CN115107021A - Mechanical arm path planning rapid prototyping system - Google Patents
Mechanical arm path planning rapid prototyping system Download PDFInfo
- Publication number
- CN115107021A CN115107021A CN202210582771.0A CN202210582771A CN115107021A CN 115107021 A CN115107021 A CN 115107021A CN 202210582771 A CN202210582771 A CN 202210582771A CN 115107021 A CN115107021 A CN 115107021A
- Authority
- CN
- China
- Prior art keywords
- mechanical arm
- path
- obstacle
- random
- camera
- 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
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000004891 communication Methods 0.000 claims abstract description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 46
- 230000005484 gravity Effects 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 9
- 230000004888 barrier function Effects 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 230000002457 bidirectional effect Effects 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000004088 simulation Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 230000006872 improvement Effects 0.000 claims description 2
- 238000013461 design Methods 0.000 abstract description 3
- 235000011470 Adenanthera pavonina Nutrition 0.000 description 10
- 241000428378 Lopa Species 0.000 description 10
- 239000004575 stone Substances 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
The invention relates to a system and a method for rapid prototyping of mechanical arm path planning, which comprises a camera, a computer and a mechanical arm; the camera is connected with the computer through a data line, the mechanical arm and the camera are installed out of hand in an eye-to-eye mode, and the mechanical arm and the computer are connected through a network cable and used for achieving communication between Matlab and the mechanical arm; the invention has reasonable design.
Description
Technical Field
The invention relates to the field of mechanical arms, in particular to a system and a method for rapid prototyping of mechanical arm path planning.
Background
The appearance of arm has liberated human both hands, can replace human to accomplish some repeated or dangerous work, can improve production efficiency and guarantee personnel's safety. Path planning is an important part in the process of completing tasks by the robotic arm. Most of the current mechanical arm path planning depends on manual teaching, and the method is simple, but has some defects. After manual teaching, the robot arm can only perform actions according to set path points or programs. When the working environment of the mechanical arm changes, the teaching needs to be carried out again, and the method is not suitable for the complex working environment of the mechanical arm.
At present, scholars at home and abroad have proposed some advanced algorithms to realize path planning of the mechanical arm, such as an artificial potential field method, an ant colony algorithm, a genetic algorithm and the like. However, when the algorithms are applied to the mechanical arm, two difficulties exist, firstly, the working space of the mechanical arm becomes high-dimensional, and some algorithms are not applicable any more; the other is that collision detection becomes more complicated, and not only the end of the robot arm but also each link of the robot arm needs to be detected. Therefore, in order to select a high-quality algorithm to implement path planning, a path planning algorithm needs to be studied.
Many scholars currently propose some advanced path planning algorithms, but due to the limitation of various conditions, the improved methods are only verified at a theoretical level and lack of physical verification. If the difficulty of writing a program on hardware to realize the algorithm is high, a large amount of time is needed to be consumed, and the progress of the project is not facilitated. Therefore, the invention designs a rapid prototype system for path planning of the mechanical arm, and aims to rapidly verify the feasibility of the proposed path planning algorithm.
Disclosure of Invention
The invention aims to solve the technical problem of providing a mechanical arm path planning rapid prototyping system and a method, wherein the system takes a path planning algorithm as a core and aims to rapidly verify the feasibility of the proposed path planning algorithm.
In order to solve the problems, the technical scheme adopted by the invention is as follows:
a rapid prototyping system for mechanical arm path planning comprises a camera, a computer and a mechanical arm;
the camera is connected with the computer through a data line, the mechanical arm and the camera are installed out of hand in an eye-to-eye mode, and the mechanical arm and the computer are connected through a network cable and used for achieving communication between Matlab and the mechanical arm;
the camera adopts a ZED2 binocular camera, comprises a left camera and a right camera and is used for shooting scene pictures;
the mechanical arm system also comprises other accessories such as a control cabinet, a demonstrator and the like;
the mechanical arm is provided with an external communication interface and can conveniently communicate with external equipment;
the software part of the computer is used for simulating an image processing and path planning algorithm;
image processing, namely acquiring the positions of all obstacles in a working scene of the mechanical arm by using a visual method, and firstly, identifying and positioning all the obstacles by using any target detection algorithm; and then, realizing the conversion of the position of the obstacle by using a hand-eye calibration method. Under the condition that the information of the obstacles is known, a path planning algorithm is programmed and realized in Matlab, a feasible path is planned for the mechanical arm, and the mechanical arm moves to the specified position under the condition that the mechanical arm is not in contact with the obstacles. The mechanical arm is not in contact with the obstacle, namely the distance between the mechanical arm and the obstacle is larger than the set distance.
