CN113050648A - Robot obstacle avoidance method and system - Google Patents
Robot obstacle avoidance method and system Download PDFInfo
- Publication number
- CN113050648A CN113050648A CN202110312055.6A CN202110312055A CN113050648A CN 113050648 A CN113050648 A CN 113050648A CN 202110312055 A CN202110312055 A CN 202110312055A CN 113050648 A CN113050648 A CN 113050648A
- Authority
- CN
- China
- Prior art keywords
- robot
- simulation
- simulation time
- preset
- 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
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Abstract
The invention discloses a robot obstacle avoidance method and system, wherein the method comprises the following steps: the robot plans a global optimal path leading to a preset target point, and then carries out motion simulation by combining sensor data and dynamically-changed simulation time so as to obtain an optimal movement track of the robot adapting to terrain at the next moment. The invention improves the classic dynamic window method, and can realize self-adaptive obstacle avoidance by dynamically adjusting the simulation time through a self-adaptive fuzzy method under different obstacle distributions.
Description
Technical Field
The invention relates to the field of robots, in particular to a robot obstacle avoidance method and system.
Background
In a moving robot, obstacle avoidance is an essential function. The dynamic window method is one of the classical local planning algorithms, because of high real-time performance and low complexity, which is often applied to robots. However, the classical dynamic window method has limitations, and only the simulation time with a fixed scale is adopted in the calculation of motion simulation each time, so that obstacle avoidance can only adapt to a narrow area or an open area singly. How to enable the robot to use the dynamic window method to realize the adaptive obstacle avoidance of multiple terrains is a challenge currently facing.
Disclosure of Invention
In order to solve the problems, the invention provides a robot obstacle avoidance method and system, which enable a robot to realize multi-terrain self-adaptive obstacle avoidance by using a dynamic window method through adjusting simulation time. The specific technical scheme of the invention is as follows:
a robot obstacle avoidance method comprises the following steps: s1, the robot plans a global optimal path going to a preset target point on the static map; s2, the robot reads data needed by motion simulation, then sets simulation time and carries out motion simulation by combining the global optimal path to obtain a plurality of simulation tracks; s3, the robot detects the simulation track to judge whether the simulation time needs to be adjusted, if not, the robot selects the optimal movement track to move, then returns to S2 to execute until the robot reaches a preset target point, and if so, the robot enters S4; and S4, adjusting the simulation time by the robot, detecting whether the simulation time meets the preset condition, if so, performing motion simulation again, returning to S3, otherwise, executing the preset action, and returning to S2. The method of the invention can dynamically adjust the simulation time of the robot, and the robot plans the optimal moving path according to the corresponding simulation time, thereby improving the obstacle avoidance capability of the robot.
Further, in step S2, the data required by the motion simulation includes current pose information, motion parameters, and a sampling speed, where the current pose information includes current position coordinates of the robot and a current head orientation angle, the motion parameters include a radius of the robot, a wheel distance, and a default acceleration, the sampling speed is obtained by sampling through a speed sampling window formed by current speed information of the robot and the default acceleration, and the speed information is provided by a speed sensor.
Further, the method for setting the simulation time in step S2 is that the robot determines whether the number of the obstacle point clouds in the preset range of the current position of the robot is smaller than a preset number, if not, the robot adopts a first preset time as the simulation time, if so, the robot adopts a second preset time as the simulation time, and the first preset time is smaller than the second preset time. Smaller simulation time is adopted in narrow areas with dense obstacles, collision of simulation tracks obtained through simulation can be avoided, and larger simulation time is adopted in open areas with few obstacles, so that the simulation tracks can be prevented from falling into oscillation or local optimal solution.
Further, the method for determining whether the simulation time needs to be adjusted in step S3 is that the simulation time needs to be adjusted if the robot detects that all simulation tracks show collision, and the simulation time does not need to be adjusted if the robot detects that at least one collision-free simulation track exists. Adjusting the simulation time allows the robot to better walk in a narrow area.
