CN116009530A - Path planning method and system for self-adaptive tangential obstacle avoidance - Google Patents
Path planning method and system for self-adaptive tangential obstacle avoidance Download PDFInfo
- Publication number
- CN116009530A CN116009530A CN202211460263.1A CN202211460263A CN116009530A CN 116009530 A CN116009530 A CN 116009530A CN 202211460263 A CN202211460263 A CN 202211460263A CN 116009530 A CN116009530 A CN 116009530A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- robot
- tangential
- path planning
- obstacle avoidance
- 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.)
- Pending
Links
Images
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a path planning method and a system for self-adaptive tangential obstacle avoidance, wherein the system comprises a laser radar, a raspberry pie, an STM32 controller, a motor and a motor driver; whether the obstacle influences the moving path of the robot or not is evaluated in importance and is divided into important obstacles and common obstacles, and only important obstacles need to be considered when the obstacle is tangentially avoided, so that the calculation complexity is reduced; the area division is carried out on the influence range of the repulsive force of the important obstacle, and the important obstacle is divided into a safe distance area, a tangential obstacle avoidance area and an artificial potential field area, so that the obstacle avoidance safety of the robot is improved; tangential obstacle avoidance is performed by using a fuzzy controller, so that the problem of local minimum value is avoided; meanwhile, the severe change of the resultant force direction in a narrow channel between obstacles is avoided, and the phenomenon of path oscillation is avoided.
Description
Technical Field
The invention relates to a path planning method and a system for self-adaptive tangential obstacle avoidance, and belongs to the technical field of path planning.
Background
The mobile robot moves to the target point according to a planning path of a global path planning algorithm such as an a-algorithm, but the a-algorithm can only plan a path under the condition of knowing global map information, and when an external environment changes, the a-algorithm cannot sense the change of the external environment, so that the robot collides with an obstacle, and path planning fails. Therefore, a local path planning algorithm capable of sensing environmental changes is required to complete obstacle avoidance work in cooperation with a global path planning algorithm.
At present, in the mainstream local path planning algorithm of several mobile robots, the model of a dynamic window method is complex, and the real-time performance of the planned path is long and obstacle avoidance is general due to prospective deficiency; the time elastic band method needs to calculate the speed and the angular speed in the control period through the distance difference, the angle difference and the time difference between the two states, so that the calculation complexity is high and the control is unstable; the artificial potential field method has the advantages of simple principle, good real-time performance and small calculation complexity, and is widely applied. However, the traditional artificial potential field method faces the problems of unreachable target, local minimum value, path oscillation and the like, and cannot well complete the path planning task in a complex environment; for the robot moving in the complex environment, the existing local path planning algorithm includes a dynamic window method, a time elastic band method, an artificial potential field method and the like. The dynamic window method has poor prospective and unstable control of the time elastic band method, and the model and the calculation complexity of the two algorithms are higher; the artificial potential field method has the advantages of simple principle, good real-time performance and small calculation complexity, but also has the defects of unreachable target, local minimum value, path oscillation and the like.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a self-adaptive tangential obstacle avoidance path planning method and a self-adaptive tangential obstacle avoidance system, which solve the problem of unreachable targets by improving the repulsive potential field function of the traditional artificial potential field method; the self-adaptive repulsion gain coefficient fuzzy controller ensures that the repulsion gain coefficient changes along with the change of the surrounding environment, thereby improving the adaptability of the robot to the change of the surrounding environment; through the tangential obstacle avoidance fuzzy controller, the local minimum problem and the path oscillation phenomenon of a narrow channel between obstacles are avoided.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows: a path planning system of self-adaptive tangential obstacle avoidance comprises a laser radar, a raspberry group, an STM32 controller, a motor and a motor drive;
the laser radar is used for collecting environmental information, communicating with the raspberry group through a USB interface and transmitting laser radar data to the map building unit;
the STM32 controller is used for completing control of the executing mechanism, transmitting information through the serial port and the raspberry group, and completing task scheduling such as acquisition speed, motion control and the like;
the raspberry group is used for global path planning and local path planning; the sensor data is subjected to map modeling through a map construction unit to generate a global cost map and a local cost map; after setting the target point, the global path planning unit completes global path planning and transmits the global path planning to the global path correction unit; the local path planning firstly calculates the distance between the robot and the obstacle, the resultant force and the angle between the obstacle, the attractive force and the tangential angle through a distance calculating unit and an angle calculating unit and fuzzifies, then carries out fuzzy reasoning and defuzzifies according to a fuzzy rule base, and finally completes the local path planning through a repulsive force gain coefficient self-adaptive adjusting unit and a self-adaptive tangential obstacle avoidance unit and transmits the local path planning to a correction unit for global path correction.
