Driving Route Planning Method, Device and Equipment

Abstract

The present application discloses a driving route planning method, apparatus, and electronic device. The method includes: identifying traffic scene information where the vehicle is located; determining reasonable driving space information of the vehicle according to the traffic scene information; obtaining a first planned route for the vehicle to travel; and determining a target driving route from the first planned route according to the reasonable driving space information. By adopting this processing method, the reasonable driving space of the vehicle (ego vehicle) is dynamically adjusted according to the driving perception information of the vehicle in the continuous behavior space in a strongly interactive environment, thereby realizing path pre-decision processing based on the actual traffic scene, and then planning a driving route within a reasonable space; therefore, the rationality of route planning can be effectively improved, and a safe, comfortable, highly efficient, and traffic-regulation-compliant route can be found, thereby improving the driving effect of the vehicle.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and particularly to a driving path planning method and apparatus, and an electronic device. Background Art

[0002] An autonomous vehicle, also known as a driverless vehicle, a computer-driven vehicle, or a wheeled mobile robot, is an intelligent vehicle that realizes driverless through a computer system, and has been widely popularized and applied in industries such as instant delivery and express delivery services.

[0003] During driving, an autonomous vehicle needs to make real-time path decisions for a highly interactive environment (surrounding obstacles, such as pedestrians, other vehicles, etc.) to find a safe, comfortable, highly efficient, and traffic-rule-compliant path. For autonomous vehicles, variable environments, road conditions, strong interactions, etc. all pose great challenges to autonomous driving algorithms.

[0004] In the process of implementing the present invention, the inventors found that the existing driving path planning solutions at least have the problem of unreasonable driving path planning. Summary of the Invention

[0005] This application provides a driving path planning method to solve the problem of unreasonable driving path planning existing in the prior art. This application also provides a driving path planning apparatus and an electronic device.

[0006] This application provides a driving path planning method, including:

[0007] Identifying traffic scene information where the vehicle is located;

[0008] Determining reasonable driving space information of the vehicle according to the traffic scene information;

[0009] Obtaining a first planned path for the vehicle to travel;

[0010] Determining a target driving path from the first planned path according to the reasonable driving space information.

[0011] Optionally, the identifying traffic scene information where the vehicle is located includes:

[0012] Obtaining environmental perception information of the space around the vehicle;

[0013] Identifying traffic scene information where the vehicle is located according to the environmental perception information.

[0014] Optionally, the identifying traffic scene information where the vehicle is located further includes:

[0015] Obtaining lane setting information of the current road;

[0016] Identifying the traffic scene information in which the vehicle is located according to the environmental perception information includes:

[0017] Identifying the intention information of the obstacle according to the environmental perception information;

[0018] Identifying the traffic scene information in which the vehicle is located according to the intention information of the obstacle and the lane setting information.

[0019] Optionally, identifying the traffic scene information in which the vehicle is located further includes:

[0020] Obtaining the vehicle driving route information;

[0021] The identifying the traffic scene information in which the vehicle is located according to the intention information of the obstacle and the lane setting information includes:

[0022] Identifying the traffic condition information of each lane according to the intention information of the obstacle and the lane setting information;

[0023] Identifying the traffic scene information in which the vehicle is located according to the traffic condition information of each lane and the vehicle driving route information.

[0024] Optionally, identifying the traffic scene information in which the vehicle is located includes:

[0025] Obtaining the vehicle position information and the traffic condition information;

[0026] Identifying the traffic scene information in which the vehicle is located according to the position information and the traffic condition information.

[0027] Optionally, determining the reasonable driving space information of the vehicle according to the traffic scene information adopts at least one of the following methods:

[0028] If the traffic scene information includes that all the same-direction lanes are blocked, then set the reasonable driving space to include the illegal driving lane;

[0029] If the traffic scene information includes that some of the same-direction lanes are blocked, then set the reasonable driving space to include the illegal driving lane adjacent to the unblocked lane;

[0030] If the traffic scene information includes that an obstacle occupies the current driving lane, then obtain the lane specification information of the current driving lane; according to the lane specification information, judge whether the current driving lane supports the vehicle to bypass the obstacle; if the above judgment result is yes, then set the reasonable driving space not to include the illegal driving lane adjacent to the current driving lane; if the above judgment result is no, then set the reasonable driving space to include the illegal driving lane adjacent to the current driving lane;

[0031] If the traffic scene information includes a single-lane blind bend in the same direction, obtain the lane specification information of the reverse lane; according to the lane specification information, determine the range information of the partial area of the reverse lane that can be used as a reasonable driving space; if the traffic scene information includes an obstruction in the target turning lane, set the reasonable driving space to include the first straight lane adjacent to the target turning lane and the second straight lane adjacent to the first straight lane;

[0032] If the traffic scene information includes that the target turning lane is unobstructed, set the reasonable driving space to include the target turning lane and the first straight lane adjacent to the target turning lane.

[0033] Optionally, it further includes:

[0034] Obtain the lane specification information of the unobstructed lane;

[0035] According to the lane specification information, determine whether the unobstructed lane supports vehicle detouring;

[0036] If the above judgment result is yes, set the reasonable driving space to not include the illegal driving lane adjacent to the unobstructed lane;

[0037] If the above judgment result is no, set the reasonable driving space to include the illegal driving lane adjacent to the unobstructed lane.