Further, the method for obtaining the optimal movement trajectory in step S3 is that the robot inputs the simulation trajectory, the global optimal path, the obstacle point cloud information, and the weight information into a trajectory cost function to perform weighting calculation, where the simulation trajectory with the lowest cost function value is the optimal movement trajectory. The optimal moving track obtained by using the evaluation function for weighting calculation can enable the robot to walk better and faster.
Further, the method for adjusting the simulation time in step S4 is to set a constant first, and then decrease the simulation time until at least one collision-free simulation trajectory is detected after the motion simulation or the simulation time is shortened to a preset value. Adjusting the simulation time allows the robot to better walk in a narrow area.
Further, the method for detecting whether the simulation time meets the preset condition in step S4 includes setting a preset minimum value, comparing the simulation time with the preset minimum value, if the simulation time is greater than the preset minimum value, the simulation time meets the preset condition, otherwise, the simulation time does not meet the preset condition. When the simulation time is shortened to the minimum value, the motion simulation is not carried out any more, and the simulation track is prevented from being involved in oscillation.
Further, the preset action performed by the robot in step S4 is that the robot travels straight at a default speed until the collision sensor detects a collision, and then turns to the robot and stops when no obstacle is detected in front. Executing the preset action can adjust the position of the robot to set the appropriate simulation time and perform the motion simulation again, thereby obtaining the optimal moving path at the next moment.
A robot obstacle avoidance system comprises a parameter module, a sensor module, a global planner and a local planner, wherein the parameter module is connected with the global planner and the local planner and used for providing preset parameters comprising a static map, a robot radius, a wheel interval and default acceleration; a sensor module connected to the local planner for providing sensor data; the global planner is connected with the parameter module and the local planner and is used for generating a global optimal path; and the local planner dynamically adjusts simulation time to perform motion simulation to generate an optimal moving track at the next moment by receiving and analyzing data of the parameter module, the sensor module and the global planner, so that multi-terrain self-adaptation of the robot is realized. The robot of the system can dynamically adjust the simulation time of the robot, and the robot plans the optimal moving path according to the corresponding simulation time, so that the obstacle avoidance capability of the robot is improved.
Further, the sensor module includes a speed sensor, a laser sensor, and an impact sensor. The sensors are used for providing data required by the motion simulation process of the robot.
Further, the local planner includes an adaptive fuzzy method framework and a dynamic window method framework, wherein the adaptive fuzzy method framework dynamically adjusts simulation time using data of the sensor module; the dynamic window method framework generates the optimal movement track of the next moment by using the data of the parameter module, the sensor module, the global planner and the self-adaptive fuzzy method framework. The self-adaptive fuzzy method frame can solve the limitation problem that only fixed-scale simulation time is adopted in a classic dynamic window method, the dynamic variable simulation time is transmitted to the dynamic window method for motion simulation, and the optimal moving track of the robot at the next moment under different terrains can be obtained.
Drawings
Fig. 1 is a diagram illustrating an obstacle avoidance system of a robot according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a local planner according to an embodiment of the invention.
Fig. 3 is a block diagram of an adaptive fuzzy method according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described in detail below with reference to the accompanying drawings in the embodiments of the present invention. It should be understood that the following specific examples are illustrative only and are not intended to limit the invention.
As shown in fig. 1, a robot obstacle avoidance system includes a parameter module, a sensor module, a global planner, and a local planner. The parameter module is a virtual module formed by different data, is connected with the global planner and the local planner and is used for providing preset parameters including a static map, a robot radius, a wheel interval and default acceleration. The static map can be used for providing necessary information for searching a global optimal path, pose information of the robot and the like, and the use of the map belongs to the prior art and is not described herein again. The sensor module is connected to the local planner for providing sensor data, the sensor module being a physical module comprising a speed sensor, a laser sensor and a collision sensor. The speed sensor can provide linear speed and angular speed information required by robot motion simulation, the linear speed is the moving instant speed of the robot, and when the linear speeds of the left and right wheels of the robot are not consistent, the angular speeds are different. The laser sensor may provide obstacle point cloud information around the robot as a reference for setting simulation time. The collision sensor can control the robot to steer when the robot collides. The global planner is a virtual module compiled by codes, is connected with the parameter module and the local planner, can generate a global optimal path after receiving the static map of the parameter module, and then transmits the global optimal path as input to the local planner for motion simulation. The local planner is a core component in the system and is also a virtual module compiled by codes, and by receiving and analyzing data of the parameter module, the sensor module and the global planner, the simulation time can be dynamically adjusted to perform motion simulation so as to generate the optimal moving track of the robot at the next moment, thereby realizing multi-terrain self-adaptation of the robot. The local planner includes an adaptive fuzzy method framework and a dynamic window method framework. The self-adaptive fuzzy method frame is used for adjusting simulation time according to actual conditions, and then the simulation time is provided for the dynamic window method frame to carry out motion simulation so as to generate the optimal moving track of the robot at the next moment.
As shown in fig. 2, a robot obstacle avoidance method includes the following steps:
and step S1, the robot plans a global optimal path to the preset target point on the static map. After the robot completes the SLAM mapping, the map is stored in the parameter module. When the robot wants to go from the current location to another target point, the target point needs to be set in the built map. Then the robot uses the global planner to search on the map, and a global optimal path to the target point can be obtained. In this embodiment, the robot searches for a path using the a-algorithm. The a-algorithm is a very common path finding and graph traversing algorithm, and has better performance and accuracy. However, the searched global optimal path only has the characteristic of the shortest path and does not have the function of real-time obstacle avoidance, so that a local planner is required to perform real-time motion simulation, and a path having the characteristics of global optimal path and obstacle avoidance exists in a motion track obtained by simulation. Currently, the dynamic window method is one of the more popular local planning algorithms. However, the dynamic window method has limitations, and it adopts a fixed-scale simulation time in the simulation process, so that the obstacle avoidance of the robot can only adapt to a narrow area or an open area. Therefore, the invention adds the self-adaptive fuzzy method frame in the local planner, and aims to adjust the simulation time by combining the actual situation so that the robot can avoid the obstacles on various terrains.
And step S2, the robot reads data required by motion simulation, then sets simulation time and carries out motion simulation by combining the global optimal path to obtain a plurality of simulation tracks. The data required by the motion simulation comprise current pose information, motion parameters and sampling speed of the robot. The current pose information comprises a current position coordinate of the robot and a current machine head orientation angle, and the current machine head orientation angle is an angle formed by the current right front orientation of the robot and an x axis of a coordinate system. The motion parameters include robot radius, wheel spacing, and default acceleration. The sampling speed is obtained by sampling through a speed sampling window formed by the current speed information of the robot and the default acceleration, and the speed information is provided by a speed sensor. It should be noted that the speed for motion simulation is a sampling speed. The sampling speed is sampled in a speed sampling window. Assuming that the length of the speed sampling window is 20 milliseconds, the speed of the left and right wheels of the robot takes a value between the current linear speed and the speed which can be reached after 20 milliseconds. When the left and right wheels take different speeds, the angular velocities are also different. The speed which can be reached after 20 milliseconds is calculated by the current linear speed and the default acceleration of the robot. The robot takes a plurality of groups of sampling speeds to carry out motion simulation so as to obtain a plurality of groups of simulation tracks.
Before motion simulation, the simulation time needs to be set by using an adaptive fuzzy method. Referring to fig. 3, the robot scans the surrounding environment by using the laser sensor, and then determines whether the number of the obstacle point clouds in the preset range of the current position of the robot is smaller than the preset number, if not, the robot adopts first preset time as simulation time, and if so, the robot adopts second preset time as simulation time, wherein the first preset time is smaller than the second preset time. For example, the robot determines whether the number of obstacle point clouds within 0.4 meter of the left and right sides of the robot is less than 100. If yes, the robot is in a relatively open area, and then a second preset time such as 2.5 seconds is adopted as simulation time. If the number of the robots is more than 100, the robots are positioned in a narrower channel, and a first preset time such as 1.5 seconds is used as the simulation time. In the motion simulation, the selection of simulation time influences the performance of the whole obstacle avoidance function. If the simulation time is too long, collision exists in the simulation track of the obstacle dense area all the time, so that no path where the robot can walk exists, and if the simulation time is too short, the simulation track falls into oscillation or local optimal solution, so that the obstacle avoidance path is not smooth in an open area. One of the benefits of adding an adaptive fuzzy approach is that the appropriate simulation time can be set based on the actual situation. It should be noted that, when performing motion simulation, the entire global optimal path does not need to be input. When the global optimal path is generated, the robot merges some similar adjacent points on the path, so the global optimal path can be considered to be composed of a plurality of key points. In the motion simulation, only the nearest key point in front of the robot needs to be input.
And step S3, the robot detects the simulation track to judge whether the simulation time needs to be adjusted, if not, the robot selects the optimal movement track to move, then returns to S2 to execute until the robot reaches a preset target point, and if so, the robot enters S4. In step S2, the robot performs motion simulation to obtain multiple sets of simulation trajectories, and at this time, all the trajectories are detected once to know whether the simulation time needs to be adjusted, so that the simulation time is more reasonable. If the robot detects that at least one collision-free simulation track exists, the simulation time is reasonably set. The robot inputs the collision-free simulation track, the global optimal path, the obstacle point cloud information and the weight information given by the self-adaptive fuzzy method into a track cost function for weighting calculation, and the simulation track with the lowest cost function value is used as the current optimal moving track. In this embodiment, the following four cost functions are used: goal Cost, Obstacle Cost, Goal header Cost, and Speed Cost. Wherein, the weight of the Obstacle Cost is influenced by the adaptive fuzzy method, and the weights of other Cost functions are constant. And when the key point in front of the robot is the last node of the global path and the current position of the robot is within 0.5 meter of the key point, setting the weight of the Obstacle Cost to be 50. If the situation is not the above and the robot is in a narrow passage, the weight of the Obstacle Cost is set to 500. If not, the weight of the Obstacle Cost is set to 300. And the robot moves according to the optimal movement track, and stops when reaching a target point. It should be noted that a simulation cycle is very short, about 20 ms, so the robot can be considered as a simulation while moving. Namely, the robot reads data required by simulation while moving, sets new simulation time according to the obstacle point cloud information, and then continuously performs motion simulation and moves along an optimal movement track until reaching a target point. If the robot detects that all simulation tracks show collision, the simulation time is possibly too long, and the robot needs to be adjusted to perform simulation and move.
And step S4, the robot adjusts the simulation time, then detects whether the simulation time meets the preset condition, if so, the motion simulation is carried out again, then the operation returns to step S3, and if not, the operation returns to step S2 after the preset action is executed. In this embodiment, a constant, such as 0.5, needs to be set first. Then subtract 0.5 from the simulation time and check if the difference is greater than a minimum value, which is set to 0.5 seconds. And if the adjusted simulation time is more than 0.5 second, the motion simulation is carried out again and the corresponding action is executed by returning to the step S3. Otherwise, the robot firstly walks linearly at the default speed until collision occurs, and when the collision sensor detects the collision, the robot is controlled to steer. And the robot turns left or right, and if the robot detects that no obstacle exists in the front, the robot stops and returns to the step S2 to execute corresponding actions.
In summary, the system and the method for avoiding the obstacle by the robot provided by the invention improve the classic dynamic window method, and the robot can realize self-adaptive obstacle avoidance under different obstacle distributions by dynamically adjusting the simulation time through the self-adaptive fuzzy method.
Those skilled in the art will appreciate that all or part of the steps in the method according to the above embodiments may be implemented by a program, which is stored in a storage medium and includes instructions for causing a single chip, a chip, or a processor (processor) to execute all or part of the steps in the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents, which are to be considered as merely preferred embodiments of the invention, and not intended to be limiting of the invention, and that various changes and modifications may be effected therein by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (11)
1. A robot obstacle avoidance method is characterized by comprising the following steps:
s1, the robot plans a global optimal path going to a preset target point on the static map;
s2, the robot reads data needed by motion simulation, then sets simulation time and carries out motion simulation by combining the global optimal path to obtain a plurality of simulation tracks;
s3, the robot detects the simulation track to judge whether the simulation time needs to be adjusted, if not, the robot selects the optimal movement track to move, then returns to S2 to execute until the robot reaches a preset target point, and if so, the robot enters S4;
and S4, adjusting the simulation time by the robot, detecting whether the simulation time meets the preset condition, if so, performing motion simulation again, returning to S3, otherwise, executing the preset action, and returning to S2.
2. The obstacle avoidance method for a robot according to claim 1, wherein in step S2, the data required for motion simulation includes current pose information, motion parameters and sampling speed, wherein,
the current pose information comprises the current position coordinates and the current head orientation angle of the robot,
the motion parameters include robot radius, wheel spacing and default acceleration,
the sampling speed is obtained by sampling through a speed sampling window formed by the current speed information of the robot and the default acceleration, and the speed information is provided by a speed sensor.
3. A robot obstacle avoidance method according to claim 1, wherein the method of setting the simulation time in step S2 is that the robot determines whether the number of the obstacle point clouds in the preset range of its current position is smaller than a preset number, if not, the first preset time is used as the simulation time, if yes, the second preset time is used as the simulation time, and the first preset time is smaller than the second preset time.
4. The robot obstacle avoidance method according to claim 1, wherein the method of determining whether the simulation time needs to be adjusted in step S3 is that the simulation time needs to be adjusted if the robot detects that all simulation tracks show collision, and the simulation time does not need to be adjusted if the robot detects that at least one collision-free simulation track exists.
5. The robot obstacle avoidance method according to claim 1, wherein the method for obtaining the optimal movement trajectory in step S3 is that the robot inputs the simulated trajectory, the global optimal path, the obstacle point cloud information, and the weight information into a trajectory cost function to perform weighting calculation, wherein the simulated trajectory with the lowest cost function value is the optimal movement trajectory.
6. A robot obstacle avoidance method according to claim 1, wherein the method of adjusting the simulation time in step S4 is to set a constant first, and then decrease the simulation time until at least one collision-free simulation trajectory is detected after the motion simulation or the simulation time is shortened to a preset value.
7. A robot obstacle avoidance method according to claim 1, wherein the method of detecting whether the simulation time satisfies the preset condition in step S4 is to set a preset minimum value, then compare the simulation time with the preset minimum value, if the simulation time is greater than the preset minimum value, the simulation time satisfies the preset condition, otherwise, the simulation time does not satisfy the preset condition.
8. A robot obstacle avoidance method according to claim 1, wherein the robot performs the predetermined action in step S4 as the robot travels straight at a default speed until the collision sensor detects a collision, then turns around, and stops when no obstacle is detected in front.
9. A robot obstacle avoidance system, characterized in that the system performs the robot obstacle avoidance method of any one of claims 1 to 8, the system comprising a parameter module, a sensor module, a global planner and a local planner,
the parameter module is connected with the global planner and the local planner and used for providing preset parameters including a static map, a robot radius, a wheel spacing and default acceleration;
a sensor module connected to the local planner for providing sensor data;
the global planner is connected with the parameter module and the local planner and is used for generating a global optimal path;
and the local planner dynamically adjusts simulation time to perform motion simulation to generate an optimal moving track at the next moment by receiving and analyzing data of the parameter module, the sensor module and the global planner, so that multi-terrain self-adaptation of the robot is realized.