The mechanical arm path planning rapid prototyping system is used for rapidly verifying whether the proposed path planning algorithm is feasible, and the specific mechanical arm path planning experiment verification method comprises the following steps:
step 1: calibrating a binocular camera, and controlling the binocular camera to shoot a scene picture by using a computer after acquiring parameters of the camera;
and 2, step: identifying and positioning obstacles in the scene by using a target detection algorithm;
and step 3: the position of the barrier is converted by using a hand-eye calibration method;
and 4, step 4: compiling a script file in Matlab to realize a path planning algorithm by combining the barrier information obtained in the step 3 to obtain a feasible path;
and 5: establishing communication between the mechanical arm and Matlab in the computer, and sending path information to the mechanical arm;
step 6: and the mechanical arm moves to a specified position according to the received path information.
In step 1, firstly, the binocular camera is calibrated by using the zhang's calibration method: shooting pictures of the checkerboard calibration plates at different angles by using a binocular camera, inputting the pictures into Matlab, and acquiring parameters of the binocular camera by using a camera calibration tool box; secondly, shooting a picture of a working scene of the mechanical arm by using a binocular camera;
in step 2, firstly, a data set is made by label image software; then, training the data set by using a Faster R-CNN algorithm to obtain a model of the obstacle; secondly, transmitting the picture of the mechanical arm working scene to a computer, detecting the obstacle in the mechanical arm working scene by using the trained model to obtain the pixel coordinate of the obstacle, and acquiring the depth value from the camera to the obstacle by using a binocular camera; finally, calculating to obtain the three-dimensional coordinates of the barrier through coordinate transformation;
in step 3, the positions of the mechanical arm and the binocular camera are determined by a hand-eye calibration method with eyes outside the hands, the pose of the mechanical arm is changed for more than 10 times, pose data is recorded, external parameters of the camera are solved, a hand-eye transformation matrix is further solved, and obstacle information is converted into a mechanical arm base coordinate system;
in step 4, firstly, combining the barrier information obtained in step 3, compiling a script file in Matlab by using an improved RRT algorithm to realize a path planning algorithm, and firstly adopting bidirectional expansion; then, reducing the randomness of the sampling points by using a random point preferred idea, accelerating the searching speed by using a gravity adjustable step length strategy, and optimizing a path by using a path optimization strategy; finally, obtaining a feasible path meeting the set conditions;
firstly, setting a probability threshold bias, when the random number is greater than the bias, simultaneously generating two random points to be selected by using a random function, calculating the distance between the two random points to be selected and a target point, and then determining a node closer to the target point as a final random point; when the random number is smaller than the bias, the target point is still set as a random point;
the gravity adjustable step length strategy is characterized in that a gravity idea is added into an algorithm, the value of a gravity coefficient is adaptively adjusted according to whether a mechanical arm meets an obstacle or not in the advancing process, the step length is changed, the purpose of rapidly avoiding the obstacle is achieved, and when a random tree does not meet the obstacle during expansion, the initial value is kept unchanged for expansion; when the random tree encounters an obstacle in the expansion process, the value of the random tree is reduced, the step length in the direction of the attractive force is further reduced, a new node is obtained in a circulating mode again, if the random tree still contacts the obstacle, the value of the random tree is continuously reduced, when the value of the random tree is reduced to 0, the expansion of the new node is completely determined by the random point, and finally the new node can successfully avoid the obstacle.
The path optimization strategy is to smooth the initial path with a quadratic B-spline curve.
In the improved RRT algorithm process, firstly, two random trees are initialized, and a random point is determined in the joint space of a mechanical arm by using a random point preference strategy; then, finding the nearest point closest to the random point in the first tree, obtaining a new node by using a gravity adjustable step length strategy, calculating the Cartesian position of the new node, performing collision detection, if no collision exists, adding the new node into the random tree, judging whether the two trees are connected, if no connection exists, exchanging the two trees for expansion, if connection succeeds, outputting a path, smoothing the initial path by using a quadratic B spline curve, and finally obtaining a smoothed path;
in step 5: firstly, after path information is obtained, taking Matlab as a server side and taking a mechanical arm as a client side; then, setting the IP of the computer, the IP of a server in Matlab and the IP in a mechanical arm demonstrator as the same address, setting a port, and establishing socket communication between the mechanical arm and the Matlab in the computer when the IP of the computer and the IP of the mechanical arm are in the same network segment;
in step 6, after the communication is successful, the path information is sent to the mechanical arm, and the mechanical arm is made to move to the designated position.
The method has reasonable design, can quickly verify the feasibility of the path planning algorithm, and saves time waste caused by programming on hardware.
Drawings
FIG. 1 is a diagram of the hardware connection of the present invention.
FIG. 2 is a flow chart of the present invention.
Fig. 3 is a flow chart of the improved RRT algorithm.
Fig. 4 is a diagram of a simulation result of path planning in Matlab.
Fig. 5 is a diagram of a path planning process in an actual scenario.
(a) As a starting point, (b) is close to the obstacle 1, (c) is close to the obstacle 1, (d) is close to the obstacle 2, (e) is close to the obstacle 2, (f) is close to the obstacle 3, (h) is close to the obstacle 3, and (g) is an arrival target point.
Detailed Description
The present invention encompasses fig. 1-5, wherein, as an embodiment, fig. 1, a robot path planning rapid prototyping system comprises a camera, a computer, and a robot;
the camera adopts a binocular camera, comprises a left camera and a right camera and is used for shooting scene pictures;
the mechanical arm can be in any type and any degree of freedom, and the system also comprises a control cabinet, a demonstrator and other mechanical arm accessories;
the mechanical arm is provided with an external communication interface and can conveniently communicate with external equipment;
the software part of the computer is used for image processing and path planning algorithm simulation;
image processing, namely acquiring the positions of all obstacles in a working scene of the mechanical arm by using a visual method, and firstly, identifying and positioning all the obstacles by using any target detection algorithm; and then, realizing the conversion of the position of the obstacle by using a hand-eye calibration method. Under the condition of known obstacle information, a path planning algorithm can be quickly programmed in Matlab, a feasible path is planned for the mechanical arm, and the mechanical arm moves to a specified position under the condition of not contacting with the obstacle.
The mechanical arm is not in contact with the obstacle, namely the distance between the mechanical arm and the obstacle is larger than the set distance.
As an embodiment, as shown in fig. 1, the rapid prototyping system for path planning of mechanical arm according to an embodiment of the present invention includes a six-axis mechanical arm (for short, a loving stone mechanical arm) from loving stone company, a ZED2 binocular camera, and a computer, where the ZED2 binocular camera is connected to the computer through a USB3.0 data line, the loving stone mechanical arm and the ZED2 binocular camera are installed out of hand, and the loving stone mechanical arm and the computer are connected by a network line, so as to implement communication between Matlab and the loving stone mechanical arm.
According to the mechanical arm path planning rapid prototyping system provided by the embodiment of the invention, the obstacles in the scene are represented by the balloons.
As an embodiment, in the rapid prototyping system for mechanical arm path planning of the embodiment of the invention, the adopted path planning algorithm is an improved RRT algorithm, a three-point improvement strategy is provided on the basis of bidirectional expansion, the randomness of sampling points is reduced by using a random point preferred idea, the search speed is accelerated by using a gravity adjustable step length strategy, and the path is optimized by using a path optimization strategy.
The random point preferred strategy is an improved probability biased strategy, firstly, a probability threshold bias is set, when the random number is greater than the bias, two random points to be selected are generated simultaneously by using a random function, the distance between the two random points to be selected and a target point is calculated, and then a node closer to the target point is determined as a final random point; and when the random number is smaller than the bias, the target point is still set as the random point.
The gravity adjustable step length strategy is characterized in that a gravity idea is added into an algorithm, the value of a gravity coefficient is adaptively adjusted according to whether a mechanical arm meets an obstacle or not in the advancing process, the step length is changed, and the purpose of rapidly avoiding the obstacle is achieved. Specifically, when the random tree does not encounter an obstacle during expansion, the initial value is kept unchanged for expansion; when the random tree encounters an obstacle in the expansion process, the value of the random tree is reduced, the step length in the direction of the attractive force is further reduced, a new node is obtained in a circulating mode again, if the random tree still contacts the obstacle, the value of the random tree is continuously reduced, when the value of the random tree is reduced to 0, the expansion of the new node is completely determined by the random point, and finally the new node can successfully avoid the obstacle.