[0038] Optionally, the method further includes:

[0039] Obtain the environmental perception information of the space around the vehicle;

[0040] Then, the first planned path for the vehicle to travel is obtained by at least one of the following methods:

[0041] According to the environmental perception information, determine the escape path;

[0042] According to the environmental perception information, determine the first non-escape path;

[0043] According to the environmental perception information and the reasonable driving space information, obtain the second non-escape path planned within the reasonable driving space;

[0044] Among them, the non-escape path includes, but is not limited to: the path of its own lane, the left lane change path, the right lane change path, and the detour path.

[0045] Optionally, the determining the escape path according to the environmental perception information includes:

[0046] According to the environmental perception information, obtain the distance information between the vehicle and the vehicle in front;

[0047] determining whether a reversing operation can be performed according to the distance information;

[0048] If the above determination result is yes, an escape path is generated.

[0049] Optionally, determining a target driving path from the first planned path according to the reasonable driving space information includes:

[0050] Determine unreasonable space based on reasonable driving space information;

[0051] Screening out paths that intersect with the unreasonable space in the first planned path, and using the screened out paths as the second planned path;

[0052] A target driving path is selected from the second planned paths.

[0053] The present application also provides a driving path planning device, comprising:

[0054] A traffic scene recognition unit, used to recognize the traffic scene information in which the vehicle is located;

[0055] A reasonable driving space decision unit, used to determine reasonable driving space information of the vehicle according to the traffic scene information;

[0056] A path planning unit, used to obtain a first planned path for the vehicle to travel;

[0057] A path decision unit is used to determine a target driving path from the first planned path according to the reasonable driving space information.

[0058] The present application also provides an electronic device, comprising:

[0059] Memory and processor;

[0060] The memory is used to store a program for implementing the above-mentioned driving path planning method. The device is powered on and runs the program of the method through the processor.

[0061] The present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the computer-readable storage medium is run on a computer, the computer executes the above-mentioned various methods.

[0062] The present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the above-mentioned various methods.

[0063] Compared with the prior art, this application has the following advantages:

[0064] The driving path planning method provided by the embodiment of the present application identifies the traffic scene information where the vehicle is located; determines the reasonable driving space information of the vehicle according to the traffic scene information; obtains the first planned path to be traveled by the vehicle; and determines the target driving path from the first planned path according to the reasonable driving space information. By adopting this processing method, the reasonable driving space of the vehicle (ego vehicle) is dynamically adjusted according to the driving perception information of the vehicle in the continuous behavior space in a strongly interactive environment, thereby realizing the path pre-decision processing based on the actual traffic scene, and then planning the driving path within the reasonable space; therefore, the rationality of path planning can be effectively improved, and a path that is safe, comfortable to drive, has high traffic efficiency and does not violate traffic rules can be found, thereby improving the driving effect of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 is a flowchart of an embodiment of the driving path planning method provided by the present application;

[0066] Figure 2 is a schematic diagram of the scene of an embodiment of the driving path planning method provided by the present application;

[0067] Figures 3 to 10 is a schematic diagram of the reasonable driving space of an embodiment of the driving path planning method provided by the present application under different scenarios;

[0068] Figure 11 is a schematic diagram of a specific scene of an embodiment of the driving path planning method provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0069] Many specific details are set forth in the following description in order to provide a thorough understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of the present application. Therefore, the present application is not limited by the specific embodiments disclosed below.

[0070] In the present application, a driving path planning method and apparatus, and an electronic device are provided. Various solutions will be described in detail in the following embodiments.

[0071] First Embodiment

[0072] Please refer to Figure 1 , which is a flowchart of an embodiment of a driving path planning method provided by the present application. The execution subject of this method includes but is not limited to driverless vehicles, such as unmanned delivery vehicles, etc. A driving path planning method provided by the present application includes:

[0073] Step S101: Identify the traffic scene information where the vehicle is located.

[0074] The vehicle (ego vehicle) refers to the execution subject of the method, including but not limited to unmanned delivery vehicles, and may also be a logistics robot, etc. The traffic scene information is a general term for the information of the surrounding environment where the vehicle is located. Specific traffic scenes include but are not limited to: all lanes in the same direction are blocked, some lanes in the same direction are blocked, there are obstacles occupying the current driving lane, a blind bend in a single lane in the same direction, the target turning lane is blocked, and the target turning lane (referring to the lane to be entered, such as the right turning lane) is not blocked.

[0075] Figure 2 The application scenario diagram of the method provided by the embodiment of the present application is shown. During the driving process of the vehicle, the vehicle can identify the scene it is in through the scene recognition module; according to the scene where the vehicle is located, dynamically adjust the reasonable driving space of the vehicle; obtain various planned paths through the path planning module; and find the optimized path within the reasonable driving space.

[0076] It should be noted that the path planned by the method provided by the embodiment of the present application is a lane path, rather than the driving route to the destination. For example, the vehicle driving route refers to the driving route for the vehicle to reach the destination, such as driving from Haidian Bridge to Zhongguancun Avenue, and then from Lenovo Bridge to the Third Ring Road, etc.; while the path planned by the method provided by the embodiment of the present application refers to the lane path of which lane to take during driving on Zhongguancun Avenue.

