CN115309163A - Local path planning method based on improved direction evaluation function DWA algorithm - Google Patents
Local path planning method based on improved direction evaluation function DWA algorithm Download PDFInfo
- Publication number
- CN115309163A CN115309163A CN202211028959.7A CN202211028959A CN115309163A CN 115309163 A CN115309163 A CN 115309163A CN 202211028959 A CN202211028959 A CN 202211028959A CN 115309163 A CN115309163 A CN 115309163A
- Authority
- CN
- China
- Prior art keywords
- point
- mobile platform
- dimensional navigation
- path
- navigation target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000011156 evaluation Methods 0.000 title claims abstract description 23
- 238000005070 sampling Methods 0.000 claims abstract description 16
- 238000004904 shortening Methods 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 claims description 23
- 230000004888 barrier function Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 9
- 230000001133 acceleration Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 claims description 2
- 238000003860 storage Methods 0.000 claims description 2
- 230000001360 synchronised effect Effects 0.000 claims description 2
- 230000002194 synthesizing effect Effects 0.000 claims description 2
- 230000001131 transforming effect Effects 0.000 claims description 2
- 238000013507 mapping Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- BLRPTPMANUNPDV-UHFFFAOYSA-N Silane Chemical compound [SiH4] BLRPTPMANUNPDV-UHFFFAOYSA-N 0.000 description 1
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a local path planning method based on an improved direction evaluation function (DWA) algorithm, which comprises the following steps of: the unmanned vehicle SLAM function synchronously positions and maps the environment, generates a grid map and a cost map, and issues a two-dimensional navigation target; a DWA algorithm generates a sampling track, and an improved direction evaluation function is used for calculating the cost of the sampling track; judging whether the minimum cost path is reachable or not, if a point with the occupation probability higher than a threshold value appears in the radius length of the position, judging that the point is unreachable, and shortening the radius to the position of the reachable point to be used as the direction of the next path point; and judging the included angle between the path point and the target point of the unmanned vehicle pair, if the included angle is larger than the threshold value, reissuing the two-dimensional navigation target, and if the included angle is within the threshold value range, driving to the two-dimensional navigation target. The method avoids the situation that the traditional DWA algorithm possibly falls into the local optimum, and solves the problem that the target point is always occupied or an obstacle is always on the side.
Description
Technical Field
The invention relates to the field of unmanned driving and machine vision, in particular to a local path planning method based on an improved direction evaluation function (DWA) algorithm.
Background
The DWA algorithm is proposed by Fox D et al and is used for carrying out local obstacle avoidance on the robot. Compared with other robot path planning algorithms, the DWA algorithm is used for sampling the linear velocity and the angular velocity in a constrained velocity vector space, obtaining a plurality of groups of tracks to be evaluated by utilizing a kinematic equation of the robot, then scoring the tracks to be evaluated, selecting the optimal track with the highest score, completing local path planning, and ensuring the feasibility of distributing velocity commands to the robot.
However, for the DWA algorithm, the orientation problem after the local path planning is not considered, and for the robot whose orientation is only simple to reach the radius of the target point, the pivot steering is feasible for some indoor application scenarios, but for the dynamic environment with pedestrians and vehicles at all times, the behavior obviously has a certain risk. Therefore, for local path planning of the mobile platform on the structured road, it is more necessary to continue to turn ahead instead of in situ after obstacle avoidance or lane change is completed like an automatic driving automobile. There is no good treatment for the worst case of the DWA algorithm, i.e. the case where the target point is always occupied or where there are obstacles present on the side all the time.
Disclosure of Invention
The invention aims to provide a local path planning method based on an improved direction evaluation function (DWA) algorithm, which aims to solve the problems that in the prior art, the DWA algorithm does not consider the direction after the local path planning is finished, a target point is always occupied or an obstacle always appears on the side.
In order to achieve the above purpose, the present invention provides the following technical solutions: in a first aspect, the present invention provides a local path planning method based on an improved direction evaluation function DWA algorithm, including:
synchronously positioning and drawing the environment through the SLAM function of the unmanned vehicle, generating a grid map and a cost map, and issuing a two-dimensional navigation target;
generating a sampling track by adopting a DWA algorithm, and performing sampling track cost calculation by using an improved direction evaluation function;
judging whether the minimum cost path can be reached, if a point with the occupation probability higher than a threshold value appears in the radius length of the position is selected, judging that the point can not be reached, and shortening the radius to the position of the reachable point to be used as the next path point direction;
and judging the included angle between the path point and the target point of the unmanned vehicle pair, if the included angle is larger than the threshold value, reissuing the two-dimensional navigation target, and if the included angle is within the threshold value range, driving to the two-dimensional navigation target.
