CN114675649A - Indoor mobile robot path planning method fusing improved A and DWA algorithm - Google Patents
Indoor mobile robot path planning method fusing improved A and DWA algorithm Download PDFInfo
- Publication number
- CN114675649A CN114675649A CN202210312905.7A CN202210312905A CN114675649A CN 114675649 A CN114675649 A CN 114675649A CN 202210312905 A CN202210312905 A CN 202210312905A CN 114675649 A CN114675649 A CN 114675649A
- Authority
- CN
- China
- Prior art keywords
- path
- algorithm
- mobile robot
- dwa
- nodes
- 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
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- 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
- G05D1/0276—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 an indoor mobile robot path planning method fusing improved A and DWA algorithms, which comprises the following steps: s1, optimizing a cost function of the traditional A-x algorithm, introducing the environmental information barrier rate Q into the cost function, changing the weight of the heuristic function H (n), and realizing the self-adaptive adjustment; s2, optimizing the path smoothness, solving the problem of redundant collinear nodes and turning points by using a key point selection strategy, and reserving necessary path nodes to obtain a global path only with key points; s3, constructing an evaluation function combined with the key point information, and then applying DWA algorithm to enable the local path planning to follow the global path contour, thereby enabling the path to be smoother and realizing real-time obstacle avoidance. The invention can quickly find the optimal path, and can timely avoid the dynamic and static barriers appearing in the environment on the basis of global optimization, thereby improving the adaptability of the indoor mobile robot in the complex environment.
Description
Technical Field
The invention relates to the field of mobile robot navigation and path planning, in particular to an indoor mobile robot path planning method fusing improved A and DWA algorithms.
Background
Currently, path planning is one of the leading subjects in the research field of current mobile robots, and aims to avoid obstacles and find an optimal path from a starting point to an end point in a complex environment. The path planning technology is also a core technology for realizing the autonomous navigation function of the mobile robot. In order to solve the problem of path planning, a large number of scholars at home and abroad study the problem and put forward various algorithms.
The path planning can be divided into two categories, namely global path planning and local path planning, wherein the global path algorithm comprises an A-star algorithm, a Dijkstra algorithm, an RRT algorithm and the like; the local path algorithm comprises a DWA algorithm, a particle swarm algorithm, an artificial potential field method, an ant colony algorithm and the like.
The Dijkstra algorithm adopts a traversal search mode, the number of planning nodes is large, the node network is huge, and the algorithm efficiency is low. On the basis of the Dijkstra algorithm, the A-x algorithm introduces the estimation cost from the target point to the current point, and the path searching direction is determined according to the estimation cost, so that the algorithm efficiency is improved. The A-algorithm can rapidly realize the collision-free and shortest global path planning of the mobile robot in the known environment, and an optimal safe road is planned mainly through node state detection and a simple estimation function. However, the path planned by the a-algorithm is connected through nodes, so that the curvature is discontinuous, and the disadvantage of long path exists. The Zhao Xiao et al provides an improved A-algorithm based on the jumping point search algorithm, which improves the search speed of the path and reduces the calculation amount. Zhang et al proposed an improved a-algorithm to traverse all nodes of the path and then delete unnecessary nodes, reducing the travel path and turn time of the robot. However, these improved a algorithms only consider the optimization of the global path, and the robot cannot avoid unknown obstacles.
For the local path planning algorithm, the DWA algorithm has good local obstacle avoidance capability. Wangyongxiong and the like propose a DWA algorithm with adaptive parameters, obtain the optimal speed of robot motion and improve the safety. Mai et al propose an improved DWA algorithm that can perceive the dense object distribution situation in advance, which can make the robot avoid the dense area stably. However, the improved DWA algorithm cannot achieve global path optimization while realizing obstacle avoidance of the robot.
The improved algorithms only consider global path optimization or local obstacle avoidance in the navigation process of the mobile robot. Therefore, how to enable the robot to find the optimal path in the navigation process and avoid the obstacle in real time is always a problem to be solved by the technical field.
Disclosure of Invention
The invention aims to solve the problems and provides an indoor mobile robot path planning method fusing improved A and DWA algorithms in order to realize that a mobile robot can drive along a global optimal path and avoid obstacles in real time. The algorithm introduces environmental information into the heuristic function of the traditional A-x algorithm, so that the search efficiency is improved; redundant nodes in the track are deleted, turns are reduced, and optimization of path smoothness is achieved; and extracting key points of the improved A-algorithm planning path as intermediate target points of the DWA algorithm to perform global guidance, and realizing the fusion of the improved A-algorithm and the DWA algorithm.
The technical scheme adopted by the invention is as follows: an indoor mobile robot path planning method fusing improved A and DWA algorithms specifically comprises the following steps:
s1: optimizing a cost function of a traditional A-x algorithm, introducing an environment information barrier rate Q into the cost function, changing the weight of a heuristic function H (n), and realizing the self-adaptive adjustment of the heuristic function;
s2: optimizing the path smoothness, solving the problems of redundant collinear nodes and turning points by utilizing a key point selection strategy, reserving necessary path nodes and obtaining a global path only with key points;
s3: and constructing an evaluation function combined with the key point information, and then applying a DWA algorithm to enable the local path planning to follow the global path contour, so that the path is smoother, and real-time obstacle avoidance is realized.
Preferably, the step S1 optimizes the cost function of the conventional a-algorithm, specifically including introducing an environmental obstacle rate Q that varies with a change in the current position of the mobile robot into the cost function f (n). Assuming that the number of rectangular grids formed by the starting point and the target point of the robot is M, the number of grid obstacles in the search range from the current node to the target point is N, and the expression of the environmental obstacle ratio is as follows:
and introducing the environment obstacle rate Q into a cost function F (n), and adaptively changing the weight of the heuristic function H (n). The cost function f (n) at this time is: f (n) ═ g (n) + eQH (n), thereby achieving optimization of the conventional a algorithm.
Preferably, in the step S2, path smoothing optimization, the conventional a-algorithm path planning is composed of continuous grid center points connected together, there are many redundant nodes, the number of times of path turning is many, and the path is not smooth. Aiming at the problems, a path smoothing optimization algorithm is designed based on the Floyd algorithm idea. The method specifically comprises the following steps: the first step is as follows: and traversing all the nodes, deleting redundant nodes in the middle of each section of path, and keeping the starting point and the inflection point. The second step is that: traversing the starting point and the inflection point, connecting each node with the following nodes from the starting point as alternative paths, and judging the distance d between each path and the barrier gridiRelation to the safety distance D. If d isiIf D is less than or equal to D, deleting path, if D is less than or equal to Di> D, preserving paths, and deleting inflection points between paths. The third step: and extracting the residual nodes, outputting an optimized path and finishing the algorithm.
Preferably, the step S3 is a fusion of the modified a-star algorithm and the DWA algorithm, and the steps S1 and S2 realize the modification of the a-star algorithm, so that a navigation path including only a start point, a key point and a target point is obtained, but unknown obstacles appearing in the environment cannot be avoided. The DWA algorithm has good local obstacle avoidance capability, but only one final target point is used as a guide, so that the DWA algorithm is easy to fall into local optimum. Therefore, the two algorithms are fused, the extracted global path key points planned by the improved A-algorithm are used as the middle target points of the DWA algorithm, and the optimized evaluation function enables the local path planning to follow the planned global path contour. By fusing navigation algorithms, the global path optimization in the navigation process of the mobile robot is realized, and the mobile robot has a real-time obstacle avoidance function.
The invention has the beneficial effects that:
1. optimizing a cost function of a traditional A-star algorithm, realizing self-adaptive adjustment of the cost function, and improving the efficiency of the algorithm;
2. the problem of redundant collinear nodes and turning points is solved, necessary path nodes are reserved, a global path only with key points is obtained, and the smooth optimization of the path is realized;
3. and fusing with a DWA algorithm, constructing an evaluation function combined with the key point information, and applying the DWA algorithm to enable the local path planning to follow the global path contour, thereby enabling the path to be smoother and realizing real-time obstacle avoidance.
Drawings
Fig. 1 is a schematic diagram of a-algorithm search in mobile robot path planning;
FIG. 2 is a schematic diagram of the searching step when the current point selects the next point during path planning of the mobile robot;
FIG. 3 is a flowchart of a method for planning a path of an indoor mobile robot according to an embodiment of the present invention;
FIG. 4a is a schematic diagram of a path before smooth optimization according to an embodiment of the present invention;
FIG. 4b is a diagram illustrating a path smoothing optimization according to an embodiment of the present invention;
FIG. 5 is a flowchart of a fusion algorithm according to an embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and detailed description.
In order to fully understand the technical scheme of the present invention, the following briefly introduced algorithm a:
the traditional A-algorithm searching principle is to add a starting point into an open list, use the point as a parent node plus a close list, and search its adjacent reachable nodes plus the open list. And calculating the cost of the nodes in the open list according to the cost function, selecting the node with the lowest cost as the next father node, putting the father node into the close list, searching the reachable nodes of the father node again, calculating the cost of the reachable nodes, and sequentially circulating until the father node is the position of the target point.
The cost function of the conventional a-algorithm is: f (n) ═ g (n) + h (n). In the formula, n represents a current node, and f (n) represents a cost function of the mobile robot at the current node, which is used for selecting an optimal path. G (n) represents the actual cost value of the mobile robot from the starting point to the current point. H (n) is a heuristic function representing the estimated cost value from the current point n to the target point. Generally, h (n) is smaller than the actual cost value from the current point n to the target point, and when h (n) is 0, only g (n) is in effect, and the algorithm is Dijkstra algorithm. When the estimated value of h (n) is smaller than the actual cost value, the algorithm search time increases due to the increase of the search space. H (n) when the estimated value is larger than the actual cost value, the algorithm search speed increases, but the algorithm may not be able to search the shortest path.
It is readily apparent that h (n) has a large impact on search efficiency, and h (n) has several common manifestations: (1) a Manhattan distance; (2) a Chebyshev distance; (3) the euclidean distance. One embodiment of the present invention uses manhattan distance.
As shown in fig. 1, a search area is shown in which black lattices are obstacle nodes and white lattices are walkable nodes. Fig. 2 shows the searching steps when the current point selects the next point, assuming that the cost of straight line is 10 and the cost of oblique line is 14, as shown in fig. 2, the cost function of the lower right corner is the minimum, so the next node is the node of the lower right corner, and so on, if an obstacle is touched, the obstacle is not considered to be within the range. And stopping until the final destination point is reached, and obtaining the shortest path, wherein the path connected by the broken line represents the found shortest path, as shown in fig. 1.
The invention discloses an indoor mobile robot path planning method fusing an improved A and DWA algorithm, which is characterized by improving the A algorithm and fusing the A and DWA algorithm. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
As shown in fig. 3, a schematic flow chart of the method for planning the path of the indoor mobile robot in this embodiment specifically includes: s1, optimizing a cost function of the traditional A-x algorithm, introducing the environmental information barrier rate Q into the cost function, changing the weight of the heuristic function H (n), and realizing the self-adaptive adjustment; s2, optimizing the path smoothness, using a key point selection strategy to solve the problem of redundant collinear nodes and turning points, and reserving necessary path nodes to obtain a global path only having key points; and S3, constructing an evaluation function combined with the key point information, and then applying a DWA algorithm to enable the local path planning to follow the global path contour, thereby enabling the path to be smoother and realizing real-time obstacle avoidance.
And S1, optimizing a cost function of the traditional A-x algorithm, introducing the environment information barrier rate Q into the cost function, changing the weight of the heuristic function H (n), and realizing the self-adaptive adjustment.
When the current node is far away from the target point, the estimated cost value is far smaller than the actual value, the search space is large, the number of search nodes is large, the weight of H (n) is increased properly, and the search efficiency is improved; when the current node gradually approaches the target point, the estimated cost value is increased, the estimated cost value is close to the actual value, and in order to prevent the estimated value from being larger and falling into the local optimum, the weight of H (n) is properly reduced. Therefore, in order to adaptively adjust the weight of the heuristic function, an environmental obstacle rate Q that varies as the current position of the mobile robot changes is introduced.
By introducing the environmental obstacle rate Q, the cost function of the conventional a-algorithm is optimized. The environmental obstacle expression is:
wherein M is the number of rectangular area grids formed by the starting point and the target point, and N is the number of grid obstacles in the searching range from the current point to the target point.
The cost function f (n) is optimized to f (n) ═ g (n) + eQH (n). As the robot moves from the start point to the target point, the environmental obstacle rate Q gradually decreases, so that the weight of h (n) gradually decreases. The condition that the weight is larger when the current node is far away from the target point is met; when the current node is close to the target point, the weight is smaller. By realizing the self-adaptive adjustment of H (n), the searching efficiency of the robot at different positions is improved.
S2, optimizing the path smoothness, using a key point selection strategy to solve the problem of redundant collinear nodes and turning points, and reserving necessary path nodes to obtain a global path with only key points.
The traditional A-algorithm path planning is formed by connecting continuous grid central points, a plurality of redundant nodes exist, the path turning times are multiple, and the path is not smooth. Aiming at the problems, a path smoothing optimization algorithm is designed based on the Floyd algorithm idea.
The principle of path smoothing optimization is shown in fig. 4a and 4b, for example, the path plan of the conventional a-x algorithm planning is composed of the connection lines of the center points of the grids, the path before optimization is (S, 1, 2, …, 13, E), and there are many redundant nodes. And on the basis of considering the safety distance D, smoothly optimizing the path, so that the selection of the path is not limited to the center position of the pass grid any more. The smoothness of the optimized path is increased, the length and the turning point of the path are reduced, and the path smoothing optimization steps are as follows:
step 1: and traversing all the nodes, deleting redundant nodes in the middle of each section of path, and keeping the starting point and the inflection point. Nine nodes of S, 2, 6, 8, 9, 10, 11, 13 and E are left after the intermediate points are deleted.
Step 2: traversing the starting point and the inflection point, connecting each node with the following nodes from the starting point as alternative paths, and judging the distance d between each path and the barrier gridiRelation to the safety distance D. If d isiIf D is less than or equal to D, deleting path, if D is less than or equal to Di> D, preserving paths, and deleting inflection points between paths. Four nodes of S, 6, 8 and E are left after unnecessary inflection points are deleted.
And 3, step 3: and extracting the residual nodes, outputting the optimized path and finishing the algorithm.
S3, constructing an evaluation function combined with the key point information, and then applying DWA algorithm to enable the local path planning to follow the global path contour, thereby enabling the path to be smoother and realizing real-time obstacle avoidance.
The improved A-algorithm obtains a navigation path only containing a starting point, a key point and a target point, but can not avoid unknown obstacles in the environment. The DWA algorithm has good local obstacle avoidance capability, but only one final target point is used as a guide, so that the DWA algorithm is easy to fall into local optimum. Therefore, the two algorithms are fused, the extracted global path key points planned by the improved A-algorithm are used as the middle target points of the DWA algorithm, and the optimized evaluation function enables the local path planning to follow the planned global path contour. By fusing navigation algorithms, the global path optimization in the navigation process of the mobile robot is realized, and the mobile robot has a real-time obstacle avoidance function.
The specific flow of the fusion algorithm is shown in fig. 5. Firstly, an improved A-algorithm is adopted to plan a global path, the path is optimized by utilizing an optimized evaluation function and a key point selection strategy, and necessary key nodes of the path are obtained. And then, taking the extracted path key points as intermediate target points of the DWA algorithm, and guiding the planning of the local path. The DWA algorithm samples the speed of the mobile robot, simulates the moving track of each speed pair, selects the optimal simulated moving track by utilizing an evaluation function combined with key point information, and controls the movement of the robot to a target point at the speed corresponding to the optimal track, thereby realizing the fusion of the improved A-x algorithm and the DWA algorithm.
The embodiments described above are presented to enable a person having ordinary skill in the art to make and use the invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (4)
1. An indoor mobile robot path planning method fusing improved A and DWA algorithms is characterized in that: the method specifically comprises the following steps:
s1: optimizing a cost function of a traditional A-x algorithm, introducing an environment information barrier rate Q into the cost function, changing the weight of a heuristic function H (n), and realizing the self-adaptive adjustment of the heuristic function;
s2: optimizing the path smoothness, solving the problems of redundant collinear nodes and turning points by utilizing a key point selection strategy, reserving necessary path nodes and obtaining a global path only with key points;
s3: and constructing an evaluation function combined with the key point information, and then applying a DWA algorithm to enable the local path planning to follow the global path contour, so that the path is smoother, and real-time obstacle avoidance is realized.
2. The method of indoor mobile robot path planning incorporating the improved a and DWA algorithm of claim 1, wherein: the step S1 optimizes a cost function of the conventional a-star algorithm, specifically including introducing an environmental obstacle rate Q that changes with a change in the current position of the mobile robot into the cost function f (n);
assuming that the number of rectangular grids formed by the starting point and the target point of the robot is M, the number of grid obstacles in the search range from the current node to the target point is N, and the expression of the environmental obstacle ratio is as follows:
introducing the environment barrier rate Q into a cost function F (n), and adaptively changing the weight of a heuristic function H (n); the cost function f (n) at this time is: f (n) ═ g (n) + eQH (n), thereby achieving optimization of the conventional a algorithm.
3. The method of indoor mobile robot path planning incorporating the improved a and DWA algorithm of claim 1, wherein: the step S2 optimizing the path smoothing includes the following steps:
the first step is as follows: traversing all nodes, deleting redundant nodes in the middle of each section of path, and keeping a starting point and an inflection point;
the second step: traversing the starting point and the inflection point, connecting each node with the following node from the starting point as an alternative path, and judging the distance d between each path and the barrier gridiA relationship to a safe distance D; if d isiIf D is less than or equal to D, deleting path, if D is less than or equal to DiIf the path is larger than D, reserving the path and deleting inflection points between the paths;
the third step: and extracting the residual nodes, outputting an optimized path and finishing the algorithm.
4. The method of indoor mobile robot path planning incorporating the improved a and DWA algorithm of claim 1, wherein: the improved a-algorithm and the DWA algorithm in the step S3 are fused, the extracted global path key points planned by the improved a-algorithm are used as intermediate target points of the DWA algorithm, and the optimized evaluation function enables the local path plan to follow the planned global path contour; by fusing navigation algorithms, the global path optimization in the navigation process of the mobile robot is realized, and the mobile robot has a real-time obstacle avoidance function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210312905.7A CN114675649A (en) | 2022-03-28 | 2022-03-28 | Indoor mobile robot path planning method fusing improved A and DWA algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210312905.7A CN114675649A (en) | 2022-03-28 | 2022-03-28 | Indoor mobile robot path planning method fusing improved A and DWA algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114675649A true CN114675649A (en) | 2022-06-28 |
Family
ID=82076099
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210312905.7A Pending CN114675649A (en) | 2022-03-28 | 2022-03-28 | Indoor mobile robot path planning method fusing improved A and DWA algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114675649A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115164914A (en) * | 2022-07-11 | 2022-10-11 | 北京中航世科电子技术有限公司 | Navigation method, system, electronic equipment and medium for individual combat |