[0077] In one example, step S101 may include the following sub-steps:

[0078] Step S1011: Obtain the environmental perception information of the space around the vehicle.

[0079] In specific implementation, the surrounding environment and obstacles can be sensed through sensors (such as lidar, cameras, etc.).

[0080] Step S1013: Identify the traffic scene information where the vehicle is located according to the environmental perception information.

[0081] For example, according to the environmental perception information, if the vehicle senses that it is driving at a sharp mountain bend, the traffic scene information where the vehicle is located is a blind bend in a single lane in the same direction.

[0082] Adopting this processing method enables the scene where the vehicle is located to be identified according to the environmental perception information of the surrounding space, so that traffic scene information with higher accuracy (such as within 2 meters) can be obtained. Therefore, the rationality of the driving path planning can be effectively improved.

[0083] In one example, step S101 may also include the following sub-steps:

[0084] Step S1012: Obtain the lane setting information of the current road.

[0085] Lane setting, also known as lane configuration or lane design, can be multiple lanes in the same direction or a single lane in the same direction. The lane setting information may include the number of straight lanes, the number of left-turn lanes, the number of right-turn lanes, etc.

[0086] Correspondingly, step S1013 may include the following sub-steps:

[0087] Step S1013-1: Identify the intention information of the obstacle according to the environmental perception information.

[0088] Specifically, when implemented, the type (vehicle, person, others, etc.), position, speed, etc. of the obstacle can be obtained according to the environmental perception information; the intention of the obstacle, such as long-term parking, congestion queuing, waiting for a traffic light, etc., can be obtained through the feature analysis of the obstacle (headlights, vehicle speed, other surrounding obstacles, etc., or pattern recognition based on deep learning).

[0089] Step S1013-3: Identify the traffic scene information where the vehicle is located according to the intention information of the obstacle and the lane setting information.

[0090] In one example, step S1013-3 may include the following sub-steps:

[0091] Step S1013-3-1a: Identify the traffic condition information of each lane according to the intention information of the obstacle and the lane setting information.

[0092] The traffic condition information of the lane refers to the lane driving road condition information, which can be whether the lane is blocked, whether there is an obstacle encroachment, whether there is construction, whether there is an accident, etc.

[0093] Step S1013-3-3a: Identify the traffic scene information where the vehicle is located according to the traffic condition information of each lane.

[0094] For example, if the vehicle is driving on a straight lane and all straight lanes are blocked, the traffic scene information where the vehicle is located is that all lanes in the same direction are blocked. For another example, if the vehicle is driving on a straight lane and there is a blocked straight lane and an unblocked straight lane, the traffic scene information where the vehicle is located is that some lanes in the same direction are blocked. For yet another example, if the vehicle is driving on straight lane 1 and there is a car accident or construction in front of straight lane 1, the traffic scene information where the vehicle is located is that there is an obstacle encroaching on the current driving lane.

[0095] In one example, step S101 may include the following sub-steps: Obtain the vehicle driving route information. As described above, the vehicle driving route refers to the driving route for the vehicle to reach the destination, such as from Haidian Bridge to Zhongguancun Avenue, and then from Lenovo Bridge to the Third Ring Road, etc.

[0096] Correspondingly, step S1013-3 may include the following sub-steps:

[0097] Step S1013-3-1b: Identify the traffic condition information of each lane according to the intention information of the obstacle and the lane setting information.

[0098] Step S1013-3-3b: Identify the traffic scenario information where the vehicle is located according to the traffic condition information of each lane and the vehicle driving route information.

[0099] The vehicle driving route information can be obtained through the vehicle navigation system. By integrating the traffic condition information of each lane and the vehicle driving route information, the traffic scenario where the vehicle is located can be obtained.

[0100] For example, if the vehicle is going straight and all the straight lanes are blocked, the traffic scenario information where the vehicle is located is that all the same-direction lanes are blocked. For another example, if the vehicle is going straight and some straight lanes are blocked while some are not, the traffic scenario information where the vehicle is located is that some of the same-direction lanes are blocked.

[0101] For example, if the vehicle is going to turn right at the intersection ahead and the right-turn lane is blocked, the traffic scenario information where the vehicle is located is that the target turning lane is blocked. For another example, if the vehicle is going to turn right at the intersection ahead and the right-turn lane is driving normally, the traffic scenario information where the vehicle is located is that the target turning lane is not blocked.

[0102] In another example, step S101 can be implemented in the following way: Obtain the vehicle position information and the traffic condition information; according to the position information and the traffic condition information, identify the traffic scenario information where the vehicle is located. Specifically, when implementing, the traffic condition information can be obtained from the map navigation system, and the position information in the vehicle position information and the traffic condition information is matched; according to the traffic condition information at the position where the match occurs, determine the traffic scenario information where the vehicle is located. By adopting this processing method, the traffic scenario information can be obtained more quickly, and therefore, the real-time performance of the driving route planning can be effectively improved.

[0103] Step S103: Determine the reasonable driving space information of the vehicle according to the traffic scenario information.

