Navigation-free farthest feasible path planning method, system, equipment and medium

Abstract

The invention provides a navigation-free farthest feasible path planning method, system, equipment and medium, and the navigation-free farthest feasible path planning method comprises the steps: obtaining a grid map of an area where a target vehicle is located, and constructing a thermodynamic map according to the grid map; acquiring a speed domain and an angular speed domain of the target vehicle based on scene limitation and vehicle parameter limitation; based on vehicle dynamics and vehicle collision conditions, obtaining j first tracks of the target vehicle according to the speed domain and the angular speed domain; first tracks meeting planning condition requirements are screened out from the j first tracks to obtain a track set, i first tracks are arranged in the track set, and i is smaller than or equal to j; and performing cost calculation on the i first trajectories in the trajectory set to obtain an optimal trajectory. The technical problems that in the prior art, a parking space searching path planning method before parking does not explore a blind area, the target vehicle cannot walk farther, and the trajectory of the target vehicle is likely to fall into local optimum are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a method for planning a maximum feasible path without navigation, a system for planning a maximum feasible path without navigation, an electronic device and a readable storage medium. Background Art

[0002] Intelligent connected vehicles have become an important national development strategy, of which autonomous parking technology is an indispensable part. Most of the parking space search path planning methods before parking are exploration or planning under the acquisition of the destination. The advantage of this is that it can effectively move towards the goal, but in the real world, there may not be a set destination. For example, searching for parking spaces in a parking lot and performing parking scenarios, this process cannot obtain the corresponding available parking spaces. Moreover, since the idle and occupied status of the parking spaces themselves change in real time, the parking spaces may be available now, but the target parking spaces need to be changed at the next moment. Therefore, the initial acquisition of the corresponding available parking spaces in the parking scenario is more of a process of exploration and discovery. It is necessary to continuously search for parking spaces that meet the parking conditions in the parking lot to activate the next parking function.

[0003] However, in the actual implementation process, there is such a problem: the existing parking space search path planning method before parking does not explore the blind spot, and cannot allow the target vehicle to go further, which easily causes the trajectory of the target vehicle to fall into the local optimum. Summary of the invention

[0004] The present invention solves the technical problems that the parking space search path planning method before parking in the prior art does not explore the blind area, cannot allow the target vehicle to go further, and easily causes the trajectory of the target vehicle to fall into the local optimum.

[0005] In order to solve the above problems, the present invention provides a navigation-free farthest feasible path planning method, comprising: obtaining a grid map of the area where the target vehicle is located, and constructing a heat map according to the grid map; obtaining the speed domain and angular velocity domain of the target vehicle based on scene restrictions and vehicle parameter restrictions; obtaining j first trajectories of the target vehicle according to the speed domain and angular velocity domain based on vehicle dynamics and vehicle collision conditions; selecting the first trajectories that meet the planning condition requirements from the j first trajectories to obtain a trajectory set, wherein i first trajectories are provided in the trajectory set, i≤j; performing cost calculation on the i first trajectories in the trajectory set to obtain an optimal trajectory; and controlling the target vehicle according to the optimal trajectory; wherein the planning condition requirement is that the sampling duration of the first trajectory is within a sampling time range, and the sampling time range is: , and the first trajectory does not produce collision within the first sampling time.

[0006] Compared with the prior art, the technical effect achieved by adopting this technical solution is as follows: Taking the parking scene as an example, the target vehicle driving into the parking lot and parking in the parking space can be divided into two steps: the first step is to explore without a destination until a parking space that can be parked is obtained; the second step is to park in the parking space. The present application relates to the planning of the parking space search path before parking, that is, the map can be ignored, the environmental information can be obtained in real time, and the environment can be explored in real time until the corresponding parking space is obtained. Generally speaking, the first trajectory is constrained by the sampling time, but in this application, the time is not completely used as a constraint condition. The trajectory will be sampled with a duration greater than the maximum sampling time of the constraint, so that the first trajectory can be longer, so that it will not fall into the local optimum, that is, a "dead end", reducing the probability of manual operation to reverse out of the "dead end", and higher safety; at the same time, a variable-length trajectory is adopted, so that the sampling time of the target vehicle can reach up to the second sampling time, so that the first trajectory lasts longer, and the variable-length trajectory can allow the target vehicle to go farther even in the position area outside the field of vision.

[0007] In one example of the present invention, controlling a target vehicle according to an optimal trajectory includes: obtaining an optimal sampling time according to a sampling duration corresponding to the optimal trajectory; processing the optimal trajectory according to the size of the optimal sampling time and the first sampling time to obtain a target trajectory; and controlling the target vehicle according to the target trajectory.

[0008] Compared with the prior art, the technical effect achieved by adopting this technical solution is: in this application, the first trajectory with the largest cost is selected as the optimal trajectory according to the cost function, and each first trajectory and each sampling duration are set accordingly, and the sampling duration corresponding to the optimal trajectory is defined as the optimal sampling time. Since the range of the optimal sampling time is , it is necessary to time match the optimal sampling time corresponding to the optimal trajectory, match the optimal sampling time to the first sampling time, process the optimal trajectory to generate the target trajectory, and finally control the target vehicle according to the target trajectory. By time matching the optimal sampling time, the output target trajectory is prevented from being too long, thereby meeting memory requirements and avoiding data leakage.