A path planning method of self-adaptive tangential obstacle avoidance comprises the following steps:
step one: adding a distance factor between the robot and the target point in the traditional repulsive force function to strengthen attractive force and weaken repulsive force; the improved repulsive force consists of two parts, namely a component force F rep1 Directed to the robot by an obstacle, force component F rep2 Pointing to a target point by a robot;
step two: the self-adaptive repulsion gain coefficient fuzzy controller takes the distance between the robot and the obstacle and the distance between the robot and the target point as input, and self-adaptively adjusts the repulsion gain coefficient according to a fuzzy rule;
step three: whether the obstacle affects the moving direction of the robot or not is evaluated to evaluate the importance of the obstacle, and the obstacle is divided into an important obstacle and a common obstacle; important obstacles are defined as: the included angle omega between the resultant force direction of the robot and the obstacle is smaller, and the distance d between the robot and the obstacle is closer or moderate; common obstacles are defined as: the resultant force direction of the robot has a larger included angle omega with the obstacle or the distance d between the robot and the obstacle is longer;
step four: for important obstacles, dividing the repulsive force influence range into a safe distance area, a tangential obstacle avoidance area and an artificial potential field area;
step five: for important obstacles, after the robot enters a tangential obstacle avoidance area, tangential obstacle avoidance is performed;
step six: the self-adaptive tangential obstacle avoidance fuzzy controller is designed into three inputs and one output, and the distance d between the robot and the obstacle, the resultant force, the angle omega of the obstacle, the attractive force and the adjusted repulsive force component F are calculated rep1 The included angle delta of the robot is used as input, and the robot is judged to be controlled by an artificial potential field in the potential field according to the output value output, so that the robot can avoid barriers in a tangential direction and brake in an emergency manner;
step seven: and finally, determining the motion mode of the robot according to the section where the output value of the fuzzy controller is located.
The specific steps of the fifth step are that firstly, the robot center and the obstacle center are connected by a straight line, and an intersection point is generated between the straight line and the obstacle boundary; calculating a straight line passing through the intersection point and tangent to the obstacle, and applying a repulsive force component F at that time rep1 The direction is regulated to be parallel to the straight line direction, and the direction is determined by the positive and negative of an included angle omega; defining a clockwise direction as a positive angle, a counterclockwise direction as a negative angle, and when the resultant force and the included angle of the obstacle are positive angles, the important obstacle is positioned on the right side of the robot, F rep1 Pointing to the left along parallel lines; when the included angle between the resultant force and the obstacle is a negative angle, the important obstacle is positioned at the left side of the robot, F rep1 Pointing to the right along parallel lines;
for the adjusted repulsive force component F rep1 If it is with the attraction force F att The included angle delta of the robot is smaller, and the robot keeps manual potential field control; if it is with the attraction force F att The included angle delta is larger, the robot starts to perform tangential obstacle avoidance, and moves by one step length according to the current resultant force direction; after moving one step length, the robot adjusts the direction of the repulsive force component according to the same method and continues to move one step length until the included angle delta is smaller, the robot exits from tangential obstacle avoidance, and manual potential field control is restored.