[0104] The method provided by the embodiment of the present application dynamically adjusts the reasonable driving space information of the vehicle according to the traffic scenario information where the vehicle is located. The reasonable driving space information includes the driving space that does not violate the traffic rules. For example, in the case where all the same-direction lanes are blocked, the nearest reverse lane, non-motor vehicle lane, bus lane, etc. to the vehicle are all reasonable driving spaces; but if there are other same-direction lanes that can pass normally, the nearest reverse lane, non-motor vehicle lane, bus lane, etc. to the vehicle are all unreasonable driving spaces, which are not only unreasonable but also violate the traffic rules. For another example, when the vehicle is going to turn right at the intersection ahead, if the right-turn lane is not blocked, only the right-turn lane is the reasonable driving space, and the non-right-turn lanes are all unreasonable driving spaces.

[0105] In one example, the traffic scene information includes: all lanes in the same direction are blocked; step S103 can be implemented in the following manner: set the reasonable driving space to include the illegal driving lane. The reasons for lane blockage include, but are not limited to, heavy traffic, road construction, and traffic accidents. The illegal driving lane includes, but is not limited to, at least one of the reverse lane, non-motor vehicle lane, and bus lane.

[0106] As Figure 3 shown, when all lanes in the same direction are blocked, it is necessary to bypass using the reverse lane, non-motor vehicle lane, or bus lane. At this time, it is necessary to release the reverse lane and release the non-motor vehicle lane or bus lane, and use them as the reasonable driving space. By adopting this processing method, when all lanes in the same direction are blocked, the driving behavior of crossing the solid line and bypassing using the reverse lane is reasonable and does not violate traffic regulations.

[0107] In one example, the traffic scene information includes: partial blockage of lanes in the same direction; step S103 can be implemented in the following manner: set the reasonable driving space to include the illegal driving lane adjacent to the unblocked lane. By adopting this processing method, when the own lane is blocked but there are other lanes in the same direction that can pass normally, the driving behavior of crossing the solid line and bypassing using the reverse lane is not only unreasonable but also violates traffic regulations.

[0108] Specifically, step S103 may include the following sub-steps: 1) Obtain the lane specification information of the unblocked lane. The lane specification information includes, but is not limited to, the width of the lane, the type of road surface (such as asphalt road, dirt road, highway, national road, etc.), and may also include obtaining the vehicle width information, etc.; 2) According to the lane specification information, determine whether the unblocked lane supports vehicle bypass; 3) If the above judgment result is yes, set the reasonable driving space not to include the illegal driving lane adjacent to the unblocked lane; 4) If the above judgment result is no, set the reasonable driving space to include the illegal driving lane adjacent to the unblocked lane.

[0109] As Figure 4a shown, when there are still lanes in the same direction that can pass normally, the same-direction lane should be given priority. For example, when driving in the leftmost same-direction lane 1, the non-motor vehicle lane or bus lane should be set as an unreasonable driving space. To avoid blocking vehicle bypass, the reverse lane can be set as a reasonable driving space, but if the remaining space in the leftmost same-direction lane 1 is wide enough, the reverse lane can be set as an unreasonable driving space.

[0110] As Figure 4bAs shown, it is preferred to drive in the rightmost same-direction lane. At this time, the reverse lane should be set as an unreasonable driving space. To avoid blocking vehicle detours, the non-motor vehicle lane or the bus lane can be set as a reasonable driving space. However, if the remaining space in the rightmost same-direction lane 3 is wide enough, the non-motor vehicle lane or the bus lane can be set as an unreasonable driving space.

[0111] As Figure 9 shown, if there are multiple target lanes (such as straight lanes 2 and 3) and they are not blocked, the other incorrect route lanes outside the target lanes (such as the left-turn lane 1 and the right-turn lane 4) should be set as unreasonable driving spaces.

[0112] As Figure 10 shown, if other target lanes (such as straight lane 2) are blocked and only one target lane (such as straight lane 3) remains, the incorrect route lane adjacent to the remaining one target lane (such as right-turn lane 4) can be released. However, if the remaining space in this target lane (such as straight lane 3) is wide enough and it is determined that it will not block the detour, the above-mentioned incorrect route lane (such as right-turn lane 4) can also be set as an unreasonable driving space.

[0113] In one example, the traffic scene information includes: there is an obstacle occupying the current driving lane; step S103 may include the following sub-steps: 1) Obtain the lane specification information of the current driving lane. In addition, it may also include obtaining vehicle width information, etc.; 2) According to the lane specification information, determine whether the current driving lane supports the vehicle to detour around the obstacle; if the above determination result is yes, set the reasonable driving space to not include the illegal driving lane adjacent to the current driving lane; if the above determination result is no, set the reasonable driving space to include the illegal driving lane adjacent to the current driving lane.

[0114] As Figure 5a shown, there is an obstacle occupying the same-direction lane 1 and the vehicle needs to detour. At this time, if the remaining width of the own lane is not wide enough, the reverse lane can be set as a reasonable driving space; if the remaining width of the own lane is wide enough, the reverse lane can be set as an unreasonable driving space.