In a second aspect, the invention provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of the first aspect when executing the program.
In a third aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of the first aspect.
In a fourth aspect, the invention provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of the method of the first aspect.
Compared with the prior art, the invention has the following beneficial effects: the structure of the invention adds the orientation of the unmanned vehicle after issuing the two-dimensional navigation points into the consideration category, and solves the orientation problem of DWA algorithm in the prior art after finishing the local path planning; whether the two-dimensional navigation target can be reached or not is preferentially judged, and the situation that a target point is occupied by an obstacle in the process of local path planning is effectively avoided; and (3) independently judging the included angle between the next path point and the target point by the mobile platform, and generating error prediction on the traditional DAW algorithm when an obstacle always appears on the side.
Drawings
FIG. 1 is a schematic overall flow chart of the present invention.
Fig. 2 is a schematic diagram of two-dimensional point issue and unmanned vehicle orientation.
Fig. 3 is a schematic diagram of sampling points and road prediction.
Fig. 4 is a schematic diagram of a front obstacle blocking an object.
Fig. 5 is a schematic diagram of the following movement and the included angle of the side obstacle.
Detailed Description
With reference to the attached drawings, a local path planning method based on a DWA algorithm of an improved direction evaluation function comprises the following steps:
step 1, as shown in figure 1, starting the synchronous positioning and map building functions of the mobile platform, transforming a laser radar coordinate system, a base coordinate system and a milemeter coordinate system through the functions, issuing map original data, grid map data and robot posture distribution entropy data, and generating a grid map and a cost map by using an external computer. Starting a navigation function package for navigation of a mobile platform, issuing a two-dimensional navigation target (2D Nav Goal), designating the pose of the mobile platform to be required to go to the position, acquiring the current orientation of the mobile platform, considering the orientation as one of evaluation criteria, calculating the angle to which the two-dimensional navigation target is required to point as shown in FIG. 2, issuing one two-dimensional navigation target in the direction of pointing to the next path point at the position of the radius R of the grid map where the mobile platform is located, and solving the problem of acquiring the orientation of an unmanned vehicle while planning the path. Optionally, the current orientation of the mobile platform is obtained by subscribing to the mavros/global _ position/assembly _ hdg topic.
Step 2, define V s The method is a set of linear velocity and angular velocity of the mobile platform, namely the maximum range of local path searching and solving by DWA algorithm:
V s ＝{(v,ω)|v∈[v min ,v max ],ω∈[ω min ,ω max ]}
definition V a For linear velocity and angular velocity of moving platform without collision with obstacle
And
for the maximum line deceleration and the maximum angular deceleration of the mobile platform, distance (v, ω) is defined as the Distance from the obstacle on the track corresponding to the velocity (v, ω), and then:
considering the limitation of the torque of the motor of the mobile platform, one control period T s The maximum and minimum reachable speed change ranges of the mobile platform exist, so that the dynamic window needs to be reduced, and v is defined c And ω c For the current linear and angular velocities of the mobile platform, define
And
the maximum linear acceleration and angular acceleration of the mobile platform are as follows:
synthesizing the maximum speed constraint of the mobile platform, the collision-free constraint with the barrier and the motor torque constraint of the mobile platform to obtain a dynamic window set:
V＝V s ∩V a ∩V b
in the velocity vector space V, as shown in fig. 3, according to the number of sampling points of the linear velocity and the angular velocity, the continuous velocity vector space V can be discretized to obtain discrete sampling points (V, ω), and for each sampling point, the motion trajectory of the mobile platform can be given according to the kinematic equation of the mobile platform, as shown in fig. 3;
the invention provides a direction evaluation sub-function introduced into an evaluation function, which removes the following of a local path to a global optimal path, and the direction evaluation sub-function is as follows:
wherein psi GPS Direction of the next waypoint to which the mobile platform is to be steered, psi i In order to plan the direction pointed by the destination of the path to be selected, whether the direction of the mobile platform at the moment points to the direction of the next path point is judged, if the direction is close to the direction, the cost is lower, and if the direction is far away from the direction, the cost is higher, and the improved overall evaluation function is as follows:
Cost(v,ω)＝αObs(v,ω)+βDir(v,ω)+γGdist(v,ω)
the method comprises the following steps of selecting a path with the highest score as a local optimal path of a current mobile platform, and taking the path direction as a brand-new assessment standard to be incorporated into a local path planning flow.