The beneficial effects of the invention are as follows: the invention is improved. The problem of unreachable targets is solved by improving the repulsive potential field function of the traditional artificial potential field method; the self-adaptive repulsion gain coefficient fuzzy controller ensures that the repulsion gain coefficient changes along with the change of the surrounding environment, thereby improving the adaptability of the robot to the change of the surrounding environment; through the tangential obstacle avoidance fuzzy controller, the local minimum problem and the path oscillation phenomenon of a narrow channel between obstacles are avoided.
Drawings
FIG. 1 is a graph of an improved repulsive force function force analysis of the present invention;
FIG. 2 is a diagram of an obstacle importance assessment of the present invention;
FIG. 3 is a schematic view of the important obstacle repulsive force influence range division of the present invention;
FIG. 4 is a schematic view of a robot performing tangential obstacle avoidance according to the present invention;
FIG. 5 is a schematic view of a robot exit tangential obstacle avoidance of the present invention;
FIG. 6 is a schematic diagram of a tangential obstacle avoidance process of a robot according to the present invention;
FIG. 7 is a schematic diagram of a path planning system according to the present invention;
FIG. 8 is a schematic diagram of different experimental environments for verifying the effectiveness of the invention, wherein (a) is an artificial potential field method after improving a repulsive force function, (b) is an artificial potential field method after adaptively adjusting a repulsive force gain coefficient through a fuzzy controller, and (c) is an artificial potential field method after adaptively tangentially avoiding obstacles;
FIG. 9 is a graph of an alignment of performance verification under varying environmental complexities of the present invention, graph (a) is the path effect of escape force method employed in a simple environment; FIG. (b) is a path effect of the tangential obstacle avoidance of the present invention in a simple environment; fig. (c) shows the path effect of escape force method in more complex environment; FIG. (d) is a path effect of a more complex environment employing the tangential obstacle avoidance of the present invention; fig. (e) shows the path effect of escape force method in complex environment; and (f) the path effect of adopting the tangential obstacle avoidance method in the complex environment.
Detailed Description
The present invention will be further described in detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the detailed description and specific examples, while indicating the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, and the terms used herein in this description of the invention are for the purpose of describing particular embodiments only and are not intended to be limiting of the invention.
The invention mainly aims to provide a path planning method for a mobile robot self-adaptive tangential obstacle avoidance under a complex environment and a hybrid path planning system. The method aims to overcome the defects of an artificial potential field method in local path planning and improve the performance in a complex environment.
In order to achieve the above purpose, the invention provides an adaptive tangential obstacle avoidance method of a mobile robot. The tangential obstacle avoidance device is characterized in that the direction of the component force of the repulsive force of the obstacle is continuously adjusted to be the tangential direction of the intersection point generated by the connecting line of the center of the robot and the center of the obstacle and the obstacle, and the robot makes circular motion around the obstacle to achieve the obstacle avoidance effect. The method comprises the following specific steps:
firstly, adding a distance factor between a robot and a target point in a traditional repulsive force function to strengthen attractive force and weaken repulsive force; the improved repulsive force consists of two parts, namely a component force F rep1 Directed to the robot by an obstacle, force component F rep2 The target point is pointed to by the robot as shown in fig. 1.
And secondly, the self-adaptive repulsion gain coefficient fuzzy controller takes the distance between the robot and the obstacle and the distance between the robot and the target point as input, and self-adaptively adjusts the repulsion gain coefficient according to a fuzzy rule, wherein the fuzzy rule is shown in the following table 1.
TABLE 1 repulsive force gain coefficient fuzzy rule table
{ HJ, JJ, SZ, JY, HY } in the first row of Table 1 is the fuzzy set of robot and obstacle distances, and the sequentially corresponding fuzzy linguistic variables are { very near, moderate, far }; { HJ, JJ, SZ, JY, HY } in the first column is a fuzzy set of distances between the robot and the target point, and the fuzzy language variables corresponding in sequence are consistent with d 1; NS, MD, PB are three different repulsive gain coefficients, respectively representing smaller, moderate, larger repulsive gain coefficients.