[0115] As Figure 5b shown, there is an obstacle occupying the same-direction lane 3 and the vehicle needs to detour. At this time, if the remaining width of the own lane is not wide enough, the non-motor vehicle lane or the bus lane can be set as a reasonable driving space; if the remaining width of the own lane is wide enough, the non-motor vehicle lane or the bus lane can be set as an unreasonable driving space.

[0116] In one example, the traffic scenario information includes: a single-lane blind bend in the same direction; step S103 may include the following sub-steps: 1) Obtain the lane specification information of the current driving lane, and may also include obtaining the vehicle width information of the vehicle, etc.; 2) Determine the range information of the partial area of the reverse lane that can be used as a reasonable driving space according to the lane specification information.

[0117] As Figure 6 shown, in the blind bend scenario, in order to allow reasonable overtaking by crossing the line, sufficient passing space will be reserved in the reverse lane: when L is greater than or equal to a preset width (such as 2.8 meters), the reasonable driving space is translated leftward by a certain distance, and d can be set to be less than or equal to half of the vehicle width.

[0118] In addition, in the blind bend scenario, in order to avoid the possible danger caused by unprotected overtaking, the reasonable driving space can be set to include the current lane and not include the reverse lane to prevent the vehicle from deeply entering the reverse lane.

[0119] In one example, the traffic scenario information includes: the target turning lane is blocked; step S103 can be implemented in the following way: set the reasonable driving space to include the first straight lane adjacent to the target turning lane and the second straight lane adjacent to the first straight lane. The target turning lane includes the lane that the vehicle will enter according to its pre-planned driving route, such as a right-turning lane or a left-turning lane.

[0120] As Figure 7 shown, in front of the intersection, in addition to the target lane (such as the left-turning lane 1) and the lane adjacent to it (such as the leftmost straight lane 2) which should be set as the reasonable driving space, other lanes (such as the right straight lane 3 and the right-turning lane 4) should be set as the unreasonable driving space.

[0121] As Figure 8 shown, if the target lane (such as the left-turning lane 1) is blocked, the target lane automatically extends to the adjacent lane (such as the straight lane 2), and the lane adjacent to it (such as the straight lane 3) is released, that is, the straight lanes 2 and 3 are set as the reasonable driving space, and other lanes (such as the right-turning lane 4) should be set as the unreasonable driving space.

[0122] In one example, the traffic scenario information includes: the target turning lane is not blocked; step S103 can be implemented in the following way: set the reasonable driving space to include the target turning lane and the first straight lane adjacent to the target turning lane.

[0123] So far, through the above steps S101 and S103, the pre-decision processing of the vehicle driving path is realized, that is, the reasonable driving space is dynamically adjusted based on the actual traffic scenario where the vehicle is located. Subsequently, the reasonable driving space will be used to plan the driving path within the reasonable space.

[0124] Step S105: Obtain a first planned path for the vehicle to travel.

[0125] The first planned path may include multiple paths planned in the complete space, and may also include a path planned in a reasonable driving space. The complete space includes a reasonable driving space and an unreasonable driving space. For example, when a vehicle wants to turn right at the intersection ahead, even if the right-turn lane is not blocked, the complete space may include a right-turn lane and a non-right-turn lane.

[0126] like Figure 2 As shown, the first planned path includes but is not limited to: an escape path, a self-driving lane path, a left turn path, a right turn path, a detour path, and an AERT path.

[0127] In one example, the method may also include: obtaining environmental perception information of the space around the vehicle; step S105 may adopt at least one of the following methods: 1) determining an escape path based on the environmental perception information; 2) determining a first non-escape path based on the environmental perception information; 3) obtaining a second non-escape path planned in a reasonable driving space based on the environmental perception information and reasonable driving space information. In this embodiment, the second non-escape path is referred to as an AERT path (Adjusted Extended Routing Tree, adaptive dynamically expandable passage space). This processing method can ensure normal driving in conventional scenarios without violating traffic regulations, and ensure that in extreme special scenarios, the vehicle will not be trapped and unable to reach the destination due to lack of passable space, thereby ensuring that the driving path of the autonomous driving vehicle is reasonable and compliant.

[0128] 1) Determine an escape path based on the environmental perception information.

[0129] In one example, the escape path can be determined in the following manner: according to the environmental perception information, the distance information between the vehicle and the vehicle in front is obtained; according to the distance information, whether the reversing operation can be performed is determined; if the above determination result is yes, the escape path is generated. For example, when the vehicle is traveling straight, if the traffic scene in which the vehicle is located is that the lane is blocked, and the distance to the vehicle in front is very close, and it is impossible to turn left or right directly to other lanes, and the distance between the vehicle and the vehicle behind is far, then the vehicle can perform a reversing operation, so an escape path is generated, and the escape path may include reversing first and then turning.

[0130] like Figure 11As shown, an escape path can be generated by a FS (Free Space) path planner. The FS path planner can be a planner that plans a path using a Hybrid A* algorithm and a path smoothing algorithm, or it can be a planner that plans a path using an A* algorithm and a path smoothing algorithm. Among them, the smoothing algorithm can be to fit the original curve using a smooth curve. The Hybrid A* algorithm is a graph search algorithm (Hybrid A*) that satisfies the vehicle kinematics, which is an improvement on the A* algorithm. The difference from the ordinary A* algorithm is that the path planned by Hybrid A* takes into account the kinematic constraints of the vehicle, that is, it satisfies the maximum curvature constraint of the vehicle. Since the FS path planner belongs to the prior art, it will not be described here.