[0009] In one example of the present invention, the optimal trajectory is processed according to the size of the optimal sampling time and the first sampling time to obtain the target trajectory, including: when the optimal sampling time is greater than the first sampling time, intercepting the optimal trajectory within the first sampling time as the target trajectory; and / or when the optimal sampling time is equal to the first sampling time, the target trajectory is the optimal trajectory.

[0010] Compared with the prior art, the technical effect achieved by adopting this technical solution is as follows: the specific method for time matching the optimal sampling time corresponding to the optimal trajectory is: deleting the optimal trajectory after the first sampling time, that is, deleting the redundant trajectory points with too long time in the optimal trajectory, which can also be called constraining the output length of the target trajectory.

[0011] In one embodiment of the present invention, the trajectory set is: , performing cost calculation on the i first trajectories in the trajectory set to obtain the optimal trajectory, including: performing cost calculation on the first trajectory through a cost function; the cost function is: ;in, is the set of trajectories, is the i-th first trajectory in the trajectory set; For the trajectory The speed cost function is For the trajectory The thermal cost function is For the trajectory The length cost function of For the trajectory The angular velocity cost function is: ; The thermal cost function is: ; The length cost function is: ; The angular velocity cost function is: ;in, is the speed cost coefficient, For the trajectory At the track point speed, The maximum speed limited by the scene; is the thermal cost coefficient, It's a track At the track point The thermal value, It is the thermal value limit; is the length cost coefficient, For the trajectory Length; is the angular velocity cost coefficient, For the trajectory At the track point angular velocity.

[0012] Compared with the prior art, the technical effect achieved by adopting this technical solution is as follows: traverse the i first trajectories in the trajectory set, and for each trajectory point of each first trajectory Calculate the speed cost, thermal cost, length cost and angle cost of each first trajectory to obtain the cost of each first trajectory: , is the kth track point of the i-th first track. Recommended value range: , , , . According to the cost calculation of the i first trajectories, the corresponding set is obtained: ,in, is the cost of the 0th first trajectory; is the cost of the first trajectory of the i-th track.

[0013] In one example of the present invention, a grid map of an area where a target vehicle is located is obtained, and a thermal map is constructed based on the grid map, including: initializing a fully trusted area under the grid map; obtaining an obstacle existence area of ​​an obstacle in the grid map; determining whether the obstacle existence area is in the fully trusted area; when the obstacle existence area is in the fully trusted area, determining a thermal coefficient of the obstacle existence area according to the type of the obstacle; and / or when the obstacle existence area is not in the fully trusted area, determining the thermal coefficient of the obstacle existence area as a thermal coefficient threshold.

[0014] Compared with the prior art, the technical effect achieved by adopting this technical solution is as follows: the fully credible area is a fully credible and absolutely visible area, which together with the blind area constitutes the entire area of ​​the grid map, and the obstacles in the grid map divide the grid map into relatively fully credible areas and blind areas; then, the grid map is traversed to obtain the area where obstacles exist in the grid map, which is recorded as the obstacle existence area, and the obstacle set can be regarded as a set of multiple obstacle existence areas; finally, the grid map is traversed, and for each area without obstacles, the Euclidean distance between the area and the nearest obstacle is calculated. Calculate the corresponding thermal value mapped in the thermal map (determine the thermal coefficient based on the type of obstacle and whether the obstacle area is in a completely credible area, and calculate the thermal coefficient based on the Euclidean distance Get thermal value); Finally, by determining the thermal coefficient in the raster map, a thermal map is constructed. Constructing a thermal map can make the target vehicle drive more in the middle of the road and as far away from obstacles as possible. Being away from obstacles can give the target vehicle more time to deal with special situations, such as sudden appearance of pedestrians or vehicles. This gives the target vehicle enough time to avoid accidents, while also further reducing the requirements for upstream perception accuracy.

[0015] In one example of the present invention, the speed domain and angular velocity domain of the target vehicle are obtained based on the scene restrictions and the vehicle's own parameter restrictions, including: obtaining a vehicle-related speed interval, an acceleration-related speed interval, and a collision-related speed interval; obtaining a vehicle-related angular velocity interval, an acceleration-related angular velocity interval, and a collision-related angular velocity interval; obtaining a speed domain according to the vehicle-related speed interval, the acceleration-related speed interval, and the collision-related speed interval; obtaining an angular velocity domain according to the vehicle-related angular velocity interval, the acceleration-related angular velocity interval, and the collision-related angular velocity interval; wherein the vehicle-related speed interval is: , the acceleration-related speed range is: , the collision-related velocity range is: ; The vehicle-related angular velocity range is: , the acceleration-related angular velocity range is: , the collision-related angular velocity range is: .

[0016] Compared with the existing technology, the technical effect achieved by adopting this technical solution is: based on the scene restrictions and the vehicle's own parameter restrictions, the vehicle-related speed range of the target vehicle is obtained. ; Obtain the acceleration-related speed range of the target vehicle based on comfort limits Angular velocity range related to acceleration ; Obtain the collision-related speed range of the target vehicle based on the collision limit Angular velocity range related to collision .

[0017] In one embodiment of the present invention, the velocity domain is: ; The angular velocity domain is: ;in, is the first vehicle-related speed threshold, is the first acceleration-related speed threshold, is the first collision-related speed threshold; is the second vehicle-related speed threshold, is the second acceleration-related speed threshold, is the second collision-related speed threshold; is the first vehicle-related angular velocity threshold, is the first acceleration-related angular velocity threshold, is the first collision-related angular velocity threshold; is the second vehicle-related angular velocity threshold, is the second acceleration-related angular velocity threshold, is the second collision-related angular velocity threshold.

[0018] Compared with the prior art, the technical effect achieved by adopting the technical solution is as follows: after obtaining the vehicle-related speed interval, the acceleration-related speed interval, the collision-related speed interval and the vehicle-related angular velocity interval, the acceleration-related angular velocity interval and the collision-related angular velocity interval, the speed domain can be obtained through the vehicle-related speed interval, the acceleration-related speed interval and the collision-related speed interval; the angular velocity domain can be obtained through the vehicle-related angular velocity interval, the acceleration-related angular velocity interval and the collision-related angular velocity interval.

[0019] On the other hand, an embodiment of the present invention further provides a navigation-free farthest feasible path planning system, using a navigation-free farthest feasible path planning method as in any of the above embodiments, including: a construction module, the construction module is used to obtain a grid map of the area where the target vehicle is located, and construct a heat map based on the grid map; a first acquisition module, the first acquisition module is used to obtain the speed domain and angular velocity domain of the target vehicle based on scene restrictions and vehicle parameter restrictions; a second acquisition module, the second acquisition module is used to obtain j first trajectories of the target vehicle according to the speed domain and angular velocity domain based on vehicle dynamics and vehicle collision conditions; a screening module, the screening module is used to screen out first trajectories that meet planning conditions from the j first trajectories to obtain a trajectory set, and the trajectory set is provided with i first trajectories, i≤j; a calculation module, the calculation module is used to perform cost calculation on the i first trajectories in the trajectory set to obtain an optimal trajectory; and a control module, the control module is used to control the target vehicle according to the optimal trajectory.

[0020] Compared with the prior art, the technical effect achieved by adopting this technical solution is as follows: the non-navigation longest feasible path planning system in this embodiment is used to implement the non-navigation longest feasible path planning method as in any embodiment of the present invention, so it has all the beneficial effects of the non-navigation longest feasible path planning method as in any embodiment of the present invention, which will not be repeated here.

[0021] On the other hand, an embodiment of the present invention further provides an electronic device, comprising: a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein when the program or instruction is executed by the processor, the steps of the method for planning the longest feasible path without navigation as in any of the above embodiments are implemented.

[0022] Compared with the prior art, the technical effect achieved by adopting this technical solution is as follows: the electronic device in this embodiment runs the non-navigation longest feasible path planning method as in any embodiment of the present invention, so it has all the beneficial effects of the non-navigation longest feasible path planning method as in any embodiment of the present invention, which will not be repeated here.

[0023] On the other hand, an embodiment of the present invention further provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method for planning the longest feasible path without navigation as in any of the above embodiments are implemented.

[0024] Compared with the prior art, the technical effect achieved by adopting this technical solution is as follows: the readable storage medium in this embodiment is used to store the non-navigation longest feasible path planning method as in any embodiment of the present invention, so it has all the beneficial effects of the non-navigation longest feasible path planning method as in any embodiment of the present invention, which will not be repeated here.

[0025] After adopting the technical solution of the present invention, the following technical effects can be achieved: (1) In this application, time is not the only constraint. The trajectory is sampled with a duration greater than the maximum sampling time of the constraint, so that the first trajectory can be longer. In this way, it will not fall into the local optimum, that is, a "dead end", reducing the probability of manual operation to reverse out of the "dead end" and providing higher safety. At the same time, a variable-length trajectory is used so that the sampling time of the target vehicle can reach the second sampling time at most, making the first trajectory last longer. The variable-length trajectory allows the target vehicle to go further, even in a location area outside the field of vision. (2) Deleting the optimal trajectory after the first sampling time, that is, deleting the redundant trajectory points that are too long in the optimal trajectory, which can also be called constraining the output length of the target trajectory; (3) By determining the thermal coefficient in the grid map, a thermal map is constructed. Constructing a thermal map can enable the target vehicle to move closer to the middle of the road and as far away from obstacles as possible. Being away from obstacles can provide more time to deal with special situations, such as the sudden appearance of pedestrians or vehicles. This provides enough time to avoid accidents and also further reduces the requirements for upstream perception accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A flowchart of a method for planning the longest feasible path without navigation provided in Embodiment 1 of the present invention; Figure 2 It is a specific schematic diagram of the grid map of the present invention; Figure 3 A structural schematic block diagram of a non-navigation longest feasible path planning system provided in Embodiment 2 of the present invention; Figure 4 A block diagram of an electronic device according to a third embodiment of the present invention; Figure 5 A schematic diagram of the structure of a readable storage medium provided in Embodiment 4 of the present invention.

[0027] Description of reference numerals: 100- navigation-free longest feasible path planning system; 101- construction module; 102- first acquisition module; 103- second acquisition module; 104- screening module; 105- calculation module; 106- control module; 200- electronic device; 210- memory; 211- computer program; 220- processor; 300- readable storage medium; 310- computer executable instructions. DETAILED DESCRIPTION

[0028] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention are described clearly and completely. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] [Example 1] See also Figure 1 , which is a flowchart of a method for planning the longest feasible path without navigation provided by the first embodiment of the present invention, combined with Figure 2 , the longest feasible path planning method without navigation includes: S100: Obtain a grid map of the area where the target vehicle is located, and construct a heat map based on the grid map; S200: Acquire the speed domain and angular velocity domain of the target vehicle based on the scene restriction and the vehicle's own parameter restriction; S300: Based on vehicle dynamics and vehicle collision conditions, obtain j first trajectories of the target vehicle according to the speed domain and the angular velocity domain; S400: Filter out first trajectories that meet planning conditions from j first trajectories to obtain a trajectory set, wherein the trajectory set is provided with i first trajectories, i≤j; S500: Calculate the cost of i first trajectories in the trajectory set to obtain the optimal trajectory; S600: Controlling the target vehicle according to the optimal trajectory; Among them, the planning condition requirement is: the sampling duration of the first trajectory is within the sampling time range, and the sampling time range is: , and the first trajectory does not produce collision within the first sampling time.

[0030] In a specific embodiment, taking the parking scenario as an example, the target vehicle driving into the parking lot and parking in the parking space can be divided into two steps: the first step is to explore aimlessly until a parking space that can be parked is obtained; the second step is to park in the parking space. The present application relates to the planning of the parking space search path before parking, that is, the map can be ignored, environmental information can be obtained in real time, and the environment can be explored in real time until the corresponding parking space is obtained. After obtaining j first trajectories, the j first trajectories are screened based on the planning conditions, and the first trajectories that will collide within the maximum sampling time are deleted, and the sampling duration of the first trajectory is within the sampling time range, and finally a trajectory set including i first trajectories is obtained. , is the sampling duration, which means the acquisition time of the first track is: - , Usually 0s; is the first sampling time, is the second sampling time; preferably, , , is the maximum sampling time. Generally speaking, the first trajectory is constrained by the sampling time, but in the present application, time is not completely used as a constraint condition. The trajectory will be sampled with a duration greater than the maximum sampling time of the constraint, so that the first trajectory can be longer, so that it will not fall into the local optimum, that is, a "dead end", and the probability of requiring manual operation to back out of the "dead end" is reduced, as well as higher safety; at the same time, a variable-length trajectory is used, so that the sampling time of the target vehicle can reach up to the second sampling time, so that the first trajectory lasts longer, and the variable-length trajectory allows the target vehicle to go further, even in a location area out of the field of vision. Preferably, the use scenario of the present application is not limited to parking lots, but is applicable to unprotected narrow road scenarios, such as narrow alleys.

[0031] The specific steps to obtain the trajectory set are: ①. For each set of fixed control quantities , control amount is a set of trajectory points on a first trajectory, calculated from the trajectory points starting from the starting planning point of the vehicle, and the planning sampling time is: , is the sampling time interval, The preferred value of is 0.1s, and the planned sampling time consists of multiple sampling time nodes; ②. For each sampling time node, the trajectory point calculated is combined with the heading angle to obtain the geometric information of the target vehicle, and then the collision is calculated with the gripmap (i.e., grid map); ③. For each sampling time node, the trajectory point calculated is combined with the heading angle to calculate the geometric information of the target vehicle, and the vehicle frame is converted to the polar coordinate system of the vehicle; ④. If the sampling time node does not reach the maximum sampling time at this time, prune in advance, that is, directly end the calculation of the trajectory to save computing power, and the trajectory does not belong to the first trajectory; ⑤. After calculating the above operations for each set of fixed control quantities, the first trajectory corresponding to each control quantity can be obtained to form a corresponding trajectory set; ⑥. Because a variable-length trajectory is used, the first step of confirmation of the first trajectory is required, that is, deleting the first trajectory that is lower than the number of trajectories agreed with the control, middleware, etc. (wherein, the control has control requirements, such as the duration and size of the first trajectory; the middleware has transmission capacity restrictions, such as is the agreed transmission data size). The sampling duration of the first track thus obtained is in the range of: At the same time, in order to ensure that the number of the first trajectory is not 0, that is, there is a planned trajectory, the parking trajectory (that is, the trajectory with a final speed of 0) is stored in the trajectory set. ,in, is the angular velocity ergodic number, is the angular velocity interval. At the same time, this application uses a high-frequency planning strategy to analyze the surrounding environment and effectively avoid dynamic obstacles, such as pedestrians.

[0032] Specifically, , , set the number of traversals and , calculate the traversal interval , The speed traversal interval is: and the angular velocity traversal interval is ,in, is the first speed threshold, is the second speed threshold, is the speed interval; is the first angular velocity threshold, is the second angular velocity threshold. Preferably, the speed traversal number is set = Number of angular velocity traversals .

[0033] Furthermore, S600 includes: S610: Obtaining an optimal sampling time according to a sampling duration corresponding to the optimal trajectory; S620: Processing the optimal trajectory according to the optimal sampling time and the first sampling time to obtain a target trajectory; S630: Control the target vehicle according to the target trajectory.

[0034] Specifically, in this application, the first trajectory with the largest cost is selected as the optimal trajectory according to the cost function, and each first trajectory and each sampling duration are set accordingly, and the sampling duration corresponding to the optimal trajectory is defined as the optimal sampling time. , it is necessary to time match the optimal sampling time corresponding to the optimal trajectory, match the optimal sampling time to the first sampling time, process the optimal trajectory to generate the target trajectory, and finally control the target vehicle according to the target trajectory. By time matching the optimal sampling time, the output target trajectory is prevented from being too long, thereby meeting memory requirements and avoiding data leakage.

[0035] Furthermore, S620 includes: S621: When the optimal sampling time is greater than the first sampling time, intercepting the optimal trajectory within the first sampling time as the target trajectory; and / or S622: When the optimal sampling time is equal to the first sampling time, the target trajectory is the optimal trajectory.

[0036] Specifically, the specific method for time matching the optimal sampling time corresponding to the optimal trajectory is: deleting the optimal trajectory after the first sampling time, that is, deleting the redundant trajectory points with too long time in the optimal trajectory, which can also be called constraining the output length of the target trajectory.

[0037] For example: When When , the optimal sampling time corresponding to the optimal trajectory obtained is 10.3s, that is, the acquisition time of the optimal trajectory is 10.3s, and the time length of the optimal trajectory is 10.3s. It is the length of time that the target vehicle needs to send out the trajectory, which is determined by the downstream control and transmission bandwidth. However, if the transmission size itself is limited to 80 trajectory points (that is, at this time The sampling duration is 0.1s), corresponding to 8s. If there is no constraint, the first trajectory with the highest cost of 10.3s may be transmitted. At this time, the number of trajectory points transmitted is 103, which exceeds the transmission size limit of 80 trajectory points, which may cause memory leaks.

[0038] Furthermore, the trajectory set is: , S500 includes: Calculate the cost of the first trajectory through the cost function; The cost function is: ; in, is the set of trajectories, is the i-th first trajectory in the trajectory set; For the trajectory The speed cost function is For the trajectory The thermal cost function is For the trajectory The length cost function of For the trajectory Angular velocity cost function; The speed cost function is: ; The thermal cost function is: ; The length cost function is: ; The angular velocity cost function is: ; in, is the speed cost coefficient, For the trajectory At the track point speed, The maximum speed limited by the scene; is the thermal cost coefficient, It's a track At the track point The thermal value, It is the thermal value limit; is the length cost coefficient, For the trajectory Length; is the angular velocity cost coefficient, For the trajectory At the track point angular velocity.

[0039] Specifically, traverse the i first trajectories in the trajectory set, and for each trajectory point of each first trajectory Calculate the speed cost, thermal cost, length cost and angle cost of each first trajectory to obtain the cost of each first trajectory: , is the kth track point of the i-th first track. Recommended value range: , , , . According to the cost calculation of the i first trajectories, the corresponding set is obtained: ,in, is the cost of the 0th first trajectory; is the cost of the first trajectory of the i-th track.

[0040] Furthermore, S100 includes: S110: Initializing a completely trusted area under a grid map; S120: Obtaining the obstacle existence area of ​​the obstacle in the grid map; S130: Determine whether the area where the obstacle exists is in a completely credible area; S141: When the obstacle existence area is in the completely credible area, determining the thermal coefficient of the obstacle existence area according to the type of the obstacle; and / or S142: When the obstacle existence area is not in the completely credible area, determining the thermal coefficient of the obstacle existence area as a thermal coefficient threshold.

[0041] Specifically, the fully credible area is a fully credible and absolutely visible area. This area and the blind area together constitute the entire area of ​​the grid map. The obstacles in the grid map divide the grid map into relatively fully credible areas and blind areas. The fully credible area can be regarded as a collection of multiple visible domains. Specifically, the fully credible area is , indicating that there are a visible domains under the grid map, and these a visible domains constitute a completely credible area. is the angle of the visible domain at the ath position relative to the target vehicle in the coordinate system, is the distance between the obstacle and the target vehicle coordinates at the ath visible domain The Euclidean distance of is the type of obstacle in the visible domain at the ath location; the target vehicle is the ego vehicle; is the identifier of the visible domain at position a: it indicates that the visible domain at position a is located relative to the target vehicle Direction, the Euclidean distance from the obstacle to the target vehicle coordinates is , the type of the ath obstacle.

[0042] in, ,when for , indicating that the type of obstacle in the visible domain at the ath position is a vehicle; when is pedestrian, indicating that the type of obstacle in the visible domain at the ath position is pedestrian; when If it is other, it means that the type of obstacle in the visible domain at the ath position is other types such as pillars.

[0043] Next, the grid map is traversed to obtain the area where obstacles exist in the grid map, which is recorded as the obstacle area. The obstacle set can be regarded as a set of multiple obstacle areas. Specifically, for each area where obstacles exist, the distance between the obstacle and the target vehicle in the world coordinate system is calculated. ; ; Among them, "obstacle exist" means "there is an obstacle", as D b 'The value is In contrast, "no obstacle exists" means "no obstacle exists", as D b 'The value is D max of the situation; among which, The angle of the visible domain at position b relative to the target vehicle in the coordinate system, is the Euclidean distance from the bth obstacle to the target vehicle coordinates; is the horizontal coordinate of the bth obstacle in the world coordinate system, is the ordinate of the bth obstacle in the world coordinate system; is the horizontal coordinate of the target vehicle in the world coordinate system, is the ordinate of the target vehicle in the world coordinate system; where, Indicates the default value, that is, the default distance set when there is no obstacle in this direction. Each area with obstacles is stored in , and finally obtain the obstacle set ,in, This is the area where the bth obstacle exists.