Secondly, whether an obstacle affects the moving direction of the robot is evaluated for importance of the obstacle, and is classified into an important obstacle and a general obstacle. Important obstacles are defined as: the included angle omega between the resultant force direction of the robot and the obstacle is smaller, and the distance d between the robot and the obstacle is closer or moderate; common obstacles are defined as: the resultant force direction of the robot has a larger included angle omega with the obstacle or the distance d between the robot and the obstacle is larger, as shown in fig. 2.
For important obstacles, dividing the repulsive force influence range into a safe distance area, a tangential obstacle avoidance area and an artificial potential field area as shown in fig. 3; in the figure, a plurality of circular rings constitute the range of influence of the obstacle repulsive force. The outside ring of the obstacle is a safe distance area, and the robot can take emergency braking after entering the area, so that collision with the obstacle is avoided. The outer circular ring of the safe distance area is a tangential obstacle avoidance area, and the robot continuously adjusts the repulsive force component F in the figure 3 in the area rep1 Is arranged to move the robot circumferentially around the obstacle. The outer circular ring of the tangential obstacle avoidance area is an artificial potential field area, and the robot keeps artificial potential field control in the area.
For important obstacles, the robot enters the tangential obstacle avoidance area of fig. 3, and then performs tangential obstacle avoidance. The robot center is first connected to the obstacle center in a straight line that creates an intersection with the obstacle boundary. Calculating a straight line passing through the intersection point and tangent to the obstacle, and applying a repulsive force component F at that time rep1 Is adjusted to be parallel to the straight line direction, and the direction is determined by the positive and negative of the middle included angle omega. The clockwise direction is defined as positive angle, the anticlockwise direction is negative angle, when the resultant force and the included angle of the obstacle are positive angle, the important obstacle is positioned on the right side of the robot, F rep1 Pointing to the left along parallel lines; when the resultant force and the obstacle form a negative angleImportant barriers are positioned on the left side of the robot, F rep1 Pointing to the right along parallel lines.
For the adjusted repulsive force component F rep1 If it is with the attraction force F att The included angle delta of the robot is smaller, and the robot keeps manual potential field control; if it is with the attraction force F att The included angle delta is larger, the robot starts to perform tangential obstacle avoidance, and moves by one step according to the current resultant force direction, as shown in fig. 4.
After moving one step, the robot adjusts the direction of the repulsive force component according to the same method and continues to move one step until the included angle delta is smaller, the robot exits from the tangential obstacle avoidance, and the manual potential field control is restored, as shown in fig. 5.
The self-adaptive tangential obstacle avoidance fuzzy controller is designed into three inputs and one output, and the distance d between the robot and the obstacle, the resultant force, the angle omega of the obstacle, the attractive force and the adjusted repulsive force component F are calculated rep1 The robot judges that the robot is controlled by the artificial potential field, tangential obstacle avoidance and emergency braking in the potential field according to the output value output. Tangential obstacle avoidance fuzzy controller semantics are shown in table 2.
Table 2 fuzzy semantic comparison table
The tangential obstacle avoidance fuzzy controller designs the following 10 fuzzy rules:
a.If(d is DN)then(output is ZE)；
b.If(d is DF)then(output is APF)；
c.If(d is DM)and(ω is FB)then(output is APF)；
d.If(d is DM)and(ω is ZB)then(output is APF)；
e.If(d is DM)and(ω is FS)and(δis QB)then(output is RQM)；
f.If(d is DM)and(ω is FS)and(δis QS)then(output is APF)；
g.If(d is DM)and(ω is ZS)and(δis QB)then(output is LQM)；
h.If(d is DM)and(ω is ZS)and(δis QS)then(output is APF)；
i.If(d is DM)and(ω is ZJ)and(δis QB)then(output is LQM)；
j.If(d is DM)and(ω is ZJ)and(δis QS)then(output is APF)；
and finally, determining the motion mode of the robot according to the section where the output value of the fuzzy controller is located, wherein the flow is shown as a figure 6.