[0131] In this embodiment, the FS path planner is used to search for an escape path that conforms to the vehicle kinematic model in an open space using the Hybrid A* algorithm combined with the path optimization algorithm. Compared with the function optimization algorithm of the FEM planner, the FS path planner can ensure that a global optimized path is searched, which is suitable for escape in special scenarios and avoids being unable to escape due to being trapped in local optimization and not being able to find a passable path.

[0132] 2) Determine a first non-escape path based on the environmental perception information.

[0133] The first non-escape path includes, but is not limited to: a self-driving path, a left-turn path, a right-turn path, and a detour path.

[0134] like Figure 11 As shown, a non-escape path can be generated by a FEM path planner. FEM is a planning algorithm based on the idea of ​​function optimization. It can use optimization methods such as Newton's method. It has a fast solution speed and needs to construct a boundary to obtain a convex space for solution. The FEM path planner can be a path planner and speed planner based on dynamic programming and quadratic programming. Since the FEM path planner belongs to the prior art, it will not be described here.

[0135] 3) According to the environmental perception information and the reasonable driving space information, an AERT path planned within the reasonable driving space is obtained.

[0136] like Figure 11 As shown, the FEM path planner, the environmental perception information, the map information and the reasonable driving space information can be used to obtain the AERT path planned in the reasonable driving space.

[0137] It should be noted that the first non-escape path can be a path planned in the complete space, which may include a first non-escape path that intersects with an unreasonable driving space, and may also include a first non-escape path within a reasonable driving space. Among them, the first non-escape path within the reasonable driving space and the AERT path can be different paths, and the two can have different costs.

[0138] It should be noted that in specific implementation, the method provided by the embodiments of the present application may not use the FS path planner, but only use the FEM path planner, but it is not applicable in special complex environmental conditions or escape scenarios.

[0139] Step S107: Determine a target driving path from the first planned path according to the reasonable driving space information.

[0140] After determining the reasonable driving space and unreasonable driving space of the vehicle, the reasonable space can be used to plan the driving path of the vehicle. Combining with other paths planned in the complete space, these multiple paths are decision-making, and the path with a smaller cost is selected from them. The vehicle can perform autonomous driving according to the path with the smaller cost.

[0141] In one example, step S107 may include the following sub-steps: 1) Determine the unreasonable space according to the reasonable driving space information; 2) Screen out the paths that intersect with the unreasonable space in the first planned path, and use the screened paths as the second planned path; 3) Select a target driving path from the second planned path. Adopting this processing method, the paths that intersect with the unreasonable space are screened out first, and then the optimized path is selected from the remaining reasonable paths using the cost function, which can improve the rationality and intelligence level of the planned path.

[0142] As Figure 11 shown, the unreasonable driving space can be used to evaluate each path separately through the path decision module, screen out the paths that intersect with the unreasonable driving space, calculate their respective costs using the cost function, and select the optimized path. Since the algorithm for calculating the path cost belongs to the relatively mature prior art, it will not be elaborated here.

[0143] As can be seen from the above embodiments, the driving path planning method provided by the embodiments of the present application identifies the traffic scene information where the vehicle is located; determines the reasonable driving space information of the vehicle according to the traffic scene information; obtains the first planned path for the vehicle to travel; and determines the target driving path from the first planned path according to the reasonable driving space information. By adopting this processing method, the reasonable driving space of the vehicle is dynamically adjusted according to the driving perception information of the vehicle in the continuous behavior space in a strongly interactive environment, thereby realizing the path pre-decision processing based on the actual traffic scene, and then planning the driving path within the reasonable space; therefore, the rationality of path planning can be effectively improved, and a path that is safe, comfortable to drive, has high traffic efficiency and does not violate traffic regulations can be found, thereby improving the driving effect of the vehicle.

[0144] Second Embodiment

[0145] In the above embodiments, a driving path planning method is provided. Correspondingly, the present application also provides a driving path planning device. This device corresponds to the embodiments of the above method. Since the device embodiments are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, refer to the partial description of the method embodiments. The device embodiments described below are only illustrative.

[0146] The present application further provides a driving path planning device, including: a traffic scene recognition unit, a reasonable driving space decision unit, a path planning unit, and a path decision unit.

[0147] The traffic scene recognition unit is used to recognize the traffic scene information where the vehicle is located; the reasonable driving space decision unit is used to determine the reasonable driving space information of the vehicle according to the traffic scene information; the path planning unit is used to obtain the first planned path for the vehicle to travel; the path decision unit is used to determine the target driving path from the first planned path according to the reasonable driving space information.

[0148] In one example, the traffic scene recognition unit is specifically configured to obtain the environmental perception information of the space around the vehicle; and recognize the traffic scene information where the vehicle is located according to the environmental perception information.

[0149] In one example, the traffic scene recognition unit is specifically configured to obtain the lane setting information of the current road; recognize the intention information of the obstacle according to the environmental perception information; and recognize the traffic scene information where the vehicle is located according to the intention information of the obstacle and the lane setting information.