| CN115344049A (en) * | 2022-09-14 | 2022-11-15 | 江苏天一航空工业股份有限公司 | Automatic path planning and vehicle control method and device for passenger boarding vehicle |
| CN116560382A (en) * | 2023-07-11 | 2023-08-08 | 安徽大学 | Mobile robot path planning method based on hybrid intelligent algorithm |
| CN116610129A (en) * | 2023-07-17 | 2023-08-18 | 山东优宝特智能机器人有限公司 | Local path planning method and system for leg-foot robot |
-
2022
- 2022-03-28 CN CN202210312905.7A patent/CN114675649A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115164914A (en) * | 2022-07-11 | 2022-10-11 | 北京中航世科电子技术有限公司 | Navigation method, system, electronic equipment and medium for individual combat |
| CN115164914B (en) * | 2022-07-11 | 2023-10-03 | 北京中航世科电子技术有限公司 | Navigation method, system, electronic equipment and medium for individual combat |
| CN115344049A (en) * | 2022-09-14 | 2022-11-15 | 江苏天一航空工业股份有限公司 | Automatic path planning and vehicle control method and device for passenger boarding vehicle |
| CN115344049B (en) * | 2022-09-14 | 2023-08-29 | 江苏天一航空工业股份有限公司 | Automatic path planning and vehicle control method and device for passenger boarding vehicle |
| CN116560382A (en) * | 2023-07-11 | 2023-08-08 | 安徽大学 | Mobile robot path planning method based on hybrid intelligent algorithm |
| CN116610129A (en) * | 2023-07-17 | 2023-08-18 | 山东优宝特智能机器人有限公司 | Local path planning method and system for leg-foot robot |
| CN116610129B (en) * | 2023-07-17 | 2023-09-29 | 山东优宝特智能机器人有限公司 | Local path planning method and system for leg-foot robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114675649A (en) | Indoor mobile robot path planning method fusing improved A and DWA algorithm | |
| CN110487279B (en) | Path planning method based on improved A-Algorithm | |
| CN111780777A (en) | Unmanned vehicle route planning method based on improved A-star algorithm and deep reinforcement learning | |
| CN115079705A (en) | Routing planning method for inspection robot based on improved A star fusion DWA optimization algorithm | |
| CN112013846B (en) | Path planning method combining dynamic step RRT algorithm and potential field method | |
| CN111174798A (en) | Foot type robot path planning method | |
| CN112327856B (en) | Robot path planning method based on improved A-star algorithm | |
| CN106595663A (en) | Aircraft auto-route planning method with combination of searching and optimization | |
| CN107357295B (en) | Path searching method and chip based on grid map and robot | |
| CN113485369A (en) | Indoor mobile robot path planning and path optimization method for improving A-x algorithm | |
| US11747826B2 (en) | Method for route optimization based on dynamic window and redundant node filtering | |
| CN110320919B (en) | Method for optimizing path of mobile robot in unknown geographic environment | |
| CN114510057A (en) | ROS-based mobile robot autonomous navigation method in indoor environment | |
| CN116360457A (en) | Path planning method based on self-adaptive grid and improved A-DWA fusion algorithm | |
| CN115167398A (en) | Unmanned ship path planning method based on improved A star algorithm | |
| Li et al. | Application of improved ant colony optimization in mobile robot trajectory planning | |
| CN113703450B (en) | Mobile robot path planning method based on smoothing factor improved ant colony algorithm | |
| CN114779772A (en) | Path planning method and device fusing global and local algorithms | |
| CN114442618A (en) | ACO-PSO-VFH-based autonomous dynamic path planning method for indoor mobile robot | |
| CN117249842A (en) | Unmanned vehicle mixed track planning method based on track smooth optimization | |
| Li et al. | Path Planning of Robots Based on an Improved A-star Algorithm | |
| CN115826586B (en) | Path planning method and system integrating global algorithm and local algorithm | |
| Liu et al. | Energy efficient path planning for indoor wheeled mobile robots | |
| CN114610076B (en) | Flight path planning method combining artificial potential field method and A-star algorithm angle constraint | |
| CN114077255B (en) | Intelligent vehicle road-finding method based on elliptical model 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 |