The invention also provides a mixed path planning system suitable for the mobile robot, which is composed of a laser radar, a raspberry group, an STM32 controller, a motor and a motor drive as shown in fig. 7.
The laser radar is used for collecting environmental information, communicating with the raspberry group through the USB port and transmitting laser radar data to the map building unit.
The STM32 controller is used for completing control of the executing mechanism, information transmission is carried out through the serial port and the raspberry group, and task scheduling such as acquisition speed, motion control and the like is completed.
Raspberry groups are used for global path planning and local path planning. And carrying out map modeling on the sensor data through a map construction unit to generate a global cost map and a local cost map. After setting the target point, the global path planning unit completes global path planning and transmits the global path planning to the global path correction unit. The local path planning firstly calculates the distance between the robot and the obstacle, the resultant force and the angle between the obstacle, the attractive force and the tangential angle through a distance calculating unit and an angle calculating unit and fuzzifies, then carries out fuzzy reasoning and defuzzifies according to a fuzzy rule base, and finally completes the local path planning through a repulsive force gain coefficient self-adaptive adjusting unit and a self-adaptive tangential obstacle avoidance unit and transmits the local path planning to a correction unit for global path correction.
The invention further illustrates the rationality of the invention through the validity verification, the experimental environment is a two-dimensional space of 60m by 60m, and the starting point and the target point of the robot and the coordinates of the obstacle are set according to different experimental requirements. The gravitational coefficient of the traditional artificial potential field method is set to be 60 by default, the repulsive force coefficient is set to be 50, the moving step length of the robot is set to be 1m, the influence distance of the obstacle is set to be the radius of the obstacle plus 5m, and NS, MD and PB of the adaptive repulsive force gain coefficient fuzzy controller are respectively 10, 20 and 30. The experimental environment shown in fig. 8 is constructed by taking a magenta square as a robot starting point, taking a blue star as a target point, taking a black circle as an obstacle, taking a circle with a broken line outside the black circle as a safe distance area, and taking a planned path as a red small point. Fig. 8 (a) is an artificial potential field method after improving the repulsive force function, fig. 8 (b) is an artificial potential field method after adaptively adjusting the repulsive force gain coefficient by the fuzzy controller, and fig. 8 (c) is an artificial potential field method after adaptively tangentially avoiding the obstacle. Comparing fig. 8 (a) and fig. 8 (b), the manual potential field method after self-adaptive adjustment enables the robot to move forward for a certain period, but the robot still falls into a local minimum value because of unchanged collineation, and the robot avoids the local minimum value and smoothly reaches a target point after the tangential obstacle avoidance is added in fig. 8 (c), so that the effectiveness of the invention for solving the local minimum value is verified.
The invention also verifies performance under different environmental complexities. For this, three experimental environments of simplicity, more complexity and complexity were respectively constructed and compared with an artificial potential field method based on escape force, as shown in fig. 8.
As can be seen from fig. 9, the planned path of the escape method is longer in a simple, more complex environment; under a complex environment, the escape force method fails to successfully plan a path; the escape force method generates serious path concussion phenomenon when the narrow channel between obstacles moves, as shown in fig. 9 (c). The total step size and time consumption of path planning for three environmental complexities is shown in table 3. The result shows that under the simple and complex environment, compared with an escape method, the escape method disclosed by the invention has the advantages of better path planning and less time consumption in planning; under complex conditions, the invention can plan a better path and complete obstacle avoidance.
■ Table 3 comparative analysis
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, or alternatives falling within the spirit and principles of the invention.