[0044] Finally, traverse the grid map and calculate the Euclidean distance to the nearest obstacle for each area without obstacles. Calculate the corresponding thermal value mapped in the thermal map (determine the thermal coefficient based on the type of obstacle and whether the obstacle area is in a completely credible area, and calculate the thermal coefficient based on the Euclidean distance Get thermal value): ; In the formula, “if obstacle in A visible and “if obstacle not in A visible " are two logical judgment statements, "if obstacle in A visible " means "when the obstacle is in the completely credible area", and at the same time "if obstacle type is car" is satisfied, that is, when the obstacle type is identified as a vehicle, the value is " * In contrast, in “if obstacle in A visible ", and at the same time meets "if obstacle type ispedestrian", that is, when the obstacle type is identified as pedestrian, the value is " "; In addition, in "if obstacle in A visible ", and if the obstacle is a vehicle or a pedestrian, which does not belong to the above two situations, the value is " ”; in contrast, in “if obstacle not in A visible ", that is, "when the obstacle is not in the completely credible area", the value is " ”; is the Euclidean distance between the cth obstacle-free area and the nearest obstacle; There are different types of obstacles in The thermal coefficient in Indicates that the nearest obstacle is the vehicle in The thermal coefficient in Indicates that the nearest obstacle is The thermal coefficient in Indicates that the nearest obstacle is a pillar or other type. The thermal coefficient in The obstacle is not there. The thermal coefficient in is the thermal coefficient threshold. . Preferably, the recommended value range is: .

[0045] Finally, by determining the thermal coefficient in the grid map to construct a thermal map, constructing a thermal map can make the target vehicle walk in the middle of the road and as far away from obstacles as possible. Being away from obstacles can give more time to deal with special situations, such as pedestrians or vehicles that suddenly appear, and there is enough time to avoid accidents. At the same time, the requirements for upstream perception accuracy are further reduced. At the same time, this application pays more attention to the spatial passability of the visible area (that is, the completely credible area), and does not kill the invisible area (that is, the blind spot) with a stick, but is more inclined to give a certain random small variable to the blind spot, so that the target vehicle has a certain probability of exploring the blind spot, especially in the right-angle turn scene, the exploration of the blind spot reflects the excellent cornering ability.

[0046] Preferably, before S110, S100 also includes: obtaining a grid map of the area where the target vehicle is located; specifically, obtaining the body chassis data of the target vehicle and the grid map of the sensing end. This application requires less data, and only requires the basic sensing end to be provided to the drivable area, which effectively reduces the dependence on sensors and effectively reduces the hardware cost required for technical applications.

[0047] Furthermore, S200 includes: S210: Obtaining a vehicle-related speed interval, an acceleration-related speed interval, and a collision-related speed interval; S220: Obtaining a vehicle-related angular velocity interval, an acceleration-related angular velocity interval, and a collision-related angular velocity interval; S230: Obtaining a speed domain according to the vehicle-related speed interval, the acceleration-related speed interval, and the collision-related speed interval; S240: Obtaining an angular velocity domain according to the vehicle-related angular velocity interval, the acceleration-related angular velocity interval, and the collision-related angular velocity interval; Among them, the vehicle-related speed range is: , the acceleration-related speed range is: , the collision-related velocity range is: ; The vehicle-related angular velocity range is: , the acceleration-related angular velocity range is: , the collision-related angular velocity range is: .

[0048] Specifically, the vehicle-related speed range of the target vehicle is obtained based on the scene restrictions and the vehicle's own parameter restrictions. The parking lot itself has a maximum speed constraint, and its driving principles need to be followed: , is the first vehicle-related speed threshold, is the second vehicle-related speed threshold; preferably, ; , which is the maximum speed limited by the scene. Based on the steering wheel limit of the vehicle itself, the vehicle-related angular velocity range of the target vehicle is obtained , the steering wheel of the target vehicle itself has a limit, which can be defined as: , is the first vehicle-related angular velocity threshold, is the second vehicle-related angular velocity threshold; preferably, , which is the minimum angular velocity value related to the vehicle body; , which is the maximum angular velocity value related to the vehicle body.

[0049] Obtain the acceleration-related speed range of the target vehicle based on comfort constraints Angular velocity range related to acceleration In a parking lot environment, both acceleration and deceleration need to be constrained. Rapid acceleration is not allowed, otherwise it will cause unsafe impacts on other people and other cars. Angular acceleration refers to the rate of change of the driver's steering wheel. The steering wheel will not change significantly per unit time, otherwise it will cause discomfort and may even cause harm to the vehicle and other cars: , is the first acceleration-related speed threshold, is the second acceleration-related speed threshold; preferably, , , is the speed of the target vehicle at the beginning of planning, is the difference in planning time points, is the minimum acceleration in the current scene, It is the maximum acceleration value in the current scene. , is the first acceleration-related angular velocity threshold, is the second acceleration-related angular velocity threshold; preferably, , , is the angular velocity of the ego vehicle at the beginning of planning; is the difference in planning time points; is the minimum angular acceleration in the current scene; is the maximum angular acceleration in the current scene.

[0050] Obtain collision-related speed range of target vehicle based on collision limit Angular velocity range related to collision , obtain the nearest collision distance of the target vehicle in the current state, and calculate the maximum speed that can be braked to ensure a safe distance: , is the first collision-related velocity threshold, is the second collision-related speed threshold; preferably, , , is the Euclidean distance between the target vehicle and the obstacle at the current relative speed and angular velocity. , is the first collision-related angular velocity threshold, is the second collision-related angular velocity threshold; preferably, , , for It is the maximum angular velocity in the current scene.

[0051] This application performs path planning through the vehicle's own parameters, scenario restrictions and driving parameters to minimize the demand for hardware. It can be deployed on a platform with lower computing power, without the need for large computing power support like deep learning algorithms. The path planning meets the requirements of vehicle dynamics and is in line with the physical laws of the real world. It is also a complete white-box planning that can effectively track and solve problems, rather than a black-box strategy like deep learning.

[0052] Furthermore, the velocity domain is: ; The angular velocity domain is: ;in, is the first vehicle-related speed threshold, is the first acceleration-related speed threshold, is the first collision-related speed threshold; is the second vehicle-related speed threshold, is the second acceleration-related speed threshold, is the second collision-related speed threshold; is the first vehicle-related angular velocity threshold, is the first acceleration-related angular velocity threshold, is the first collision-related angular velocity threshold; is the second vehicle-related angular velocity threshold, is the second acceleration-related angular velocity threshold, is the second collision-related angular velocity threshold.

[0053] Specifically, after obtaining the vehicle-related speed interval, acceleration-related speed interval, collision-related speed interval and the vehicle-related angular velocity interval, acceleration-related angular velocity interval, and collision-related angular velocity interval, the speed domain can be obtained through the vehicle-related speed interval, acceleration-related speed interval, and collision-related speed interval; the angular velocity domain can be obtained through the vehicle-related angular velocity interval, acceleration-related angular velocity interval, and collision-related angular velocity interval.

[0054] Among them, it can be expressed as , , is the first speed threshold, is the second speed threshold; , , is the first angular velocity threshold, is the second angular velocity threshold.

[0055] [Example 2] See also Figure 3The present embodiment further provides a non-navigation farthest feasible path planning system 100, which uses the non-navigation farthest feasible path planning method as in the first embodiment. The non-navigation farthest feasible path planning system 100 includes: a construction module 101, a first acquisition module 102, a second acquisition module 103, a screening module 104, a calculation module 105 and a control module 106. The construction module 101 is used to obtain a grid map of the area where the target vehicle is located, and to construct a heat map according to the grid map; the first acquisition module 102 is used to obtain a speed domain and an angular velocity domain of the target vehicle based on scene restrictions and vehicle parameter restrictions; the second acquisition module 103 is used to obtain j first trajectories of the target vehicle according to the speed domain and the angular velocity domain based on vehicle dynamics and vehicle collision conditions; the screening module 104 is used to screen out first trajectories that meet planning conditions from the j first trajectories to obtain a trajectory set, wherein i first trajectories are provided in the trajectory set, i≤j; the calculation module 105 is used to perform cost calculation on the i first trajectories in the trajectory set to obtain an optimal trajectory; and the control module 106 is used to control the target vehicle according to the optimal trajectory.

[0056] In a specific embodiment, the construction module 101, the first acquisition module 102, the second acquisition module 103, the screening module 104, the calculation module 105 and the control module 106 of the non-navigation longest feasible path planning system 100 cooperate to implement the non-navigation longest feasible path planning method as described in the first embodiment above, which will not be repeated here.

[0057] [Example 3] See also Figure 4 , this embodiment provides a structural schematic diagram of an electronic device 200, the electronic device 200, for example, includes a processor 220 and a memory 210 electrically connected to the processor 220, the memory 210 stores a computer program 211, and the processor 220 loads the computer program 211 to implement the non-navigation longest feasible path planning method as in the first embodiment.

[0058] [Example 4] See also Figure 5 This embodiment also provides a readable storage medium 300, which stores computer executable instructions 310. When the computer executable instructions 310 are read and executed by the processor 220, the electronic device 200 where the readable storage medium 300 is located is controlled to implement the non-navigation longest feasible path planning method as in the first embodiment.

[0059] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are only illustrative. For example, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0060] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned readable storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0061] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for planning the longest feasible path without navigation, characterized in that: The non-navigation farthest feasible path planning method comprises: Obtaining a grid map of the area where the target vehicle is located, and constructing a heat map based on the grid map; Acquire the speed domain and angular velocity domain of the target vehicle based on scene restrictions and vehicle parameter restrictions; Based on vehicle dynamics and vehicle collision conditions, obtaining j first trajectories of the target vehicle according to the velocity domain and the angular velocity domain; Filtering the first trajectories that meet the planning condition requirements from the j first trajectories to obtain a trajectory set, wherein the trajectory set is provided with i first trajectories, i≤j; Performing cost calculation on i first trajectories in the trajectory set to obtain an optimal trajectory; Controlling the target vehicle according to the optimal trajectory; The planning condition requirement is that the sampling duration of the first trajectory is within a sampling time range, and the sampling time range is: , and the first trajectory does not cause collision within the first sampling time.