And 3, after the optimal path is selected, continuously judging whether the barrier occupies the two-dimensional navigation target or not in the process of driving the mobile platform along the planned path, wherein as shown in fig. 4, the cost of reaching the target point of the mobile platform is high at this time, although the mobile platform does not collide with the barrier where the target point is located, the planned path always surrounds the barrier, the mobile platform can always move around the barrier, at this time, a judgment threshold needs to be set in advance, if the occupation probability is higher than the threshold within the radius length of the obtained position, the point is regarded as an unreachable point, the radius is shortened to the position of the reachable point, the situation that the two-dimensional navigation target of the mobile platform cannot be reached is judged as the direction from the mobile platform to the next path point at this time, if the two-dimensional navigation target cannot be reached, the two-dimensional navigation target is issued again in the direction pointing to the next path point at the radius R of the mobile platform, so as to get rid of the occupation of the barrier to the two-dimensional navigation target, and the situation that the barrier occupies the two-dimensional navigation target in the process of local path planning can be effectively avoided.
And 4, judging whether a side has a barrier to move forward together with the mobile platform and block the situation that the side moves to a target point, judging an included angle between the mobile platform and the next path point and between the mobile platform and the target point in order to prevent the mobile platform from reversely moving or falling into local optimum and not moving forward any more, setting a threshold value for judging the included angle to be a larger acute angle, continuing to move forward if the included angle is smaller than or equal to the threshold value, and issuing a two-dimensional navigation target pointing to the next path point at a far end again if the included angle is an obtuse angle larger than the set threshold value, repeating the second-step value judgment until the two-dimensional navigation target successfully passes through the threshold value detection, and finishing local path planning. The step effectively avoids the problem that the traditional DWA algorithm mobile platform has a large included angle with a lane line to generate wrong prediction.
In the embodiment, the verification of the design algorithm is completed based on an RIA-R100 mobile platform produced by Shanghai silicon step scientific instruments, and the RIA-R100 mobile platform is loaded with a Velodyne VLP-16 laser radar, an Intel RealSense D435 depth camera, a U-Blox 7GPS module, an HC-SR04 ultrasonic radar and a Silan RPLIDAR-A2 laser radar. The external notebook computer uses a main frequency 2.60GHz Intel i7-9750H processor, and is provided with a 16GB memory and an Inviada RTX2060 display card, and the operating system is Win 10.
Based on the above, when the direction evaluation function DWA algorithm is used for local path planning, the problems that the direction of the DWA algorithm after the local path planning is finished is not considered, the target point is always occupied or an obstacle appears on the side edge all the time in the prior art can be effectively solved.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, it is possible to make various changes and modifications without departing from the inventive concept, and these changes and modifications are all within the scope of the present invention.
Claims (8)
1. A local path planning method based on an improved direction evaluation function (DWA) algorithm is characterized by comprising the following steps:
synchronously positioning and drawing the environment through the SLAM function of the unmanned vehicle, generating a grid map and a cost map, and issuing a two-dimensional navigation target;
generating a sampling track by adopting a DWA algorithm, and performing sampling track cost calculation by using an improved direction evaluation function;
judging whether the minimum cost path can be reached, if a point with the occupation probability higher than a threshold value appears in the radius length of the position is selected, judging that the point can not be reached, and shortening the radius to the position of the reachable point to be used as the next path point direction;
and judging the included angle between the path point and the target point of the unmanned vehicle, if the included angle is larger than the threshold value, reissuing the two-dimensional navigation target, and if the included angle is within the threshold value range, driving to the two-dimensional navigation target.