[0150] In one example, the traffic scene recognition unit is specifically configured to obtain vehicle driving route information; recognize traffic condition information of each lane according to the intention information of the obstacle and the lane setting information; and recognize the traffic scene information where the vehicle is located according to the traffic condition information of each lane and the vehicle driving route information.

[0151] In one example, the traffic scene recognition unit is specifically configured to obtain vehicle position information and traffic road condition information; and recognize the traffic scene information where the vehicle is located according to the position information and the traffic road condition information.

[0152] In one example, the reasonable driving space decision-making unit is specifically configured to, if the traffic scene information includes that all the same-direction lanes are blocked, set the reasonable driving space to include the illegal driving lane; if the traffic scene information includes that some of the same-direction lanes are blocked, set the reasonable driving space to include the illegal driving lane adjacent to the unblocked lane; if the traffic scene information includes that there is an obstacle occupying the current driving lane, obtain the lane specification information of the current driving lane; judge whether the current driving lane supports the vehicle to bypass the obstacle according to the lane specification information; if the above judgment result is yes, set the reasonable driving space not to include the illegal driving lane adjacent to the current driving lane; if the above judgment result is no, set the reasonable driving space to include the illegal driving lane adjacent to the current driving lane; if the traffic scene information includes a blind bend in a single same-direction lane, obtain the lane specification information of the reverse lane; determine the range information of the partial area of the reverse lane that can be used as the reasonable driving space according to the lane specification information; if the traffic scene information includes that the target turning lane is blocked, set the reasonable driving space to include the first straight driving lane adjacent to the target turning lane and the second straight driving lane adjacent to the first straight driving lane; if the traffic scene information includes that the target turning lane is not blocked, set the reasonable driving space to include the target turning lane and the first straight driving lane adjacent to the target turning lane.

[0153] In one example, the reasonable driving space decision-making unit is further configured to obtain the lane specification information of the unblocked lane; judge whether the unblocked lane supports the vehicle to bypass according to the lane specification information; if the above judgment result is yes, set the reasonable driving space not to include the illegal driving lane adjacent to the unblocked lane; if the above judgment result is no, set the reasonable driving space to include the illegal driving lane adjacent to the unblocked lane.

[0154] In one example, the device further includes: an environment perception unit configured to obtain environment perception information of the space around the vehicle; the path planning unit is specifically configured to determine an escape path according to the environment perception information; determine a first non-escape path according to the environment perception information; obtain a second non-escape path planned within a reasonable driving space according to the environment perception information and reasonable driving space information; wherein, the non-escape path includes, but is not limited to: the own-lane path, the left lane-changing path, the right lane-changing path, and the detour path.

[0155] In one example, the path planning unit is specifically configured to obtain the distance information between the vehicle and the vehicle in front according to the environment perception information; determine whether a reverse operation can be performed according to the distance information; if the determination result is yes, generate an escape path.

[0156] In one example, the path planning unit is specifically configured to determine an unreasonable space according to the reasonable driving space information; screen out the paths in the first planned path that intersect with the unreasonable space, and use the screened paths as the second planned path; select a target driving path from the second planned path.

[0157] Third Embodiment

[0158] In the above embodiments, a driving path planning method is provided. Correspondingly, the present application also provides an electronic device, and the electronic device may be an autonomous vehicle. The embodiments of this device correspond to the embodiments of the above method. Since the device embodiments are basically similar to the method embodiments, the description is relatively simple, and for the related parts, refer to the partial description of the method embodiments. The device embodiments described below are merely illustrative.

[0159] The present application further provides an electronic device, including: a processor and a memory. The memory is used to store a program for implementing the driving path planning method provided in the above embodiments, and the device is powered on and runs the program of the method through the processor.

[0160] Although the present application is disclosed above with preferred embodiments, it is not used to limit the present application. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application should be defined by the scope of the claims of the present application.

[0161] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0162] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0163] 1. Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The 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 technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data and carrier waves.

[0164] 2. Those skilled in the art will appreciate that the embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application 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.) that contain computer-usable program code.

Claims

1. A driving route planning method, characterized in that, including: identifying traffic scene information where the vehicle is located; determining reasonable driving space information of the vehicle according to the traffic scene information; obtaining a first planned path for the vehicle to travel; determining a target driving path from the first planned path according to the reasonable driving space information; wherein, the determining the reasonable driving space information of the vehicle according to the traffic scene information adopts at least one of the following methods: if the traffic scene information includes that all lanes in the same direction are blocked, then set the reasonable driving space to include the illegal driving lane; if the traffic scene information includes that some lanes in the same direction are blocked, then set the reasonable driving space to include the illegal driving lane adjacent to the unblocked lane; if the traffic scene information includes that there is an obstacle occupying the current driving lane, then obtain the lane specification information of the current driving lane; according to the lane specification information, judge whether the current driving lane supports the vehicle to bypass the obstacle; if the judgment result is yes, then set the reasonable driving space not to include the illegal driving lane adjacent to the current driving lane; if the judgment result is no, then set the reasonable driving space to include the illegal driving lane adjacent to the current driving lane; if the traffic scene information includes a blind bend in a single-lane in the same direction, then obtain the lane specification information of the reverse lane; according to the lane specification information, determine the range information of the partial area of the reverse lane that can be used as the reasonable driving space; if the traffic scene information includes that the target turning lane is blocked, then set the reasonable driving space to include the first straight lane adjacent to the target turning lane and the second straight lane adjacent to the first straight lane; if the traffic scene information includes that the target turning lane is not blocked, then set the reasonable driving space to include the target turning lane and the first straight lane adjacent to the target turning lane.