2. The method for planning the longest feasible path without navigation according to claim 1, characterized in that: The controlling the target vehicle according to the optimal trajectory includes: Obtaining an optimal sampling time according to the sampling duration corresponding to the optimal trajectory; Processing the optimal trajectory according to the optimal sampling time and the first sampling time to obtain a target trajectory; The target vehicle is controlled according to the target trajectory.

3. The method for planning the longest feasible path without navigation according to claim 2, characterized in that: The processing of the optimal trajectory to obtain a target trajectory according to the optimal sampling time and the first sampling time includes: When the optimal sampling time is greater than the first sampling time, intercepting the optimal trajectory within the first sampling time as the target trajectory; and / or When the optimal sampling time is equal to the first sampling time, the target trajectory is the optimal trajectory.

4. According to the non-navigation farthest feasible path planning method of claim 1, the trajectory set is: , characterized in that, The performing cost calculation on the i first trajectories in the trajectory set to obtain an optimal trajectory includes: Calculating the cost of the first trajectory using a cost function; The cost function is: ; in, is the trajectory set, is the i-th first trajectory in the trajectory set; For the trajectory The speed cost function is For the trajectory The thermal cost function is For the trajectory The length cost function of For the trajectory Angular velocity cost function; The speed cost function is: ; The thermal cost function is: ; The length cost function is: ; The angular velocity cost function is: ; in, is the speed cost coefficient, For the trajectory At the track point speed, The maximum speed limited by the scene; is the thermal cost coefficient, It's a track At the track point The thermal value, It is the thermal value limit; is the length cost coefficient, For the trajectory Length; is the angular velocity cost coefficient, For the trajectory At the track point angular velocity.

5. The method for planning the longest feasible path without navigation according to claim 1, characterized in that: The step of obtaining a grid map of an area where the target vehicle is located and constructing a heat map according to the grid map includes: Initializing a fully trusted region under the grid map; Obtaining an obstacle existence area of ​​an obstacle in the grid map; Determining whether the obstacle-existing area is in the completely credible area; When the obstacle existing area is in the completely credible area, determining the thermal coefficient of the obstacle existing area according to the type of the obstacle; and / or When the obstacle existing area is not in the completely credible area, the thermal coefficient of the obstacle existing area is determined to be a thermal coefficient threshold.

6. The method for planning the longest feasible path without navigation according to claim 1, characterized in that: The obtaining of the speed domain and angular velocity domain of the target vehicle based on the scene restriction and the vehicle's own parameter restriction includes: Obtain vehicle-related speed intervals, acceleration-related speed intervals, and collision-related speed intervals; Obtain vehicle-related angular velocity intervals, acceleration-related angular velocity intervals, and collision-related angular velocity intervals; Obtaining the speed domain according to the vehicle-related speed interval, the acceleration-related speed interval, and the collision-related speed interval; Obtaining the angular velocity domain according to the vehicle-related angular velocity interval, the acceleration-related angular velocity interval, and the collision-related angular velocity interval; Wherein, the vehicle-related speed range is: , the acceleration-related speed range is: , the collision-related speed range is: ; The vehicle-related angular velocity range is: , the acceleration-related angular velocity interval is: , the collision-related angular velocity interval is: .

7. The method for planning the longest feasible path without navigation according to claim 6, characterized in that: The speed domain is: ; The angular velocity domain is: ; in, is the first vehicle-related speed threshold, is the first acceleration-related speed threshold, is the first collision-related speed threshold; is the second vehicle-related speed threshold, is the second acceleration-related speed threshold, is the second collision-related speed threshold; is the first vehicle-related angular velocity threshold, is the first acceleration-related angular velocity threshold, is the first collision-related angular velocity threshold; is the second vehicle-related angular velocity threshold, is the second acceleration-related angular velocity threshold, is the second collision-related angular velocity threshold.

8. A non-navigation farthest feasible path planning system, wherein the non-navigation farthest feasible path planning system uses the non-navigation farthest feasible path planning method according to any one of claims 1 to 7, characterized in that: include: A construction module, the construction module is used to obtain a grid map of the area where the target vehicle is located, and construct a heat map according to the grid map; A first acquisition module, the first acquisition module is used to acquire the speed domain and angular velocity domain of the target vehicle based on scene restrictions and vehicle parameter restrictions; A second acquisition module, the second acquisition module is used to acquire j first trajectories of the target vehicle according to the velocity domain and the angular velocity domain based on vehicle dynamics and vehicle collision conditions; A screening module, the screening module is used to screen out the first trajectories that meet the planning condition requirements from the j first trajectories to obtain a trajectory set, wherein the trajectory set is provided with i first trajectories, i≤j; A calculation module, the calculation module is used to calculate the cost of the i first trajectories in the trajectory set to obtain an optimal trajectory; A control module is used to control the target vehicle according to the optimal trajectory.

9. An electronic device, characterized in that: The electronic device comprises: a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the non-navigation longest feasible path planning method as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the non-navigation longest feasible path planning method as described in any one of claims 1 to 7 are implemented.

Images