Claims (3)
1. The self-adaptive tangential obstacle avoidance path planning system is characterized by comprising a laser radar, a raspberry group, an STM32 controller, a motor and a motor drive;
the laser radar is used for acquiring environmental information, communicating with the raspberry group through a USB interface and transmitting laser radar data to the map construction unit;
the STM32 controller is used for completing control of the executing mechanism, transmitting information through the serial port and the raspberry group, and completing task scheduling such as acquisition speed, motion control and the like;
the raspberry group is used for global path planning and local path planning; the sensor data is subjected to map modeling through a map construction unit to generate a global cost map and a local cost map; after setting the target point, the global path planning unit completes global path planning and transmits the global path planning to the global path correction unit; the local path planning firstly calculates the distance between the robot and the obstacle, the resultant force and the angle between the obstacle, the attractive force and the tangential angle through a distance calculating unit and an angle calculating unit and fuzzifies, then carries out fuzzy reasoning and defuzzifies according to a fuzzy rule base, and finally completes the local path planning through a repulsive force gain coefficient self-adaptive adjusting unit and a self-adaptive tangential obstacle avoidance unit and transmits the local path planning to a correction unit for global path correction.
2. The path planning method for the self-adaptive tangential obstacle avoidance is characterized by comprising the following steps of:
step one: adding a distance factor between the robot and the target point in the traditional repulsive force function to strengthen attractive force and weaken repulsive force; the improved repulsive force consists of two parts, namely a component force F rep1 Directed to the robot by an obstacle, force component F rep2 Pointing to a target point by a robot;
step two: the self-adaptive repulsion gain coefficient fuzzy controller takes the distance between the robot and the obstacle and the distance between the robot and the target point as input, and self-adaptively adjusts the repulsion gain coefficient according to a fuzzy rule;
step three: whether the obstacle affects the moving direction of the robot or not is evaluated to evaluate the importance of the obstacle, and the obstacle is divided into an important obstacle and a common obstacle; important obstacles are defined as: the included angle omega between the resultant force direction of the robot and the obstacle is smaller, and the distance d between the robot and the obstacle is closer or moderate; common obstacles are defined as: the resultant force direction of the robot has a larger included angle omega with the obstacle or the distance d between the robot and the obstacle is longer;
step four: for important obstacles, dividing the repulsive force influence range into a safe distance area, a tangential obstacle avoidance area and an artificial potential field area;
step five: for important obstacles, after the robot enters a tangential obstacle avoidance area, tangential obstacle avoidance is performed;
step six: the self-adaptive tangential obstacle avoidance fuzzy controller is designed into three inputs and one output, and the distance d between the robot and the obstacle, the resultant force, the angle omega of the obstacle, the attractive force and the adjusted repulsive force component F are calculated rep1 The included angle delta of the robot is used as input, and the robot is judged to be controlled by an artificial potential field in the potential field according to the output value output, so that the robot can avoid barriers in a tangential direction and brake in an emergency manner;
step seven: and finally, determining the motion mode of the robot according to the section where the output value of the fuzzy controller is located.