2. The method according to claim 1, characterized in that, The identifying the traffic scene information where the vehicle is located includes: obtaining environmental perception information of the space around the vehicle; identifying the traffic scene information where the vehicle is located according to the environmental perception information.

3. The method according to claim 2, wherein The identifying the traffic scene information where the vehicle is located further includes: obtaining the lane setting information of the current road; The identifying the traffic scene information where the vehicle is located according to the environmental perception information includes: identifying the intention information of the obstacle according to the environmental perception information; identifying the traffic scene information where the vehicle is located according to the intention information of the obstacle and the lane setting information.

4. The method according to claim 3, wherein The identifying the traffic scene information where the vehicle is located further includes: obtaining the vehicle driving route information; The identifying the traffic scene information where the vehicle is located according to the intention information of the obstacle and the lane setting information includes: identifying the traffic condition information of each lane according to the intention information of the obstacle and the lane setting information; identifying the traffic scene information where the vehicle is located according to the traffic condition information of each lane and the vehicle driving route information.

5. The method according to claim 1, wherein The identifying the traffic scene information where the vehicle is located includes: obtaining the vehicle position information and the traffic condition information; identifying the traffic scene information where the vehicle is located according to the position information and the traffic condition information.

6. The method according to claim 1, characterized in that, It further includes: obtaining the lane specification information of the unblocked lane; Determining whether an unblocked lane supports a detour of the vehicle according to the lane specification information; If the above judgment result is yes, the reasonable driving space is set to not include the illegal driving lane adjacent to the unblocked lane; If the above judgment result is no, the reasonable driving space is set to include the illegal driving lane adjacent to the unblocked lane.

7. The method according to claim 1, characterized in that The method further comprises: Obtain environmental perception information of the space around the vehicle; The obtaining of the first planned path for the vehicle to travel adopts at least one of the following methods: Determining an escape path based on the environmental perception information; Determining a first non-escape path according to the environmental perception information; According to the environmental perception information and the reasonable driving space information, a second non-escaping path planned in the reasonable driving space is acquired; Among them, the non-escaping paths include but are not limited to: self-driving path, left lane change path, right lane change path, and detour path.

8. The method according to claim 7, wherein The step of determining an escape path according to the environmental perception information includes: Acquiring distance information between the vehicle and the preceding vehicle according to the environmental perception information; determining whether a reversing operation can be performed according to the distance information; If the above determination result is yes, an escape path is generated.

9. The method according to claim 1, wherein The step of determining a target driving path from the first planned path according to the reasonable driving space information includes: Determine unreasonable space based on reasonable driving space information; Screening out paths that intersect with the unreasonable space in the first planned path, and using the screened out paths as the second planned path; A target driving path is selected from the second planned paths.

10. A driving path planning device, characterized in that, include: A traffic scene recognition unit, used to recognize the traffic scene information in which the vehicle is located; A reasonable driving space decision unit, used to determine reasonable driving space information of the vehicle according to the traffic scene information; A path planning unit, used to obtain a first planned path for the vehicle to travel; A path decision unit, configured to determine a target driving path from the first planned path according to the reasonable driving space information; Wherein, determining the reasonable driving space information of the vehicle according to the traffic scene information adopts at least one of the following methods: If the traffic scene information includes that all lanes in the same direction are blocked, the reasonable driving space is set to include the illegal driving lane; If the traffic scene information includes that a lane in the same direction is partially blocked, setting the reasonable driving space to include an illegal driving lane adjacent to an unblocked lane; If the traffic scene information includes that an obstacle occupies the current driving lane, then the lane specification information of the current driving lane is obtained; based on the lane specification information, whether the current driving lane supports the vehicle to bypass the obstacle is determined; if the above determination result is yes, the reasonable driving space is set to not include the illegal driving lane adjacent to the current driving lane; if the above determination result is no, the reasonable driving space is set to include the illegal driving lane adjacent to the current driving lane; If the traffic scene information includes a one-way single-lane blind bend in the same direction, obtain the lane specification information of the reverse lane; according to the lane specification information, determine the range information of the partial area of the reverse lane that can be used as a reasonable driving space; if the traffic scene information includes an obstruction of the target turning lane, set the reasonable driving space to include the first straight lane adjacent to the target turning lane and the second straight lane adjacent to the first straight lane. If the traffic scene information includes that the target turning lane is not blocked, set the reasonable driving space to include the target turning lane and the first straight lane adjacent to the target turning lane.

11. An electronic device, characterized in that, Comprising: A memory and a processor; The memory is used to store a program for implementing the driving path planning method according to any one of claims 1-9 above, and the device is powered on and runs the program of the method through the processor.

Images