The path optimization strategy is to smooth the initial path with a quadratic B-spline curve.
As an embodiment, as shown in fig. 2, a flowchart of a rapid prototyping system for path planning of a rock manipulator is provided, and the specific implementation steps are as follows:
step 1: calibrating a ZED2 binocular camera by using a Zhang calibration method, shooting pictures of checkerboard calibration plates at different angles by using a ZED2 binocular camera, inputting the shot pictures into Matlab, acquiring parameters of the ZED2 binocular camera by using a camera calibration tool box, and then shooting pictures of a working scene of a Lopa stone mechanical arm by using a ZED2 binocular camera;
step 2: recognizing and positioning obstacles in a mechanical arm working scene by using a target detection algorithm, manufacturing a balloon data set by using label image software, training the balloon data set by using a Faster R-CNN algorithm to obtain a model of the obstacles, transmitting a picture of the Lopa mechanical arm working scene to a computer, recognizing the obstacles in the mechanical arm working scene by using the trained model to obtain pixel coordinates of the obstacles, acquiring depth values from a camera to the obstacles by using a binocular camera, and finally calculating three-dimensional coordinates of the obstacles by coordinate transformation;
and step 3: determining the positions of a six-axis mechanical arm and a ZED2 binocular camera by adopting a hand-eye calibration method with eyes outside hands, fixing the ZED2 binocular camera at one position, not contacting with a Lobstite mechanical arm, placing a chessboard grid calibration plate at the tail end of the Lobstite mechanical arm, changing the pose of the Lobstite mechanical arm for more than 10 times, recording the pose data, solving the camera external parameters, further solving a hand-eye transformation matrix, and converting barrier information into a Lobstite mechanical arm base coordinate system;
and 4, step 4: firstly, initializing two random trees, determining a random point in a joint space of the rock-like mechanical arm by using a random point preference strategy, finding the closest point in the first tree to the random point, obtaining a new node by using a gravity adjustable step length strategy, calculating the Cartesian position of the new node, detecting collision, adding the new node into the random tree if no collision exists, judging whether the two trees are connected, if no connection exists, exchanging the two trees for expansion, if the connection is successful, outputting a path, smoothing the initial path by using a quadratic B spline curve, and finally obtaining a smoothed path;
and 5: after the path information is obtained, Matlab is used as a server side, a Lopa mechanical arm is used as a client side, the IP of a computer, the IP of a server in Matlab and the IP of a Lopa mechanical arm demonstrator are set to be the same address, ports are set, and the Lopa mechanical arm and the IP of the Lopa mechanical arm are in the same network segment, so that socket communication between the Lopa mechanical arm and the Matlab in the computer can be established. After the communication is successful, the path information is sent to the Lopa stone mechanical arm, and the Lopa stone mechanical arm is made to move to the specified position.
A path planning simulation result diagram obtained by using the improved RRT algorithm in Matlab is shown in fig. 4, and a path planning process in an actual scene is shown in fig. 5, so that a Lopa mechanical arm can safely bypass 3 obstacles arranged in a scene and smoothly reach a specified position, and feasibility of the improved RRT algorithm is rapidly verified.
The present invention has been described in sufficient detail for clarity of disclosure and is not exhaustive of the prior art.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; it is obvious as a person skilled in the art to combine several aspects of the invention. And such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention. The technical contents not described in detail in the present invention are all known techniques.
Claims (10)
1. A rapid prototyping system for mechanical arm path planning is characterized in that: comprises a camera, a computer and a mechanical arm;
the camera is connected with the computer through a data line, the mechanical arm and the camera are installed out of hand in an eye-to-eye mode, and the mechanical arm and the computer are connected through a network cable and used for achieving communication between Matlab and the mechanical arm.
2. The robotic arm path planning rapid prototyping system of claim 1 wherein:
the camera adopts a ZED2 binocular camera, comprises a left camera and a right camera and is used for shooting scene pictures; the mechanical arm is provided with an external communication interface and can conveniently communicate with external equipment;
the software part of the computer is used for image processing and simulation of path planning algorithms.
3. The robotic arm path planning rapid prototyping system of claim 2 wherein: image processing, namely acquiring the positions of all obstacles in a working scene of the mechanical arm by using a visual method, and firstly, identifying and positioning all the obstacles by using any target detection algorithm; and then, realizing the conversion of the position of the obstacle by using a hand-eye calibration method. Under the condition of known obstacle information, a path planning algorithm is programmed and realized in Matlab, a feasible path is planned for the mechanical arm, and the mechanical arm moves to a specified position under the condition of not contacting with the obstacle.
4. The robotic arm path planning rapid prototyping system of claim 3 wherein: the path planning algorithm is an improved RRT algorithm, a three-point improvement strategy is provided on the basis of bidirectional expansion, the randomness of sampling points is reduced by using a random point preferred idea, the searching speed is accelerated by using a gravity adjustable step length strategy, and a path is optimized by using a path optimization strategy.
5. A rapid prototyping system for mechanical arm path planning is characterized in that: the following steps are carried out in the following manner,
step 1: calibrating a binocular camera, and controlling the binocular camera to shoot a scene picture by using a computer after acquiring parameters of the camera;
and 2, step: identifying and positioning the obstacles in the scene by using a target detection algorithm;
and step 3: the position of the barrier is converted by using a hand-eye calibration method;
and 4, step 4: compiling a script file in Matlab to realize a path planning algorithm by combining the barrier information obtained in the step 3 to obtain a feasible path;
and 5: establishing communication between the mechanical arm and Matlab in the computer, and sending path information to the mechanical arm;
and 6: and the mechanical arm moves to a specified position according to the received path information.
6. The robotic arm path planning rapid prototyping system of claim 5 wherein: in step 1, firstly, the binocular camera is calibrated by using the zhang's calibration method: shooting pictures of the checkerboard calibration plates at different angles by using a binocular camera, inputting the pictures into Matlab, and acquiring parameters of the binocular camera by using a camera calibration tool box; secondly, a picture of the working scene of the mechanical arm is shot by a binocular camera.
7. The robotic arm path planning rapid prototyping system of claim 5 wherein: in step 2, firstly, a data set is made by label image software; then, training the data set by using a Faster R-CNN algorithm to obtain a model of the obstacle; secondly, transmitting the picture of the mechanical arm working scene to a computer, detecting the obstacle in the mechanical arm working scene by using the trained model to obtain the pixel coordinate of the obstacle, and acquiring the depth value from the camera to the obstacle by using a binocular camera; and finally, calculating to obtain the three-dimensional coordinates of the obstacle through coordinate transformation.
8. The robotic arm path planning rapid prototyping system of claim 5 wherein: in step 3, the positions of the mechanical arm and the binocular camera are determined by adopting a hand-eye calibration method with eyes outside the hand, the pose of the mechanical arm is changed for more than 10 times, pose data is recorded, external parameters of the camera are solved, a hand-eye transformation matrix is further solved, and the obstacle information is converted into a mechanical arm base coordinate system.
9. The robotic arm path planning rapid prototyping system of claim 5 wherein: in step 4, firstly, combining the barrier information obtained in step 3, compiling a script file in Matlab to realize an improved RRT algorithm, and firstly adopting bidirectional expansion; then, reducing the randomness of the sampling points by using a random point preferred idea, accelerating the searching speed by using a gravity adjustable step length strategy, and optimizing a path by using a path optimization strategy; finally, obtaining a feasible path meeting the set conditions;
firstly, setting a probability threshold bias, when the random number is greater than the bias, simultaneously generating two random points to be selected by using a random function, calculating the distance between the two random points to be selected and a target point, and then determining a node closer to the target point as a final random point; when the random number is smaller than the bias, the target point is still set as a random point;
the gravity adjustable step length strategy is characterized in that a gravity idea is added into an algorithm, and the step length is changed by adaptively adjusting the value of a gravity coefficient according to whether a mechanical arm meets an obstacle in the advancing process so as to achieve the purpose of rapidly avoiding the obstacle: when the random tree is expanded without encountering an obstacle, expanding the random tree while keeping the initial value unchanged; and when the random tree meets an obstacle in the expansion process, reducing the value of the random tree, further reducing the step length in the direction of the gravitation, circularly obtaining a new node again, if the random tree still contacts the obstacle, continuously reducing the value of the new node, and when the value of the new node is reduced to 0, completely determining the expansion of the new node by the random point, and finally enabling the new node to successfully avoid the obstacle.
The path optimization strategy is to smooth the initial path with a quadratic B-spline curve.
In the improved RRT algorithm process, firstly, two random trees are initialized, and a random point is determined in the joint space of a mechanical arm by using a random point preferred strategy; then, finding the closest point in the first tree to the random point, obtaining a new node by using a gravity adjustable step length strategy, calculating the Cartesian position of the new node, performing collision detection, if no collision exists, adding the new node into the random tree, judging whether the two trees are connected, if no connection exists, exchanging the two trees for expansion, if the connection is successful, outputting a path, smoothing the initial path by using a quadratic B spline curve, and finally obtaining the smoothed path.
10. The robotic arm path planning rapid prototyping system of claim 5 wherein:
in step 5: firstly, after path information is obtained, taking Matlab as a server side and taking a mechanical arm as a client side; then, setting the IP of the computer, the IP of a server in Matlab and the IP in a mechanical arm demonstrator as the same address, setting a port, and establishing socket communication between the mechanical arm and the Matlab in the computer when the IP of the computer and the IP of the mechanical arm are in the same network segment;
in step 6, after the communication is successful, the path information is sent to the mechanical arm, and the mechanical arm is made to move to the designated position.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210582771.0A CN115107021A (en) | 2022-05-26 | 2022-05-26 | Mechanical arm path planning rapid prototyping system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210582771.0A CN115107021A (en) | 2022-05-26 | 2022-05-26 | Mechanical arm path planning rapid prototyping system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115107021A true CN115107021A (en) | 2022-09-27 |
Family
ID=83327198
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210582771.0A Pending CN115107021A (en) | 2022-05-26 | 2022-05-26 | Mechanical arm path planning rapid prototyping system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115107021A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI829561B (en) * | 2023-03-20 | 2024-01-11 | 國立陽明交通大學 | Method and system for path planning of robot arm in dynamic environment |
-
2022
- 2022-05-26 CN CN202210582771.0A patent/CN115107021A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI829561B (en) * | 2023-03-20 | 2024-01-11 | 國立陽明交通大學 | Method and system for path planning of robot arm in dynamic environment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109960880B (en) | Industrial robot obstacle avoidance path planning method based on machine learning | |
CN110769985B (en) | Viewpoint-invariant visual servoing of robotic end effectors using recurrent neural networks | |
CN112677153B (en) | Improved RRT algorithm and industrial robot path obstacle avoidance planning method | |
CN105676642B (en) | A kind of six-DOF robot station layout and run duration cooperative optimization method | |
CN103170973B (en) | Man-machine cooperation device and method based on Kinect video camera | |
CN110986953B (en) | Path planning method, robot and computer readable storage medium | |
CN109986560B (en) | Mechanical arm self-adaptive grabbing method for multiple target types | |
CN109976347B (en) | Visual servo path planning method based on rapid expansion random tree and potential field method | |
CN111844007B (en) | Obstacle avoidance path planning method and device for mechanical arm of pollination robot | |
CN112847336B (en) | Action learning method and device, storage medium and electronic equipment | |
CN113211447B (en) | Mechanical arm real-time perception planning method and system based on bidirectional RRT algorithm | |
CN115107021A (en) | Mechanical arm path planning rapid prototyping system | |
CN111152227A (en) | Mechanical arm control method based on guided DQN control | |
CN114347008A (en) | Industrial robot-based method and device for grabbing workpieces out of order and intelligent terminal | |
CN115958590A (en) | RRT-based mechanical arm deep frame obstacle avoidance motion planning method and device | |
CN115781685A (en) | High-precision mechanical arm control method and system based on reinforcement learning | |
CN114536351B (en) | Redundant double-arm robot teaching method and device, electronic equipment and system | |
CN116690557A (en) | Method and device for controlling humanoid three-dimensional scanning motion based on point cloud | |
JP2021529674A (en) | Systems and methods for natural tasks in one or more robot cross-reference paragraphs | |
CN114029940B (en) | Motion path planning method, device, equipment, medium and mechanical arm | |
WO2023051706A1 (en) | Gripping control method and apparatus, and server, device, program and medium | |
Cazzato et al. | Real-time human head imitation for humanoid robots | |
Shu et al. | Research on optimal path sampling algorithm of manipulator based on potential function | |
Regal et al. | Using Single Demonstrations to Define Autonomous Manipulation Contact Tasks in Unstructured Environments via Object Affordances | |
Zhou et al. | An Adaptive Path Planning Approach for Digital Twin-Enabled Robot Arm Based on Inverse Kinematics and Deep Reinforcement Learning |
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 |