3. The method for planning a path for adaptive tangential obstacle avoidance according to claim 2, wherein the step five comprises the specific steps of connecting the robot center and the obstacle center in a straight line, wherein the straight line and the obstacle boundary form an intersection point; calculating a straight line passing through the intersection point and tangent to the obstacle, and applying a repulsive force component F at that time rep1 The direction is regulated to be parallel to the straight line direction, and the direction is determined by the positive and negative of the included angle w; defining a clockwise direction as a positive angle, a counterclockwise direction as a negative angle, and when the resultant force and the included angle of the obstacle are positive angles, the important obstacle is positioned on the right side of the robot, F rep1 Pointing to the left along parallel lines; when the included angle between the resultant force and the obstacle is a negative angle, the important obstacle is positioned at the left side of the robot, F rep1 Pointing to the right along parallel lines;
for the adjusted repulsive force component F rep1 If it is with the attraction force F att The included angle delta of the robot is smaller, and the robot keeps manual potential field control; if it is with the attraction force F att The included angle delta is larger, the robot starts to perform tangential obstacle avoidance, and moves by one step length according to the current resultant force direction; after moving one step length, the robot adjusts the direction of the repulsive force component according to the same method and continues to move one step length until the included angle delta is smaller, the robot exits from tangential obstacle avoidance, and manual potential field control is restored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211460263.1A CN116009530A (en) | 2022-11-17 | 2022-11-17 | Path planning method and system for self-adaptive tangential obstacle avoidance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211460263.1A CN116009530A (en) | 2022-11-17 | 2022-11-17 | Path planning method and system for self-adaptive tangential obstacle avoidance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116009530A true CN116009530A (en) | 2023-04-25 |
Family
ID=86036120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211460263.1A Pending CN116009530A (en) | 2022-11-17 | 2022-11-17 | Path planning method and system for self-adaptive tangential obstacle avoidance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116009530A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116540723A (en) * | 2023-05-30 | 2023-08-04 | 南通大学 | Underwater robot sliding mode track tracking control method based on artificial potential field |
-
2022
- 2022-11-17 CN CN202211460263.1A patent/CN116009530A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116540723A (en) * | 2023-05-30 | 2023-08-04 | 南通大学 | Underwater robot sliding mode track tracking control method based on artificial potential field |
| CN116540723B (en) * | 2023-05-30 | 2024-04-12 | 南通大学 | Underwater robot sliding mode track tracking control method based on artificial potential field |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111413966B (en) | Progressive model prediction unmanned planning tracking cooperative control method | |
| WO2018176593A1 (en) | Local obstacle avoidance path planning method for unmanned bicycle | |
| CN111506081B (en) | Robot trajectory tracking method, system and storage medium | |
| Tan et al. | Coordination control for multiple unmanned surface vehicles using hybrid behavior-based method | |
| CN107966907B (en) | Obstacle avoidance solution applied to redundant manipulator | |
| CN110488835B (en) | Unmanned system intelligent local path planning method based on double back propagation neural networks | |
| Xu et al. | COLREGs-abiding hybrid collision avoidance algorithm based on deep reinforcement learning for USVs | |
| US20200310444A1 (en) | Route determining device, robot, and route determining method | |
| CN115683145A (en) | Automatic driving safety obstacle avoidance method based on track prediction | |
| CN112506199B (en) | Local path planning method based on dynamic window method and suitable for Ackerman model robot | |
| CN113093804B (en) | Unmanned ship formation control method and control system based on inversion sliding mode control | |
| Qi et al. | Learning-based path planning and predictive control for autonomous vehicles with low-cost positioning | |
| Hong et al. | A modified dynamic window approach to obstacle avoidance combined with fuzzy logic | |
| CN116643572A (en) | Local path planning method, electronic equipment and medium for indoor complex environment | |
| CN116009530A (en) | Path planning method and system for self-adaptive tangential obstacle avoidance | |
| Chen et al. | Runtime safety assurance for learning-enabled control of autonomous driving vehicles | |
| Zhang et al. | Structured road-oriented motion planning and tracking framework for active collision avoidance of autonomous vehicles | |
| Sun et al. | Cooperative strategy for pursuit-evasion problem in the presence of static and dynamic obstacles | |
| Zhang et al. | Multi-UUV path planning based on improved artificial potential field method | |
| Zennir et al. | Comparison of PID and fuzzy controller for path tracking control of autonomous electrical vehicles | |
| CN116841298A (en) | Finite time tracking control method suitable for four-wheel mobile robot lane change early warning | |
| Lin et al. | A convolution neural network based obstacle avoiding method for unmanned underwater vehicle | |
| CN114943168B (en) | Method and system for combining floating bridges on water | |
| Cao et al. | Trajectory planning and tracking control of unmanned ground vehicle leading by motion virtual leader on expressway | |
| CN114046791A (en) | Vehicle path planning method based on layered monitoring domain and self-adaptive artificial potential field method |
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 |