2. The local path planning method based on the DWA algorithm is characterized in that the environment is synchronously positioned and mapped through the SLAM function of the unmanned vehicle, a grid map and a cost map are generated, and a two-dimensional navigation target is issued, and the method specifically comprises the following steps:
starting a synchronous positioning and mapping function of the mobile platform, transforming a laser radar coordinate system, a base coordinate system and a milemeter coordinate system through the function, issuing map original data, grid map data and robot posture distribution entropy data, and generating a grid map and a cost map;
starting a navigation function package for navigation of the mobile platform, issuing a pose of a two-dimensional navigation target to designate the mobile platform to go to the position, acquiring the current orientation of the mobile platform, calculating the angle to which the two-dimensional navigation target needs to point, and issuing a two-dimensional navigation target in the direction of pointing to the next path point at the position of the grid map where the mobile platform is located and the radius R of the two-dimensional navigation target.
3. The local path planning method based on the improved direction evaluation function DWA algorithm of claim 1, characterized in that, the sampling trajectory is generated by adopting the DWA algorithm, and the improved direction evaluation function is used for calculating the cost of the sampling trajectory, specifically as follows:
definition V s The method is a set of linear velocity and angular velocity of the mobile platform, namely the maximum range of local path searching and solving by DWA algorithm:
V s ＝{(v,ω)|v∈[v min ,v max ],ω∈[ω min ,ω max ]}
definition V a For the linear velocity and angular velocity of the moving platform without collision with the obstacle when moving, defining
And
for the maximum line deceleration and the maximum angular deceleration of the mobile platform, distance (v, ω) is defined as the Distance from the obstacle on the track corresponding to the velocity (v, ω), and then:
reducing the dynamic window to define v c And ω c For the current linear and angular velocities of the mobile platform, define
And
the maximum linear acceleration and angular acceleration of the mobile platform are as follows:
synthesizing the maximum speed constraint of the mobile platform, the collision-free constraint with the barrier and the motor torque constraint of the mobile platform to obtain a dynamic window set:
V＝V s ∩V a ∩V b
in the velocity vector space V, discretizing the continuous velocity vector space V according to the number of sampling points of linear velocity and angular velocity to obtain discrete sampling points (V, omega), giving a motion track of the mobile platform according to a kinematic equation of the mobile platform for each sampling point, and introducing a direction evaluation subfunction which is as follows:
wherein psi GPS Direction of the next waypoint to which the mobile platform is required to steer, /) i In order to plan the direction pointed by the destination of the path to be selected, it is determined whether the direction of the mobile platform at this time points to the direction of the next path point, if the direction is close to the direction, the cost is lower, and if the direction is far from the direction, the cost is higher, and the improved overall evaluation function is as follows:
Cost(v,ω)＝αObs(v,ω)+βDir(v,ω)+γGdist(v,ω)
the method comprises the following steps of firstly, selecting a track with the highest score as a current local optimal path of a mobile platform, wherein alpha, beta and gamma are coefficients, obs (v, omega) is the total cost of the track passing through a total grid, the track with obstacles is directly abandoned, gdist (v, epsilon) is the distance from a track end point to a target point, and the three subfunctions are subjected to weighted operation by combining with a direction evaluation subfunction to be used as an evaluation standard of the optimal local path.
4. The local path planning method based on the DWA algorithm according to claim 1, wherein the method specifically comprises the steps of judging whether the minimum cost path is reachable, if a point with an occupation probability higher than a threshold value appears in the radius length of the position, judging that the point is not reachable, and shortening the radius to the position of the reachable point as the next path point direction:
after the optimal path is selected, the mobile platform continues to judge whether the obstacle occupies the two-dimensional navigation target all the time in the process of driving along the planned path, a judgment threshold value is set, if the occupation probability appears in the radius length of the obtained position and is higher than the judgment threshold value, the point is considered to be an unreachable point, the radius is shortened until the point is the position of the reachable point, the unreachable situation of the two-dimensional navigation target of the mobile platform is judged as the direction of the mobile platform going to the next path point at the moment, and if the two-dimensional navigation target is unreachable at the moment, the two-dimensional navigation target is issued in the direction pointing to the next path point at the position away from the radius R of the mobile platform again, so that the occupation of the obstacle on the two-dimensional navigation target is avoided.