10. A robotic obstacle avoidance system according to claim 9, wherein the sensor module comprises a speed sensor, a laser sensor and a collision sensor.
11. The robot obstacle avoidance system of claim 9, wherein the local planner includes an adaptive fuzzy method framework and a dynamic window method framework, wherein,
the self-adaptive fuzzy method frame dynamically adjusts the simulation time by using the data of the sensor module;
the dynamic window method framework generates the optimal movement track of the next moment by using the data of the parameter module, the sensor module, the global planner and the self-adaptive fuzzy method framework.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110312055.6A CN113050648A (en) | 2021-03-24 | 2021-03-24 | Robot obstacle avoidance method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110312055.6A CN113050648A (en) | 2021-03-24 | 2021-03-24 | Robot obstacle avoidance method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113050648A true CN113050648A (en) | 2021-06-29 |
Family
ID=76514720
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110312055.6A Pending CN113050648A (en) | 2021-03-24 | 2021-03-24 | Robot obstacle avoidance method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113050648A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114371724A (en) * | 2021-12-03 | 2022-04-19 | 中国人民解放军海军航空大学 | Obstacle avoidance method and system for aircraft |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090093960A1 (en) * | 2007-10-04 | 2009-04-09 | Jeffrey Scott Puhalla | Method and system for obstacle avoidance for a vehicle |
| CN107703948A (en) * | 2017-11-14 | 2018-02-16 | 上海理工大学 | Mobile robot local dynamic station paths planning method based on adaptive dynamic window |
| CN109814557A (en) * | 2019-01-23 | 2019-05-28 | 西北工业大学 | A kind of robot path planning method that Global motion planning device is leading |
| CN110018689A (en) * | 2019-05-15 | 2019-07-16 | 福州大学 | A kind of more virtual target point overall situation active path planning algorithms based on dynamic window |
| CN110221613A (en) * | 2019-06-12 | 2019-09-10 | 北京洛必德科技有限公司 | Robot path planning method and device based on modified Artificial Potential Field Method |
| CN110465928A (en) * | 2019-08-23 | 2019-11-19 | 河北工业大学 | A kind of paths planning method of storage commodity pick-and-place mobile platform and the mobile platform |
| CN111123947A (en) * | 2019-12-31 | 2020-05-08 | 深圳前海达闼云端智能科技有限公司 | Robot traveling control method and device, electronic device, medium, and robot |
| CN111142530A (en) * | 2019-12-31 | 2020-05-12 | 深圳前海达闼云端智能科技有限公司 | Method for determining running track of robot, robot and storage medium |
| CN112325884A (en) * | 2020-10-29 | 2021-02-05 | 广西科技大学 | ROS robot local path planning method based on DWA |
| CN112462786A (en) * | 2020-12-03 | 2021-03-09 | 大连海事大学 | Unmanned ship collision avoidance method based on fuzzy control strategy double-window algorithm |
-
2021
- 2021-03-24 CN CN202110312055.6A patent/CN113050648A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090093960A1 (en) * | 2007-10-04 | 2009-04-09 | Jeffrey Scott Puhalla | Method and system for obstacle avoidance for a vehicle |
| CN107703948A (en) * | 2017-11-14 | 2018-02-16 | 上海理工大学 | Mobile robot local dynamic station paths planning method based on adaptive dynamic window |
| CN109814557A (en) * | 2019-01-23 | 2019-05-28 | 西北工业大学 | A kind of robot path planning method that Global motion planning device is leading |
| CN110018689A (en) * | 2019-05-15 | 2019-07-16 | 福州大学 | A kind of more virtual target point overall situation active path planning algorithms based on dynamic window |
| CN110221613A (en) * | 2019-06-12 | 2019-09-10 | 北京洛必德科技有限公司 | Robot path planning method and device based on modified Artificial Potential Field Method |
| CN110465928A (en) * | 2019-08-23 | 2019-11-19 | 河北工业大学 | A kind of paths planning method of storage commodity pick-and-place mobile platform and the mobile platform |
| CN111123947A (en) * | 2019-12-31 | 2020-05-08 | 深圳前海达闼云端智能科技有限公司 | Robot traveling control method and device, electronic device, medium, and robot |
| CN111142530A (en) * | 2019-12-31 | 2020-05-12 | 深圳前海达闼云端智能科技有限公司 | Method for determining running track of robot, robot and storage medium |
| CN112325884A (en) * | 2020-10-29 | 2021-02-05 | 广西科技大学 | ROS robot local path planning method based on DWA |
| CN112462786A (en) * | 2020-12-03 | 2021-03-09 | 大连海事大学 | Unmanned ship collision avoidance method based on fuzzy control strategy double-window algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 王永雄 等: "穿越稠密障碍物的自适应动态窗口法", 《控制与决策》, vol. 34, no. 5, pages 927 - 936 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114371724A (en) * | 2021-12-03 | 2022-04-19 | 中国人民解放军海军航空大学 | Obstacle avoidance method and system for aircraft |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112099493B (en) | Autonomous mobile robot trajectory planning method, system and equipment | |
| Mujahad et al. | Closest Gap based (CG) reactive obstacle avoidance navigation for highly cluttered environments | |
| CN109597425B (en) | Unmanned aerial vehicle navigation and obstacle avoidance method based on reinforcement learning | |
| Seder et al. | An integrated approach to real-time mobile robot control in partially known indoor environments | |
| CN111142530B (en) | Method for determining running track of robot, robot and storage medium | |
| CN113341984A (en) | Robot path planning method and device based on improved RRT algorithm | |
| CN115079705A (en) | Routing planning method for inspection robot based on improved A star fusion DWA optimization algorithm | |
| Li et al. | Obstacle avoidance for mobile robot based on improved dynamic window approach | |
| KR20150104484A (en) | Method and apparatus for generating pathe of autonomous vehicle | |
| CN112506199B (en) | Local path planning method based on dynamic window method and suitable for Ackerman model robot | |
| Hong et al. | A modified dynamic window approach to obstacle avoidance combined with fuzzy logic | |
| CN113050648A (en) | Robot obstacle avoidance method and system | |
| CN110954124A (en) | Adaptive path planning method and system based on A-PSO algorithm | |
| CN113219990B (en) | Robot path planning method based on adaptive neighborhood and steering cost | |
| US8924013B2 (en) | Method and system for path planning and controlling | |
| CN111045428B (en) | Obstacle avoidance method, mobile robot, and computer-readable storage medium | |
| Kala et al. | Robot path planning using dynamic programming with accelerating nodes | |
| Si et al. | Improvement of dynamic window approach in dynamic obstacle environment | |
| CN115586774A (en) | Mobile robot obstacle avoidance method based on improved dynamic window method | |
| CN116009530A (en) | Path planning method and system for self-adaptive tangential obstacle avoidance | |
| CN114047759A (en) | Local path planning method based on DWA and artificial potential field fusion | |
| Dong et al. | Path Planning Research for Outdoor Mobile Robot | |
| Li et al. | Navigation Simulation of Autonomous Mobile Robot Based on TEB Path Planner | |
| CN115826590B (en) | Mobile robot local path planning method and system with self-adaptive parameters | |
| Yu et al. | An intelligent robot motion planning method and application via lppo in unknown environment |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 519000 2706, No. 3000, Huandao East Road, Hengqin new area, Zhuhai, Guangdong Applicant after: Zhuhai Yiwei Semiconductor Co.,Ltd. Address before: Room 105-514, No.6 Baohua Road, Hengqin New District, Zhuhai City, Guangdong Province Applicant before: AMICRO SEMICONDUCTOR Co.,Ltd. |