CN112025715A - Mobile robot double-layer path planning method with unknown local environment - Google Patents
Mobile robot double-layer path planning method with unknown local environment Download PDFInfo
- Publication number
- CN112025715A CN112025715A CN202010993923.7A CN202010993923A CN112025715A CN 112025715 A CN112025715 A CN 112025715A CN 202010993923 A CN202010993923 A CN 202010993923A CN 112025715 A CN112025715 A CN 112025715A
- Authority
- CN
- China
- Prior art keywords
- planning
- path
- unknown
- sub
- mobile robot
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
- B25J9/1666—Avoiding collision or forbidden zones
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a mobile robot double-layer path planning method with unknown local environment, which comprises the following steps: (1) acquiring global environment information of an area to be planned; (2) dividing a region to be planned into a plurality of sub-regions, and carrying out global path planning to obtain paths in each sub-region; (3) walking according to the path planned by the global path, and updating the external local environment information in a visual window of the mobile robot in real time; (4) when an unknown obstacle is encountered, a rolling planning walking method is adopted to complete the local path planning and walking of the sub-area where the unknown obstacle is located; (5) planning a path from the sub-region where the unknown barrier is located to the starting point of the next sub-region by adopting a point-to-point path planning method, and reaching the starting point of the next sub-region according to the path; (6) and (4) returning to execute the step (3) until all the sub-area paths are finished and reach the end point, and obtaining all the paths of the area to be planned. The method can effectively cope with the occurrence of unknown obstacles in the environment, and has effectiveness.
Description
Technical Field
The invention relates to a path planning method, in particular to a double-layer path planning method for a mobile robot with unknown local environment.
Background
The mining area abandoned land refers to an open-pit mining field, a subsidence area and land which is polluted by heavy metal and loses economic utilization value after mining of a mine. A large amount of coal gangue mountains, waste plant areas, trampled subsidence areas, water accumulation areas and the like exist in the abandoned site of the mining area, and the characteristics form the complexity of the environment of the abandoned site of the mining area. The prior environment information of the abandoned mine area is obtained by a remote sensing satellite system, the whole environment is a globally known environment, but a part of an unsensed area may exist in the environment, so when an unknown obstacle suddenly appears in the environment, how to avoid the obstacle and ensure that the area realizes regular full-coverage traversal needs to be considered.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the problems in the prior art, the invention provides a double-layer path planning method for a mobile robot, which can effectively avoid obstacles and is suitable for complex environments with unknown local environments, such as abandoned mine areas and the like.
The technical scheme is as follows: the invention relates to a double-layer path planning method of a mobile robot with unknown local environment, which comprises the following steps:
(1) acquiring global environment information of an area to be planned;
(2) dividing a region to be planned into a plurality of sub-regions, and performing global path planning by adopting a biological excitation neural network algorithm according to global environment information to obtain paths in each sub-region;
(3) walking according to the path planned by the global path, detecting external local environment information in real time by adopting a sensor in the walking process, and updating in real time in a visual window of the mobile robot;
(4) when the unknown barrier is encountered, the local path planning and walking of the subregion where the unknown barrier is located are completed by adopting a rolling planning walking method;
(5) planning a path from the sub-region where the unknown barrier is located to the starting point of the next sub-region by adopting a point-to-point path planning method, and reaching the starting point of the next sub-region according to the path;
(6) and (4) returning to execute the step (3) until all the sub-area paths are finished and reach the end point, and obtaining all the paths of the area to be planned.
Further, the rolling planning walking method in step (4) specifically includes:
(4.1) judging whether a target point of a subregion where the unknown obstacle is located is reached according to the current visual window; if yes, executing the step (5), otherwise, executing the step (4.2)
(4.2) updating the planning window to be a current visual window in a rolling manner, and determining the optimal sub-target point of the current rolling planning period by using a priority heuristic method according to the external local environment information in the planning window;
(4.3) planning a path to the optimal child target point by adopting a biological excitation neural network algorithm, and walking to the optimal child target point according to the planned path, wherein the visual window is updated in real time in the walking process;
and (4.4) returning to execute the step (4.2).
Further, the priority heuristic method specifically includes:
(4.2.1) dividing adjacent positions into 8 cells by taking the current position of the mobile robot as a center;
(4.2.2) acquiring a traversing mode of the mobile robot, and selecting the priority sequence of the template 1 to form a sequence when the traversing mode is from left to right; when the traversal mode is from right to left, the priority order of the template 2 is selected to form a sequence;
wherein, the priority in the template 1 is as follows from high to low: right side cells, rear side cells, front side cells, left side cells, right rear cells, right front cells, left rear cells and left front cells; the priorities in the template 2 are as follows from high to low: a left side cell, a front side cell, a rear side cell, a right side cell, a left rear cell, a left front cell, a right rear cell and a right front cell;
(4.2.3) sequentially judging whether barriers exist in the 8 cells according to the external local environment information in the planning window, and if the barriers exist, deleting the cells from the sequence;
(4.2.4) selecting the bin with the highest priority level in the sequence as the optimal child target point.
Further, the point-to-point path planning method in the step (5) is realized by adopting a biological excitation neural network algorithm.
Further, the global environment information of the area to be planned is obtained through a remote sensing satellite system.
Has the advantages that: compared with the prior art, the invention has the following remarkable advantages: the double-layer path planning algorithm acquires unknown information in the environment in real time through the rolling window, and when encountering an unknown obstacle, performs real-time local path planning on a subregion of the unknown obstacle in a mode of detecting, planning and walking at the same time, so that effective obstacle avoidance can be realized, and a regular coverage path can be obtained. The method adopts a global path planning method under the overall known environment, calls a local path planning method when encountering unknown obstacles, and can effectively avoid the occurrence of the unknown obstacles in complex environments such as mining area waste areas and the like.
Drawings
FIG. 1 is a schematic flow diagram of one embodiment of the present invention;
FIG. 2 is a block diagram of one embodiment of the present invention;
FIG. 3 is a flow chart of a rolling programming walking method;
FIG. 4 is a flow diagram of a priority heuristic;
FIG. 5 is a schematic diagram of two templates in a priority heuristic;
FIG. 6 is a convex environment with a convex obstruction in the area to be planned;
FIG. 7 is a concave environment with a concave obstacle in the area to be planned;
FIG. 8 shows the result of the full coverage path planning in the convex environment;
FIG. 9 is a map of neuron activity values in a convex environment;
FIG. 10 shows the result of the full coverage path planning in the concave environment;
fig. 11 is a map of neuron activity values in a concave environment.
Detailed Description
The embodiment provides a double-layer path planning method for a mobile robot with unknown local environment, as shown in fig. 1, including the following steps:
(1) and acquiring global environment information of the area to be planned.
The global environment information of the area to be planned is known and is obtained through a remote sensing satellite system.
(2) And dividing the area to be planned into a plurality of sub-areas, and performing global path planning by adopting a BINN algorithm according to global environment information to obtain paths in each sub-area.
(3) And walking according to the path planned by the global path, detecting external local environment information in real time by adopting a sensor in the walking process, and updating in real time in a visual window of the mobile robot.
The mobile robot is provided with various vehicle-mounted sensors to acquire the surrounding environment information of the vehicle body, the acquired environment information has high precision, the vehicle-mounted sensors can only detect the environment information in a limited space, and a rolling window is adopted to roll forward in real time to detect the environment of the whole mining area in order to conveniently plan a path for acquiring the information in the whole unknown local area.
(4) And when the unknown obstacle is encountered according to the visual window, the local path planning and walking of the sub-region where the unknown obstacle is located are completed by adopting a rolling planning walking method.
The rolling plan walking method in this step is shown in fig. 3, and specifically includes: (4.1) judging whether a target point of a subregion where the unknown obstacle is located is reached according to the current visual window; if so, executing the step (5), otherwise, executing the steps (4.2) and (4.2) to update the rolling of the planning window into the current visual window, and determining the optimal sub-target point of the current rolling planning period by using a priority heuristic method according to the external local environment information in the planning window; (4.3) planning a path to the optimal child target point by adopting a biological excitation neural network algorithm, and walking to the optimal child target point according to the planned path, wherein the visual window is updated in real time in the walking process; and (4.4) returning to execute the step (4.2). The method can greatly reduce the difficulty of realizing the global coverage. The method can divide the complete path in the unknown environment into step-by-step local paths, greatly improves the real-time performance of the algorithm, and is beneficial to the robot to make a reasonable behavior strategy in time when detecting the unknown obstacle.
Wherein, the priority heuristic method in step (4.2) is shown in fig. 4, and specifically includes: (4.2.1) dividing adjacent positions into 8 cells by taking the current position of the mobile robot as a center; (4.2.2) acquiring a traversing mode of the mobile robot, and selecting the priority sequence of the template 1 to form a sequence when the traversing mode is from left to right; when the traversal mode is from right to left, the priority order of the template 2 is selected to form a sequence; wherein, the priority in the template 1 is as follows from high to low: right side cells, rear side cells, front side cells, left side cells, right rear cells, right front cells, left rear cells and left front cells; the priorities in the template 2 are as follows from high to low: left side cell, front side cell, back side cell, right side cell, left back cell, left front cell, right back cell, right front cell, as shown in fig. 5. (4.2.3) sequentially judging whether barriers exist in the 8 cells according to the external local environment information in the planning window, and if the barriers exist, deleting the cells from the sequence; (4.2.4) selecting the bin with the highest priority level in the sequence as the optimal child target point. The principle of specifying the template is: when the traversing mode of the mobile robot is from left to right, missing coverage areas are easy to occur on the left when unknown obstacles appear in the environment according to a global path planning algorithm; when the traversing mode of the mobile robot is from right to left, missing coverage areas easily appear on the right side when unknown obstacles appear in the environment. The priority heuristic method is visual and effective, and can effectively reduce information misjudgment and path redundancy.
(5) And planning a path from the sub-region where the unknown obstacle is located to the starting point of the next sub-region by adopting a point-to-point path planning method, and reaching the starting point of the next sub-region according to the path.
After the mobile robot completes the covering task in the unknown sub-region, the transfer from the current sub-region to the next sub-region is completed, and the point-to-point path planning method is completed through a BINN algorithm for increasing the activity value of the target neuron.
(6) And (4) returning to execute the step (3) until all the sub-area paths are finished and reach the end point, and obtaining all the paths of the area to be planned.
The invention relates to a double-layer path planning algorithm. The framework of this algorithm includes two layers: the first layer is a global path plan constructed according to prior environmental information; the second layer is a local path plan with unknown obstacles inside the sub-regions. The method adopts a global path planning method in the overall known environment, calls a local path planning method when an unknown obstacle appears, can effectively plan a local path in an unknown sub-region, and can realize full-coverage traversal in the whole working space. The two layers are both independent and dependent.
The invention is subjected to simulation verification, the area to be planned is a waste mining area, and in order to realize complete traversal of the waste mining area and reduce repeated coverage, the environment is assumed as follows according to the actual situation: (1) assuming that the environment global information of the abandoned area of the mining area is known and part of the information is unknown; (2) the complexity of the obstacle existing in the environment is assumed, namely a regular obstacle and an irregular obstacle exist at the same time; (3) during simulation experiments, the coal gangue dump is assumed to be a triangular barrier, the abandoned factory area is a polygonal barrier, and the water accumulation area of the mining area and other complex barriers are represented by irregular barriers. The area is divided into a to J sub-areas, and obstacles are added in the single sub-area J before simulation, wherein the environment with convex obstacles is shown in figure 6, and the environment with concave obstacles is shown in figure 7.
The experiment was divided into two parts: the method comprises the following steps of carrying out full-coverage path planning experiments in the environment with convex obstacles and carrying out full-coverage path planning experiments in the environment with concave obstacles. The first layer full coverage path planning parameters are set as follows: e-100, a-20, B-1, D-1, μ -1, c-1, E being a constant much larger than B, a being the decay rate, B being the upper bound of the neuron activity value, -D being the lower bound of the neuron activity value, μ, c being constant terms. The second layer full coverage parameter settings are as follows: e-200, a-20, B-1, D-1, μ -0.8, c-1. The point-to-point path planning experiment is divided into three parts, and parameters of a J-I area are set as follows: e ═ 200, a ═ 20, B ═ 1, D ═ 1, μ ═ 1, and c ═ 1; region I-F: e ═ 200, a ═ 10, B ═ 1, D ═ 1, μ ═ 1, and c ═ 1; region F-C: e-200, a-20, B-1, D-1, μ -1, and c-1. In this experiment, the starting point of each subregion is denoted by "+", the path planning results will vary according to the situation of obstacles in the environment, and the end points are denoted by "star". Fig. 8 is a full coverage path planning result when a convex obstacle exists in the J area, and fig. 9 is a neuron activity value map of the mobile robot at the (9,29) position. Fig. 10 is a full coverage path planning experiment in an environment where a concave obstacle exists inside the J area, and fig. 11 is a neuron activity value map of the mobile robot at the (8,29) position. As shown in the experimental result diagram, in the aspect of full-coverage path planning, the mobile robot can reformulate a walking path when encountering an obstacle, and timely cover the left free area; in the aspect of point-to-point path planning, when the mobile robot drives to a node containing an unknown obstacle region, the effective transfer from the current node to the optimal starting point of the next sub-region can be completed.
While the invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not to be limited to the disclosed embodiment, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (5)
1. A mobile robot double-layer path planning method with unknown local environment is characterized by comprising the following steps:
(1) acquiring global environment information of an area to be planned;
(2) dividing a region to be planned into a plurality of sub-regions, and performing global path planning by adopting a biological excitation neural network algorithm according to global environment information to obtain paths in each sub-region;
(3) walking according to the path planned by the global path, detecting external local environment information in real time by adopting a sensor in the walking process, and updating in real time in a visual window of the mobile robot;
(4) when the unknown barrier is encountered, the local path planning and walking of the subregion where the unknown barrier is located are completed by adopting a rolling planning walking method;
(5) planning a path from the sub-region where the unknown barrier is located to the starting point of the next sub-region by adopting a point-to-point path planning method, and reaching the starting point of the next sub-region according to the path;
(6) and (4) returning to execute the step (3) until all the sub-area paths are finished and reach the end point, and obtaining all the paths of the area to be planned.
2. The method for planning the double-layer path of the mobile robot with unknown local environment according to claim 1, wherein: the rolling planning walking method in the step (4) specifically comprises the following steps:
(4.1) judging whether a target point of a subregion where the unknown obstacle is located is reached according to the current visual window; if yes, executing the step (5), otherwise, executing the step (4.2)
(4.2) updating the planning window to be a current visual window in a rolling manner, and determining the optimal sub-target point of the current rolling planning period by using a priority heuristic method according to the external local environment information in the planning window;
(4.3) planning a path to the optimal child target point by adopting a biological excitation neural network algorithm, and walking to the optimal child target point according to the planned path, wherein the visual window is updated in real time in the walking process;
and (4.4) returning to execute the step (4.2).
3. The method for planning the double-layer path of the mobile robot with unknown local environment according to claim 2, wherein: the priority heuristic method specifically comprises the following steps:
(4.2.1) dividing adjacent positions into 8 cells by taking the current position of the mobile robot as a center;
(4.2.2) acquiring a traversing mode of the mobile robot, and selecting the priority sequence of the template 1 to form a sequence when the traversing mode is from left to right; when the traversal mode is from right to left, the priority order of the template 2 is selected to form a sequence;
wherein, the priority in the template 1 is as follows from high to low: right side cells, rear side cells, front side cells, left side cells, right rear cells, right front cells, left rear cells and left front cells; the priorities in the template 2 are as follows from high to low: a left side cell, a front side cell, a rear side cell, a right side cell, a left rear cell, a left front cell, a right rear cell and a right front cell;
(4.2.3) sequentially judging whether barriers exist in the 8 cells according to the external local environment information in the planning window, and if the barriers exist, deleting the cells from the sequence;
(4.2.4) selecting the bin with the highest priority level in the sequence as the optimal child target point.
4. The method for planning the double-layer path of the mobile robot with unknown local environment according to claim 1, wherein: and (5) realizing the point-to-point path planning method by adopting a biological excitation neural network algorithm.
5. The method for planning the double-layer path of the mobile robot with unknown local environment according to claim 1, wherein: and acquiring the global environment information of the area to be planned through a remote sensing satellite system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010993923.7A CN112025715A (en) | 2020-09-21 | 2020-09-21 | Mobile robot double-layer path planning method with unknown local environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010993923.7A CN112025715A (en) | 2020-09-21 | 2020-09-21 | Mobile robot double-layer path planning method with unknown local environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112025715A true CN112025715A (en) | 2020-12-04 |
Family
ID=73575537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010993923.7A Pending CN112025715A (en) | 2020-09-21 | 2020-09-21 | Mobile robot double-layer path planning method with unknown local environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112025715A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112147998A (en) * | 2020-08-24 | 2020-12-29 | 同济大学 | Mobile robot path planning method based on region growing method |
| CN112379697A (en) * | 2020-12-15 | 2021-02-19 | 广州极飞科技有限公司 | Trajectory planning method and device, trajectory planner, unmanned aerial vehicle and storage medium |
| CN113064432A (en) * | 2021-03-22 | 2021-07-02 | 深圳市商汤科技有限公司 | Path covering method and device, electronic equipment and storage medium |
| CN114474091A (en) * | 2022-01-26 | 2022-05-13 | 北京声智科技有限公司 | Robot killing method, robot, device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105922267A (en) * | 2016-06-28 | 2016-09-07 | 山东理工大学 | Design method of full-coverage traversal path planning algorithm of cleaning robot |
| CN107577230A (en) * | 2017-08-16 | 2018-01-12 | 武汉理工大学 | A kind of intelligent avoidance collision system towards unmanned boat |
| US20180174023A1 (en) * | 2016-12-20 | 2018-06-21 | Intel Corporation | Autonomous navigation using spiking neuromorphic computers |
| CN110502006A (en) * | 2019-07-22 | 2019-11-26 | 中国矿业大学 | A kind of Mine Abandoned Land mobile robot complete coverage path planning method |
-
2020
- 2020-09-21 CN CN202010993923.7A patent/CN112025715A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105922267A (en) * | 2016-06-28 | 2016-09-07 | 山东理工大学 | Design method of full-coverage traversal path planning algorithm of cleaning robot |
| US20180174023A1 (en) * | 2016-12-20 | 2018-06-21 | Intel Corporation | Autonomous navigation using spiking neuromorphic computers |
| CN107577230A (en) * | 2017-08-16 | 2018-01-12 | 武汉理工大学 | A kind of intelligent avoidance collision system towards unmanned boat |
| CN110502006A (en) * | 2019-07-22 | 2019-11-26 | 中国矿业大学 | A kind of Mine Abandoned Land mobile robot complete coverage path planning method |
Non-Patent Citations (2)
| Title |
|---|
| 王仲民 等: "基于神经元激励的移动机器人遍历路径规划", 《控制工程》 * |
| 邱雪娜 等: "不确定动态环境下移动机器人的完全遍历路径规划", 《机器人》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112147998A (en) * | 2020-08-24 | 2020-12-29 | 同济大学 | Mobile robot path planning method based on region growing method |
| CN112379697A (en) * | 2020-12-15 | 2021-02-19 | 广州极飞科技有限公司 | Trajectory planning method and device, trajectory planner, unmanned aerial vehicle and storage medium |
| WO2022127737A1 (en) * | 2020-12-15 | 2022-06-23 | 广州极飞科技股份有限公司 | Trajectory planning method and apparatus, trajectory planner, unmanned aerial vehicle, and storage medium |
| CN112379697B (en) * | 2020-12-15 | 2024-04-12 | 广州极飞科技股份有限公司 | Track planning method, device, track planner, unmanned aerial vehicle and storage medium |
| CN113064432A (en) * | 2021-03-22 | 2021-07-02 | 深圳市商汤科技有限公司 | Path covering method and device, electronic equipment and storage medium |
| CN114474091A (en) * | 2022-01-26 | 2022-05-13 | 北京声智科技有限公司 | Robot killing method, robot, device and storage medium |
| CN114474091B (en) * | 2022-01-26 | 2024-02-27 | 北京声智科技有限公司 | Robot killing method, killing robot, killing device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112025715A (en) | Mobile robot double-layer path planning method with unknown local environment | |
| CN110502006B (en) | Full-coverage path planning method for mobile robot in abandoned land of mining area | |
| CN109976350B (en) | Multi-robot scheduling method, device, server and computer readable storage medium | |
| US11378964B2 (en) | Systems and methods for autonomous movement of material | |
| CN110908377B (en) | Robot navigation space reduction method | |
| US11591757B2 (en) | System and method for machine control | |
| CN112000754A (en) | Map construction method and device, storage medium and computer equipment | |
| CN110553660B (en) | Unmanned vehicle trajectory planning method based on A-star algorithm and artificial potential field | |
| DE102019108795A1 (en) | FAHRZEUGWEGIDENTIFIKATION | |
| CN103823466A (en) | Path planning method for mobile robot in dynamic environment | |
| CN112798002A (en) | Intelligent vehicle autonomous path planning method and system and readable storage medium | |
| CN112925315A (en) | Crawler path planning method based on improved ant colony algorithm and A-star algorithm | |
| CN108873882B (en) | Intelligent mobile device, and method, apparatus, program, and medium for planning movement path thereof | |
| CN114089765A (en) | Urban green land-oriented traversing path planning method for mowing robot | |
| CN112656307B (en) | Cleaning method and cleaning robot | |
| CN113879339A (en) | Decision planning method for automatic driving, electronic device and computer storage medium | |
| CN110244716A (en) | A method of the robot based on wave front algorithm is explored | |
| CN112987749A (en) | Hybrid path planning method for intelligent mowing robot | |
| CN112061116A (en) | Parking strategy of reinforcement learning method based on potential energy field function approximation | |
| CN115097823A (en) | Robot task execution method and device, robot and storage medium | |
| CN114764239A (en) | Cleaning robot control method, cleaning robot control device, computer equipment and storage medium | |
| CN112486182B (en) | Sweeping robot for realizing unknown environment map construction and path planning and use method thereof | |
| WO2018210303A1 (en) | Road model construction | |
| CN113110431A (en) | Real-time planning method for field test path of unmanned target vehicle | |
| CN117109574A (en) | Agricultural transportation machinery coverage path planning 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201204 |
|
| RJ01 | Rejection of invention patent application after publication |