5. The local path planning method based on the DWA algorithm is characterized in that the included angle between the path point and the target point of the unmanned vehicle is judged, if the included angle is larger than a threshold value, the two-dimensional navigation target is released again, and if the included angle is within the threshold value range, the unmanned vehicle drives to the two-dimensional navigation target, specifically as follows:
judging whether the side has obstacles to move forward together with the mobile platform, stopping the situation that the side moves to a target point, judging the included angle between the mobile platform and the next route point and between the mobile platform and the target point, continuing to move forward if the included angle is less than or equal to a threshold value, and if the included angle is greater than the set threshold value, issuing a two-dimensional navigation target pointing to the next route point at the far end again, and repeating the second step of value judgment until the two-dimensional navigation target smoothly passes through the threshold value detection.
6. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1-5 are implemented when the program is executed by the processor.
7. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
8. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211028959.7A CN115309163B (en) | 2022-08-26 | 2022-08-26 | Local path planning method based on improved direction evaluation function DWA algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211028959.7A CN115309163B (en) | 2022-08-26 | 2022-08-26 | Local path planning method based on improved direction evaluation function DWA algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115309163A true CN115309163A (en) | 2022-11-08 |
| CN115309163B CN115309163B (en) | 2024-01-26 |
Family
ID=83865019
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211028959.7A Active CN115309163B (en) | 2022-08-26 | 2022-08-26 | Local path planning method based on improved direction evaluation function DWA algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115309163B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115826590A (en) * | 2023-02-21 | 2023-03-21 | 山东大学 | Mobile robot local path planning method and system with adaptive parameters |
| CN117111617A (en) * | 2023-10-23 | 2023-11-24 | 山东优宝特智能机器人有限公司 | Robot path planning method and system considering collision uncertainty of perception dead zone |
| WO2024102042A1 (en) * | 2022-11-09 | 2024-05-16 | Telefonaktiebolaget Lm Ericsson (Publ) | Controlling a device to sense an environment around the device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108549378A (en) * | 2018-05-02 | 2018-09-18 | 长沙学院 | A kind of mixed path method and system for planning based on grating map |
| CN108628324A (en) * | 2018-07-12 | 2018-10-09 | 中国科学院深圳先进技术研究院 | Unmanned vehicle navigation method, device, equipment based on map vector and storage medium |
| CN109582038A (en) * | 2018-12-28 | 2019-04-05 | 中国兵器工业计算机应用技术研究所 | A kind of unmanned plane paths planning method |
| AU2020101429A4 (en) * | 2020-07-21 | 2020-08-20 | Aditya Nag, Mannepalli Venkata MR | Guidance algorithm for ugv using ioe systems and fog computing |
| CN111780777A (en) * | 2020-07-13 | 2020-10-16 | 江苏中科智能制造研究院有限公司 | Unmanned vehicle route planning method based on improved A-star algorithm and deep reinforcement learning |
| CN112378408A (en) * | 2020-11-26 | 2021-02-19 | 重庆大学 | Path planning method for realizing real-time obstacle avoidance of wheeled mobile robot |
| CN112817315A (en) * | 2020-12-31 | 2021-05-18 | 江苏集萃智能制造技术研究所有限公司 | Obstacle avoidance method and system for unmanned cleaning vehicle in dynamic environment |
| CN112947422A (en) * | 2021-01-28 | 2021-06-11 | 电子科技大学 | Navigation control method and platform for ROS unmanned vehicle |
| CN113110431A (en) * | 2021-04-03 | 2021-07-13 | 南京理工大学 | Real-time planning method for field test path of unmanned target vehicle |
-
2022
- 2022-08-26 CN CN202211028959.7A patent/CN115309163B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108549378A (en) * | 2018-05-02 | 2018-09-18 | 长沙学院 | A kind of mixed path method and system for planning based on grating map |
| CN108628324A (en) * | 2018-07-12 | 2018-10-09 | 中国科学院深圳先进技术研究院 | Unmanned vehicle navigation method, device, equipment based on map vector and storage medium |
| CN109582038A (en) * | 2018-12-28 | 2019-04-05 | 中国兵器工业计算机应用技术研究所 | A kind of unmanned plane paths planning method |
| CN111780777A (en) * | 2020-07-13 | 2020-10-16 | 江苏中科智能制造研究院有限公司 | Unmanned vehicle route planning method based on improved A-star algorithm and deep reinforcement learning |
| AU2020101429A4 (en) * | 2020-07-21 | 2020-08-20 | Aditya Nag, Mannepalli Venkata MR | Guidance algorithm for ugv using ioe systems and fog computing |
| CN112378408A (en) * | 2020-11-26 | 2021-02-19 | 重庆大学 | Path planning method for realizing real-time obstacle avoidance of wheeled mobile robot |
| CN112817315A (en) * | 2020-12-31 | 2021-05-18 | 江苏集萃智能制造技术研究所有限公司 | Obstacle avoidance method and system for unmanned cleaning vehicle in dynamic environment |
| CN112947422A (en) * | 2021-01-28 | 2021-06-11 | 电子科技大学 | Navigation control method and platform for ROS unmanned vehicle |
| CN113110431A (en) * | 2021-04-03 | 2021-07-13 | 南京理工大学 | Real-time planning method for field test path of unmanned target vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 吕海泳: "基于视觉SLAM 的无人运转车导航系统设计", 《山东工业技术》, vol. 5, no. 3, pages 100 - 106 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024102042A1 (en) * | 2022-11-09 | 2024-05-16 | Telefonaktiebolaget Lm Ericsson (Publ) | Controlling a device to sense an environment around the device |
| CN115826590A (en) * | 2023-02-21 | 2023-03-21 | 山东大学 | Mobile robot local path planning method and system with adaptive parameters |
| CN115826590B (en) * | 2023-02-21 | 2023-06-02 | 山东大学 | Mobile robot local path planning method and system with self-adaptive parameters |
| CN117111617A (en) * | 2023-10-23 | 2023-11-24 | 山东优宝特智能机器人有限公司 | Robot path planning method and system considering collision uncertainty of perception dead zone |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115309163B (en) | 2024-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7001628B2 (en) | Planning of parking tracks for self-driving vehicles | |
| US10884422B2 (en) | Method for generating trajectories for autonomous driving vehicles (ADVS) | |
| US10782699B2 (en) | Real-time perception adjustment and driving adaption based on surrounding vehicles' behavior for autonomous driving vehicles | |
| US10816990B2 (en) | Non-blocking boundary for autonomous vehicle planning | |
| US10823575B2 (en) | Reference line smoothing method using piecewise spiral curves with weighted geometry costs | |
| US10678248B2 (en) | Fast trajectory planning via maneuver pattern selection | |
| US10429849B2 (en) | Non-linear reference line optimization method using piecewise quintic polynomial spiral paths for operating autonomous driving vehicles | |
| US11199847B2 (en) | Curvature corrected path sampling system for autonomous driving vehicles | |
| US20220080961A1 (en) | Control system and control method for sampling based planning of possible trajectories for motor vehicles | |
| US20190243370A1 (en) | Systems and methods for accelerated curve projection | |
| US10908608B2 (en) | Method and system for stitching planning trajectories from consecutive planning cycles for smooth control execution of autonomous driving vehicles | |
| US11055540B2 (en) | Method for determining anchor boxes for training neural network object detection models for autonomous driving | |
| WO2018131090A1 (en) | Vehicle control device, vehicle control method, and vehicle control program | |
| CN115309163A (en) | Local path planning method based on improved direction evaluation function DWA algorithm | |
| US11360482B2 (en) | Method and system for generating reference lines for autonomous driving vehicles using multiple threads | |
| US11353878B2 (en) | Soft-boundary based path optimization for complex scenes for autonomous driving vehicles | |
| US11106212B2 (en) | Path planning for complex scenes with self-adjusting path length for autonomous driving vehicles | |
| US10732632B2 (en) | Method for generating a reference line by stitching multiple reference lines together using multiple threads | |
| US11474525B2 (en) | Method and apparatus for method for dynamic multi-segment path and speed profile shaping | |
| EP3925844B1 (en) | Relative speed based speed planning for buffer area | |
| US11724717B2 (en) | Implementation of dynamic cost function of self-driving vehicles | |
| US20220019228A1 (en) | Mobile object control method, mobile object control device, mobile object and storage medium | |
| CN117916682A (en) | Motion planning using a time-space convex corridor | |
| EP4151490B1 (en) | Safety guaranteed control when planning with uncertainty | |
| US20240140432A1 (en) | Long-distance autonomous lane change |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |