CN113400303A - Six-axis robot fruit and vegetable picking path planning method based on RRT (recursive least squares) algorithm - Google Patents
Six-axis robot fruit and vegetable picking path planning method based on RRT (recursive least squares) algorithm Download PDFInfo
- Publication number
- CN113400303A CN113400303A CN202110607019.2A CN202110607019A CN113400303A CN 113400303 A CN113400303 A CN 113400303A CN 202110607019 A CN202110607019 A CN 202110607019A CN 113400303 A CN113400303 A CN 113400303A
- Authority
- CN
- China
- Prior art keywords
- axis robot
- degrees
- axes
- point
- fruit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- B25J9/1679—Programme controls characterised by the tasks executed
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
The invention relates to a six-axis robot fruit and vegetable picking path planning method based on RRT algorithm, which reduces the path planning time and improves the working efficiency by adjusting the search radius range; limiting six-axis motion angles of the six-axis robot to avoid the mechanical arms of the six-axis robot moving to singular points and self-collision points and reduce the collision risk of the six-axis robot; the grabbing angle and range within the distance range of reaching the set end point E are optimized; and smoothing the inflection point of the updated tree, so that the shaking phenomenon of the six-axis robot moving to the inflection point of the broken line is avoided, and the real-time operability is improved. The invention comprehensively considers the factors of the complexity of the agricultural scene, the shortest path, the maneuverability, the safety, the feasibility and the like of the six-axis robot to plan the path, and has better practicability.
Description
Technical Field
The invention belongs to the technical field of robots, relates to optimization of a robot path algorithm and improvement of efficiency, and particularly relates to a six-axis robot fruit and vegetable picking path planning method based on an RRT algorithm.
Background
With the development of science and technology, robots are applied more and more in industrial manufacturing, fruit and vegetable picking and other occasions. The path planning of the robot is a key factor influencing the operation effect and the working efficiency of the robot, and the algorithm is the basis of the path planning. Common algorithms in path planning include fast-expanding random tree (RRT) algorithm and progressive-optimization RRT algorithm. Fruit and vegetable picking is the most time-consuming and labor-consuming link in an agricultural production chain, and has the characteristics of strong picking seasonality, high labor intensity, high cost and the like. Therefore, the improvement of the path planning method of the fruit and vegetable picking robot and the improvement of the operation performance of the fruit and vegetable picking robot have important influences on the improvement of fruit and vegetable picking efficiency, the reduction of cost and the guarantee of quality.
The RRT algorithm generates a random expansion tree by taking an initial point as a root node and increasing leaf nodes through random sampling, and when the leaf nodes in the random tree contain a target point or enter a target area, a path from the initial point to the target point can be found in the random tree. But the algorithm is computationally expensive and the generated path is feasible but not optimal.
The RRT algorithm is based on the original RRT algorithm, the selection mode of a father node is improved, a cost function is adopted to select the node with the minimum cost in the expansion node field as the father node, and meanwhile, the nodes on the existing tree are reconnected after each iteration, so that the calculation complexity and the progressive optimal solution are guaranteed. But this algorithm greatly reduces the efficiency of the algorithm in searching for parent nodes and rewiring.
The six-axis robot fruit and vegetable picking path planning solves the optimal or shortest path problem, and in addition, the factors of complexity, maneuverability, energy consumption and the like of the six-axis robot use environment also need to be comprehensively considered, and the following problems need to be solved:
(1) in the fruit and vegetable picking process, the six-axis robot needs to be static and waits for the completion of path planning, and then moves to a target point, so that the picking efficiency is low;
(2) due to the fact that the fruits and vegetables are too close to the branches, when the path planning reaches the positions close to the fruits and vegetables, the fruits and vegetables may touch the branches, and the collision risk degree is high;
(3) the path planning is a broken line, the six-axis robot can shake at the turning point of the broken line in the picking process, and the actual operation performance is poor;
(4) the prior six-axis robot in China has singular points, the robot self-collision or severe shaking phenomenon can occur when the robot reaches the singular points, and meanwhile, the self-collision phenomenon among the six axes also exists, so that the normal use of the robot is influenced;
(5) the six-axis robot has complex environment and high efficiency requirement for picking fruits and vegetables.
Therefore, the fruit and vegetable picking path planned according to the traditional RRT algorithm and RRT algorithm needs longer time and is low in efficiency, so that the six-axis robot is poor in operation performance, low in efficiency and poor in safety.
Disclosure of Invention
The invention provides a six-axis robot fruit and vegetable picking path planning method based on an RRT algorithm, which is used for solving the problems of long time and low efficiency of the existing robot fruit and vegetable picking path and improving the maneuverability, efficiency and safety of the six-axis robot.
In order to realize the purpose of the invention, the following technical scheme is adopted:
a six-axis robot fruit and vegetable picking path planning method based on RRT algorithm comprises the following steps:
step 1, initialization: acquiring data of the current position of the six-axis robot and the central position of the fruits and vegetables, respectively marking the data as a starting point S and an end point E, setting a search radius r and a value of a node falling in the range of the end point E, and limiting six-axis motion angles of the six-axis robot so as to avoid the mechanical arm of the six-axis robot from moving to a singular point and a self-collision point;
step 2, finding out the node X closest to the starting point S on the treenCalculating the starting point S to the node XnAn old path cost;
step 3, searching nodes on a tree within six-axis motion angles of the six-axis robot by taking the initial point S as a center and the search radius r as a range;
step 4, finding out a potential father node set XP, and randomly taking a father node X from the potential father node set XPp_p；
Step 5, calculating the starting point S to the father node Xp_pCost of the new path;
step 6, comparing the cost of the new path with that of the old path, and if the cost of the new path is low, executing the next step; if the cost of the new path is high, returning to the step 4 to replace the new path with the next potential parent node;
step 7, judging whether the node falls into the range of the termination point E, if so, adjusting the search angle of the search radius r, limiting the grabbing range of the six-axis robot on the fruits and vegetables, then performing collision detection, and if not, directly performing collision detection; if the collision detection is not passed, returning to execute the steps 4 to 7 until the collision detection is passed; if the collision detection is passed, executing the next step;
step 8, deleting the previous edge in the tree;
step 9, adding the new edge to the tree;
step 10, traversing all potential father nodes to obtain an updated tree;
step 11, smoothing the polyline inflection point of the updated tree;
and step 12, finishing path planning.
In order to further realize the purpose of the invention, the following technical scheme can be adopted:
in the method for planning fruit and vegetable picking paths by using the six-axis robot based on the RRT algorithm, in step 1, six motion angles of the six-axis robot are respectively defined as: one axis to three axes are 175 degrees or minus 175 degrees, and the four axes to six axes are 170 degrees or minus 170 degrees; at this time, there are two singular points: five axes are 0 degrees, and four axes are parallel to 6 axes; the three axes are 0 degrees, and the two axes are parallel to 4 axes; the range of the movement from four axes to six axes to 170-175 degrees or-170-175 degrees from the collision point.
In the six-axis robot fruit and vegetable picking path planning method based on the RRT algorithm, in step 7, the range value of the node falling into the termination point E is 15-25 cm.
Further, according to the six-axis robot fruit and vegetable picking path planning method based on the RRT algorithm, when the range value of the node falling into the termination point E is set to be 20cm, the 20cm is used as the radius of the termination point E, the right upper part of the fruit and vegetable is 0 degree, and the fruit and vegetable grabbing range is limited to be 120 degrees to 180 degrees and-120 degrees to 180 degrees.
In the six-axis robot fruit and vegetable picking path planning method based on the RRT algorithm, in step 12, the updated tree is smoothed by using the following formula,
B(t)=A0(1-t)3+3A1t(1-t)2+3A2t2(1-t)+A3t3+b,t
[0,1]；
wherein B (t) is a smoothing function, A0、A1、A2、A3Representing four adjacent points on the path, t being a scale factor and b being a correction factor.
Compared with the prior art, the invention has the advantages that:
the method can reduce the path planning time for picking the fruits and the vegetables by the six-axis robot and improve the fruit and vegetable picking efficiency; the six-axis robot is prevented from shaking and colliding at a singular point and a self-collision point, and the collision risk of the six-axis robot is reduced; the smooth path planning algorithm avoids the shaking phenomenon of the six-axis robot at the inflection point of the broken line, and improves the real-time operability.
The invention comprehensively considers the factors of the complexity of the agricultural scene, the shortest path, the maneuverability, the safety, the feasibility and the like of the six-axis robot to plan the path, and has better practicability; the method is applied to farms for live-action apple picking tests, and the picking path, efficiency, manipulation performance, safety and the like of the six-axis robot are remarkably improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.
FIG. 1 is a flow chart of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention.
As shown in fig. 1, the embodiment discloses a six-axis robot fruit and vegetable picking path planning method based on RRT algorithm, which includes the following steps:
step 1, initialization: acquiring data of the current position of the six-axis robot and the central position of the fruits and vegetables, respectively marking the data as a starting point S and an end point E, setting a search radius r and a value of a node falling in the range of the end point E, and limiting six-axis motion angles of the six-axis robot so as to avoid the mechanical arm of the six-axis robot from moving to a singular point and a self-collision point;
step 2, finding out the node X closest to the starting point S on the treenCalculating the starting point S to the node XnAn old path cost;
step 3, searching nodes on a tree within six-axis motion angles of the six-axis robot by taking the initial point S as a center and the search radius r as a range;
step 4, finding out a potential father node set XP, and randomly taking a father node X from the potential father node set XPp_p；
Step 5, calculating the starting point S to the father node Xp_pCost of the new path;
step 6, comparing the cost of the new path with that of the old path, and if the cost of the new path is low, executing the next step; if the cost of the new path is high, returning to the step 4 to replace the new path with the next potential parent node;
step 7, judging whether the node falls into the range of the termination point E, if so, adjusting the search angle of the search radius r, limiting the grabbing range of the six-axis robot on the fruits and vegetables, then performing collision detection, and if not, directly performing collision detection; if the collision detection is not passed, returning to execute the steps 4 to 7 until the collision detection is passed, and if the collision detection is passed, executing the next step;
step 8, deleting the previous edge in the tree;
step 9, adding the new edge to the tree;
step 10, traversing all potential father nodes to obtain an updated tree;
step 11, smoothing the polyline inflection point of the updated tree;
and step 12, finishing path planning.
Wherein, the specific operation of the step 1 is as follows: the starting point S of the path planning is the current position of the six-axis robot, and the ending point E of the path planning is the center of the fruits and vegetables.
The search radius r may be set according to specific situations, and in this embodiment, the value of the node falling into the range of the termination point E is set to 20cm in the experimental process, and may also be adjusted as needed.
The six-axis motion angles of the six-axis robot are respectively limited: one axis to three axes are 175 degrees or minus 175 degrees, and four axes to six axes are 170 degrees or minus 170 degrees.
In this embodiment, the six-axis robot has two singular point positions: five axes are 0 degrees, and four axes are parallel to six axes; the three axes are 0 degree, and the two axes are parallel to the four axes; from four axes to six axes of collision, the angle of the vertical beam moves to 170 degrees or-175 degrees.
The angle can be adjusted according to actual conditions and requirements. The angle is limited in an algorithm, and the RRT algorithm plans the limited movable angle.
The specific operation of step 3: the six-axis robot searches for nodes, and plans in a movable angle after limiting the angle in step 1.
The specific operation of step 7: the six-axis robot moves within a set angle by taking the end point as the center of a circle and 20cm as the radius, and the right upper side of the fruit and vegetable to be grabbed is 0 degrees, so that the grabbing range is limited to be 120 degrees or less and 180 degrees or less, namely the distance from the end point is within 20cm, and the six-axis robot can only grab the fruit and vegetable within 120 degrees below the fruit and vegetable.
The specific operation of step 12: the updated tree is smoothed using the following formula,
B(t)=A0(1-t)3+3A1t(1-t)2+3A2t2(1-t)+A3t3+b,t
[0,1]；
wherein B (t) is a smoothing function, A0、A1、A2、A3Representing four adjacent points on the path, t being a scale factor and b being a correction factor.
Hereinafter, embodiments of the present invention will be described in detail with reference to specific experiments.
(1) Simulation environment
The experimental environment is simulated in the Rviz of the ubuntu16.04 system, and the six-axis robot and the environment around the fruits and vegetables are modeled in real time by the system.
The simulation environment can display the current position of the six-axis robot and the position of the fruits and vegetables in the binocular camera relative to the six-axis robot in real time, and can also display the whole path planning process of picking the fruits and vegetables by an algorithm, wherein the whole path planning process comprises the binocular camera and the gripper which are fixed on the six-axis robot, and the six-axis robot and the fruits and vegetables can be modeled in the same proportion in the modeling process.
(2) Real farm environment
This experiment is positive for season, and the outdoor scene that carries out is picked at certain farm of Qingdao city levelness is picked, and the system is at first initialized, acquires six axis robot current position as initial point through the sensor promptly, acquires apple central point through binocular camera as the termination point, sets up search radius r and is 20cm, and the distance apart from the termination point sets up to 20 cm.
After initialization is finished, the six-axis robot carries out path planning through an improved RRT algorithm, the six-axis robot firstly moves to a position 20cm away from an initial point to a final point, then the algorithm limits a grabbing angle, and finally the grabbing hand of the six-axis robot grabs the fruit and vegetable from the oblique lower side.
In the experimental process, the branches can be effectively avoided in fruit and vegetable picking, the damage to hardware equipment such as a six-axis robot body, a binocular camera fixed on the robot body, a gripper and the like is avoided, one apple can be picked in 8 seconds on average through statistical calculation, and the picking efficiency is improved; when the six-axis robot picks the apples, the apples are smooth and have no shaking phenomenon.
The technical contents not described in detail in the present invention are all known techniques.
Claims (5)
1. A six-axis robot fruit and vegetable picking path planning method based on RRT algorithm is characterized by comprising the following steps:
step 1, initialization: acquiring data of the current position of the six-axis robot and the central position of the fruits and vegetables, respectively marking the data as a starting point S and an end point E, setting a search radius r and a value of a node falling in the range of the end point E, and limiting six-axis motion angles of the six-axis robot so as to avoid the mechanical arm of the six-axis robot from moving to a singular point and a self-collision point;
step 2, finding out the node X closest to the starting point S on the treenCalculating the starting point S to the node XnAn old path cost;
step 3, searching nodes on a tree within six-axis motion angles of the six-axis robot by taking the initial point S as a center and the search radius r as a range;
step 4, finding out a potential father node set XP, and randomly taking a father node X from the potential father node set XPp_p；
Step 5, calculating the starting point S to the father node Xp_pCost of the new path;
step 6, comparing the cost of the new path with that of the old path, and if the cost of the new path is low, executing the next step; if the cost of the new path is high, returning to the step 4 to replace the new path with the next potential parent node;
step 7, judging whether the node falls into the range of the termination point E, if so, adjusting the search angle of the search radius r, limiting the grabbing range of the six-axis robot on the fruits and vegetables, then performing collision detection, and if not, directly performing collision detection; if the collision detection is not passed, returning to execute the steps 4 to 7 until the collision detection is passed; if the collision detection is passed, executing the next step;
step 8, deleting the previous edge in the tree;
step 9, adding the new edge to the tree;
step 10, traversing all potential father nodes to obtain an updated tree;
step 11, smoothing the polyline inflection point of the updated tree;
and step 12, finishing path planning.
2. The six-axis robot fruit and vegetable picking path planning method based on the RRT algorithm as claimed in claim 1, wherein in the step 1, six-axis motion angles of the six-axis robot are respectively defined as: one axis to three axes are 175 degrees or minus 175 degrees, and the four axes to six axes are 170 degrees or minus 170 degrees; at this time, there are two singular points: five axes are 0 degrees, and four axes are parallel to 6 axes; the three axes are 0 degrees, and the two axes are parallel to 4 axes; the range of the movement from four axes to six axes to 170-175 degrees or-170-175 degrees from the collision point.
3. The six-axis robot fruit and vegetable picking path planning method based on the RRT algorithm as claimed in claim 1, wherein in the step 7, the range value of the node falling into the end point E is 15-25 cm.
4. The six-axis robot fruit and vegetable picking path planning method based on RRT algorithm according to claim 3, characterized in that when the range value of the node falling into the end point E is set to be 20cm, the end point E takes 20cm as the radius and 0 degree is right above the fruit and vegetable, the fruit and vegetable grabbing range is limited to 120 degrees to 180 degrees and-120 degrees to 180 degrees.
5. The six-axis robot fruit and vegetable picking path planning method based on RRT algorithm as claimed in claim 1, wherein in the step 12, the updated tree is smoothed by using the following formula,
B(t)=A0(1-t)3+3A1t(1-t)2+3A2t2(1-t)+A3t3+b,t
[0,1]；
wherein B (t) is a smoothing functionNumber, A0、A1、A2、A3Representing four adjacent points on the path, t being a scale factor and b being a correction factor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110607019.2A CN113400303B (en) | 2021-06-01 | 2021-06-01 | Six-axis robot fruit and vegetable picking path planning method based on RRT (recursive least squares) algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110607019.2A CN113400303B (en) | 2021-06-01 | 2021-06-01 | Six-axis robot fruit and vegetable picking path planning method based on RRT (recursive least squares) algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113400303A true CN113400303A (en) | 2021-09-17 |
| CN113400303B CN113400303B (en) | 2022-09-23 |
Family
ID=77675668
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110607019.2A Active CN113400303B (en) | 2021-06-01 | 2021-06-01 | Six-axis robot fruit and vegetable picking path planning method based on RRT (recursive least squares) algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113400303B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114407030A (en) * | 2021-11-12 | 2022-04-29 | 山东大学 | Autonomous navigation distribution network live working robot and working method thereof |
| CN116394266A (en) * | 2023-06-08 | 2023-07-07 | 国网瑞嘉(天津)智能机器人有限公司 | Robot self-collision processing method and device, robot and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106695802A (en) * | 2017-03-19 | 2017-05-24 | 北京工业大学 | Improved RRT<*> obstacle avoidance motion planning method based on multi-degree-of-freedom mechanical arm |
| CN108983780A (en) * | 2018-07-24 | 2018-12-11 | 武汉理工大学 | One kind is based on improvement RRT*The method for planning path for mobile robot of algorithm |
| CN109397292A (en) * | 2018-11-23 | 2019-03-01 | 华中科技大学 | A kind of 7 degree-of-freedom manipulator control methods and system based on analytic solutions |
| CN112223291A (en) * | 2020-10-21 | 2021-01-15 | 哈工大机器人（合肥）国际创新研究院 | Mechanical arm obstacle avoidance method and device based on three-dimensional task space constraint |
| CN112677153A (en) * | 2020-12-16 | 2021-04-20 | 东北林业大学 | Improved RRT algorithm and industrial robot path obstacle avoidance planning method |
| CN112809665A (en) * | 2020-12-16 | 2021-05-18 | 安徽工业大学 | Mechanical arm motion planning method based on improved RRT algorithm |
-
2021
- 2021-06-01 CN CN202110607019.2A patent/CN113400303B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106695802A (en) * | 2017-03-19 | 2017-05-24 | 北京工业大学 | Improved RRT<*> obstacle avoidance motion planning method based on multi-degree-of-freedom mechanical arm |
| CN108983780A (en) * | 2018-07-24 | 2018-12-11 | 武汉理工大学 | One kind is based on improvement RRT*The method for planning path for mobile robot of algorithm |
| CN109397292A (en) * | 2018-11-23 | 2019-03-01 | 华中科技大学 | A kind of 7 degree-of-freedom manipulator control methods and system based on analytic solutions |
| CN112223291A (en) * | 2020-10-21 | 2021-01-15 | 哈工大机器人（合肥）国际创新研究院 | Mechanical arm obstacle avoidance method and device based on three-dimensional task space constraint |
| CN112677153A (en) * | 2020-12-16 | 2021-04-20 | 东北林业大学 | Improved RRT algorithm and industrial robot path obstacle avoidance planning method |
| CN112809665A (en) * | 2020-12-16 | 2021-05-18 | 安徽工业大学 | Mechanical arm motion planning method based on improved RRT algorithm |
Non-Patent Citations (3)
| Title |
|---|
| 张 勤，刘丰溥，蒋先平: "番茄串收机械臂运动规划方法与试验", 《农业工程学报》 * |
| 李季等: "基于改进RRT算法的6-DOF机器人路径规划", 《计算机应用与软件》 * |
| 马慧丽等: "基于改进RRT算法的机械臂路径规划研究", 《机械设计与研究》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114407030A (en) * | 2021-11-12 | 2022-04-29 | 山东大学 | Autonomous navigation distribution network live working robot and working method thereof |
| CN116394266A (en) * | 2023-06-08 | 2023-07-07 | 国网瑞嘉(天津)智能机器人有限公司 | Robot self-collision processing method and device, robot and medium |
| CN116394266B (en) * | 2023-06-08 | 2023-10-20 | 国网瑞嘉(天津)智能机器人有限公司 | Robot self-collision processing method and device, robot and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113400303B (en) | 2022-09-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108932216B (en) | Robot inverse kinematics solving method based on particle swarm optimization algorithm | |
| CN113400303B (en) | Six-axis robot fruit and vegetable picking path planning method based on RRT (recursive least squares) algorithm | |
| WO2020134254A1 (en) | Method employing reinforcement learning to optimize trajectory of spray painting robot | |
| US9411335B2 (en) | Method and apparatus to plan motion path of robot | |
| CN108582073A (en) | A kind of quick barrier-avoiding method of mechanical arm based on improved random road sign Map Method | |
| Zhaoxin et al. | Design a robot system for tomato picking based on YOLO v5 | |
| CN113799141B (en) | Six-degree-of-freedom mechanical arm obstacle avoidance path planning method | |
| Tang et al. | Learning collaborative pushing and grasping policies in dense clutter | |
| CN112428274B (en) | Space motion planning method of multi-degree-of-freedom robot | |
| Chen et al. | Path planning of the fruit tree pruning manipulator based on improved RRT-Connect algorithm | |
| CN111552300A (en) | Crop picking system based on instance segmentation and path planning | |
| CN115958590A (en) | RRT-based mechanical arm deep frame obstacle avoidance motion planning method and device | |
| Zahid et al. | Collision free path planning of a robotic manipulator for pruning apple trees | |
| CN116038688A (en) | Mechanical arm joint space path planning method based on probability virtual potential field guided bidirectional RRT algorithm | |
| Huadong et al. | A path planning method of robot arm obstacle avoidance based on dynamic recursive ant colony algorithm | |
| Zhang et al. | A heuristic tomato-bunch harvest manipulator path planning method based on a 3D-CNN-based position posture map and rapidly-exploring random tree | |
| CN116138036B (en) | Secondary positioning method for picking young buds of famous tea | |
| Tang et al. | An improved PSO for path planning of mobile robots and its parameters discussion | |
| CN116690557A (en) | Method and device for controlling humanoid three-dimensional scanning motion based on point cloud | |
| Zhuang et al. | Obstacle avoidance path planning for apple picking robotic arm incorporating artificial potential field and a* algorithm | |
| CN116619381A (en) | Obstacle avoidance path planning method for industrial robot | |
| Li et al. | Peduncle collision-free grasping based on deep reinforcement learning for tomato harvesting robot | |
| CN114310872B (en) | Automatic vegetable-beating method for mechanical arm based on DGG point cloud segmentation network | |
| CN115810188A (en) | Method and system for identifying three-dimensional pose of fruit on tree based on single two-dimensional image | |
| CN113146637B (en) | Robot Cartesian space motion 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |