding to the cost function of the road-level path planning, the first cost parameter including at least one of path distance, road-level speed and driving direction; assigning a corresponding weight to each of the first cost parameters; and constructing the cost function of the road-level path planning based on the first cost parameter and the weights corresponding to each of the first cost parameters.

[0111] In one embodiment of the present application, the road-level path planning result includes multiple target roads, and the segmentation unit 230 is specifically used to divide the multiple target roads into multiple road segments according to preset separation areas between the multiple target roads.

[0112] In one embodiment of the present application, the cost function of the lane-level path planning is constructed in the following manner: determining a second cost parameter corresponding to the cost function of the lane-level path planning, the second cost parameter including at least one of lane changing difficulty, lane changing feasibility, and lane-level speed; assigning a corresponding weight to each of the second cost parameters; and constructing the cost function of the lane-level path planning based on the second cost parameters and the weights corresponding to each of the second cost parameters.

[0113] In one embodiment of the present application, the lane-level path planning unit 240 is specifically used to: determine the cost function values ​​of multiple lanes corresponding to a target road segment using the cost function of the lane-level path planning, where the target road segment is any one of the multiple road segments; and determine the lane-level path planning result corresponding to the target road segment based on the cost function values ​​of the multiple lanes corresponding to the target road segment.

[0114] In one embodiment of the present application, the road segment includes a current road segment and a next road segment, and the lane-level path planning result corresponding to the current road segment includes multiple target lanes. The lane-level path planning unit 240 is specifically used to: use the cost function of the lane-level path planning to determine the cost function value of entering each lane corresponding to the next road segment from each target lane corresponding to the current road segment; determine the final lane-level path planning result corresponding to the current road segment according to the cost function value of entering each lane corresponding to the next road segment from each target lane corresponding to the current road segment.

[0115] It can be understood that the above-mentioned vehicle path planning device can implement the various steps of the vehicle path planning method provided in the aforementioned embodiment. The relevant explanations about the vehicle path planning method are applicable to the vehicle path planning device and will not be repeated here.

[0116] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 3 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0117] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0118] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0119] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a path planning device for the vehicle at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0120] Obtaining basic path planning information for the vehicle, the basic path planning information including the start and end point information of the expected trajectory and the road network information of the high-precision map;

[0121] Using the path planning basic information of the vehicle and the cost function of the road-level path planning, the vehicle is subjected to road-level path planning to obtain a road-level path planning result;

[0122] Segmenting the road-level path planning result according to a preset segmentation strategy to obtain a plurality of road segments;

[0123] Based on each road segment, lane-level path planning is performed on the vehicle using a cost function of lane-level path planning to obtain a lane-level path planning result corresponding to each road segment;

[0124] The final path planning result of the vehicle is determined according to the lane-level path planning results corresponding to each road segment.

[0125] The above application Figure 1The method performed by the vehicle path planning device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0126] The electronic device may also perform Figure 1 A method for executing a path planning device of a vehicle in the vehicle, and realizing the path planning device of the vehicle in Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0127] The present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 1 The method performed by the vehicle path planning device in the illustrated embodiment is specifically used to perform:

[0128] Obtaining basic path planning information for the vehicle, the basic path planning information including the start and end point information of the expected trajectory and the road network information of the high-precision map;

[0129] Using the path planning basic information of the vehicle and the cost function of the road-level path planning, the vehicle is subjected to road-level path planning to obtain a road-level path planning result;

[0130] Segmenting the road-level path planning result according to a preset segmentation strategy to obtain a plurality of road segments;

[0131] Based on each road segment, lane-level path planning is performed on the vehicle using a cost function of lane-level path planning to obtain a lane-level path planning result corresponding to each road segment;

[0132] The final path planning result of the vehicle is determined according to the lane-level path planning results corresponding to each road segment.

[0133] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0134] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0135] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0136] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0137] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0138] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0139] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0140] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0141] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0142] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A vehicle path planning method, wherein: The method comprises: Obtaining basic path planning information for the vehicle, the basic path planning information including the start and end point information of the expected trajectory and the road network information of the high-precision map; Using the path planning basic information of the vehicle and the cost function of the road-level path planning, the vehicle is subjected to road-level path planning to obtain a road-level path planning result; Segmenting the road-level path planning result according to a preset segmentation strategy to obtain a plurality of road segments; Based on each road segment, lane-level path planning is performed on the vehicle using a cost function of lane-level path planning to obtain a lane-level path planning result corresponding to each road segment; Determining a final path planning result of the vehicle according to the lane-level path planning results corresponding to each road segment; The road segment includes a current road segment and a next road segment, the lane-level path planning result corresponding to the current road segment includes a plurality of target lanes, and the lane-level path planning is performed on the vehicle based on each road segment using a cost function of the lane-level path planning, and the lane-level path planning result corresponding to each road segment includes: Determine, by using the cost function of the lane-level path planning, a cost function value of entering each lane corresponding to the next road segment from each target lane corresponding to the current road segment; According to the cost function values ​​of each target lane corresponding to the current road segment entering each lane corresponding to the next road segment, a final lane-level path planning result corresponding to the current road segment is determined.

2. The method of claim 1, wherein: The step of obtaining basic information of vehicle path planning includes: Obtain the starting and ending point information of the vehicle's expected trajectory; According to the starting and ending point information of the expected trajectory, the road network information of the corresponding high-precision map is obtained.

3. The method of claim 1, wherein: The cost function of the road-level path planning is constructed as follows: Determining a first cost parameter corresponding to the cost function of the road-level path planning, the first cost parameter comprising at least one of a path distance, a road-level speed, and a driving direction; Assigning a corresponding weight to each of the first cost parameters; A cost function for the road-level path planning is constructed according to the first cost parameters and the weights corresponding to the first cost parameters.

4. The method of claim 1, wherein: The road-level path planning result includes a plurality of target roads. The road-level path planning result is segmented according to a preset segmentation strategy to obtain a plurality of road segments including: The plurality of target roads are divided into a plurality of road segments according to preset separation areas between the plurality of target roads.

5. The method of claim 1, wherein: The cost function of the lane-level path planning is constructed as follows: Determining a second cost parameter corresponding to the cost function of the lane-level path planning, the second cost parameter comprising at least one of lane-changing difficulty, lane-changing feasibility, and lane-level speed; assigning a corresponding weight to each of the second cost parameters; A cost function for the lane-level path planning is constructed according to the second cost parameters and the weights corresponding to the second cost parameters.

6. The method of claim 1, wherein: The lane-level path planning is performed on the vehicle based on each road segment using the cost function of the lane-level path planning to obtain the lane-level path planning result corresponding to each road segment, including: Determine cost function values ​​of multiple lanes corresponding to a target road segment using a cost function of lane-level path planning, wherein the target road segment is any one of the multiple road segments; A lane-level path planning result corresponding to the target road segment is determined according to cost function values ​​of multiple lanes corresponding to the target road segment.

7. A vehicle path planning device, wherein: The device comprises: An acquisition unit, used to acquire basic path planning information of the vehicle, wherein the basic path planning information includes the start and end point information of the expected trajectory and the road network information of the high-precision map; A road-level path planning unit, configured to perform road-level path planning on the vehicle by using the basic path planning information of the vehicle and a cost function of the road-level path planning to obtain a road-level path planning result; A segmentation unit, used to segment the road-level path planning result according to a preset segmentation strategy to obtain a plurality of road segments; A lane-level path planning unit, configured to perform lane-level path planning for the vehicle based on each road segment using a lane-level path planning cost function to obtain a lane-level path planning result corresponding to each road segment; A determination unit, configured to determine a final path planning result of the vehicle according to the lane-level path planning results corresponding to each road segment; The road segment includes a current road segment and a next road segment, the lane-level path planning result corresponding to the current road segment includes a plurality of target lanes, and the lane-level path planning unit is specifically used for: Determine, by using the cost function of the lane-level path planning, a cost function value of entering each lane corresponding to the next road segment from each target lane corresponding to the current road segment; According to the cost function values ​​of each target lane corresponding to the current road segment entering each lane corresponding to the next road segment, a final lane-level path planning result corresponding to the current road segment is determined.

8. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method of any one of claims 1 to 6.

9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute any one of the methods of claims 1 to 6.

Images