CN113246143A - Mechanical arm dynamic obstacle avoidance trajectory planning method and device - Google Patents
Mechanical arm dynamic obstacle avoidance trajectory planning method and device Download PDFInfo
- Publication number
- CN113246143A CN113246143A CN202110712139.9A CN202110712139A CN113246143A CN 113246143 A CN113246143 A CN 113246143A CN 202110712139 A CN202110712139 A CN 202110712139A CN 113246143 A CN113246143 A CN 113246143A
- Authority
- CN
- China
- Prior art keywords
- mechanical arm
- dimensional model
- virtual scene
- target
- track
- 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 title claims abstract description 45
- 238000001514 detection method Methods 0.000 claims abstract description 64
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 238000001914 filtration Methods 0.000 claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 230000007704 transition Effects 0.000 claims description 35
- 230000001133 acceleration Effects 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 18
- 230000011218 segmentation Effects 0.000 claims description 14
- 230000010354 integration Effects 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000013519 translation Methods 0.000 claims description 9
- 239000002131 composite material Substances 0.000 description 8
- 230000007613 environmental effect Effects 0.000 description 8
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012360 testing method Methods 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
- 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
-
- 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
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
Abstract
The invention provides a method and a device for planning a dynamic obstacle avoidance track of a mechanical arm, wherein the method comprises the following steps: building a virtual scene corresponding to the actual scene and unified with the actual scene based on the actual scene where the mechanical arm is located; determining a position of the robotic arm in the virtual scene; calculating to obtain a candidate motion track of the mechanical arm based on the virtual scene and the position of the mechanical arm in the virtual scene by combining a collision detection algorithm; automatically segmenting the path corresponding to the candidate motion track to obtain a plurality of sections of smooth paths through filtering, wherein the mechanical arm does not collide when moving based on the plurality of sections of smooth paths; and performing integrated calculation on the multiple sections of smooth paths to obtain a continuous collision-free executable track with the shortest execution time. The planning method for the dynamic obstacle avoidance track of the mechanical arm can automatically determine the executable track of the mechanical arm, so that the mechanical arm does not collide with the environment when moving based on the executable track, and the movement efficiency is high.
Description
Technical Field
The embodiment of the invention relates to the technical field of computers, in particular to a method and a device for planning a dynamic obstacle avoidance track of a mechanical arm.
Background
In the application field of mechanical arms developed at a high speed, most of the mechanical arms are still used in the traditional modes of teaching, adding intermediate points and the like. However, such approaches have become increasingly inadequate for more complex and diversified applications, particularly in hybrid robots that move AGVs with robotic arms. When such a composite robot is in practical application, for example, in a scene of picking articles on a shelf, devices of the robot, the shelf in a running environment, material frames on a bearing platform, goods on a clamping jaw of the robot, and the like are all environmental factors which are easy to collide with the operation of a mechanical arm.
For the above situation, if the conventional method is used, the above problems obviously cannot be solved, and especially in the case of a constantly changing environment, the collision between the robot arm and the environment cannot be completely avoided by determining the moving track of the robot arm only by using the teaching and the intermediate point.
Disclosure of Invention
The invention provides a planning method for a dynamic obstacle avoidance track of a mechanical arm, which can automatically determine the executable track of the mechanical arm, so that the mechanical arm does not collide with the environment when moving based on the executable track and has high movement efficiency, and an electronic device applying the method.
In order to solve the technical problem, an embodiment of the present invention provides a method for planning a dynamic obstacle avoidance trajectory of a robot arm, including:
building a virtual scene corresponding to the actual scene and unified with the actual scene based on the actual scene where the mechanical arm is located;
determining a position of the robotic arm in the virtual scene;
calculating to obtain a candidate motion track of the mechanical arm based on the virtual scene and the position of the mechanical arm in the virtual scene by combining a collision detection algorithm;
automatically segmenting the path corresponding to the candidate motion track to obtain a plurality of sections of smooth paths through filtering, wherein the mechanical arm does not collide when moving based on the plurality of sections of smooth paths;
and performing integrated calculation on the multiple sections of smooth paths to obtain a continuous collision-free executable track with the shortest execution time.
Optionally, the building of a virtual scene corresponding to the actual scene and unified with the actual scene based on the actual scene where the mechanical arm is located includes:
building the virtual scene based on the actual scene;
acquiring point cloud information of the actual scene;
converting the point cloud information to a coordinate system corresponding to the mechanical arm;
determining the position information of the target object in the actual scene based on the point cloud information after the coordinate system is converted, wherein the position information is the position information of the target object relative to the mechanical arm under the coordinate system corresponding to the mechanical arm;
and adjusting the position of the target object relative to the mechanical arm in the virtual scene based on the position information of the target object, so that the virtual scene is corresponding to the actual scene uniformly.
Optionally, the point cloud information is obtained by shooting the actual scene through a 3D camera,
the converting the point cloud information to a coordinate system corresponding to the mechanical arm comprises the following steps:
constructing a rotational translation matrix between a coordinate system corresponding to the 3D camera and a coordinate system corresponding to the mechanical arm;
and converting point cloud information obtained by shooting through the 3D camera to a coordinate system corresponding to the mechanical arm based on the rotation and translation matrix.
Optionally, the calculating, based on the virtual scene and the position of the mechanical arm in the virtual scene, and by combining a collision detection algorithm, a candidate motion trajectory of the mechanical arm includes:
determining a position of a three-dimensional model of the robotic arm in the virtual scene;
performing first collision detection on at least a three-dimensional model of the mechanical arm and three-dimensional models of objects located around the mechanical arm in the virtual scene to determine candidate three-dimensional models, wherein the candidate three-dimensional models comprise target three-dimensional models which collide with the three-dimensional model of the mechanical arm;
performing second collision detection on at least the candidate three-dimensional model and the three-dimensional model of the mechanical arm to obtain the target three-dimensional model through filtering, wherein the precision of the second collision detection is higher than that of the first collision detection;
and planning to obtain the candidate motion trail based on the position of the target three-dimensional model in the virtual scene and the position of the three-dimensional model which is not collided with the three-dimensional model of the mechanical arm.
Optionally, the performing at least a first collision detection on the three-dimensional model of the mechanical arm in the virtual scene and the three-dimensional model of the object located around the mechanical arm to determine a candidate three-dimensional model includes:
and at least carrying out bounding box detection on the three-dimensional model of the mechanical arm in the virtual scene and the three-dimensional model of the object around the mechanical arm so as to determine the candidate three-dimensional model with overlapped bounding boxes.
Optionally, the performing at least second collision detection on the candidate three-dimensional model and the three-dimensional model of the mechanical arm to obtain the target three-dimensional model by filtering includes:
performing collision detection on at least the candidate three-dimensional model and a grid on the surface of the three-dimensional model of the mechanical arm to determine a target grid which is overlapped with the grid on the surface of the three-dimensional model of the mechanical arm;
and indicating the three-dimensional model in which the target grid is positioned as the target three-dimensional model.
Optionally, the automatically segmenting the path corresponding to the candidate motion trajectory to obtain multiple smooth paths through filtering includes:
determining a target starting point and a target end point when the mechanical arm moves in the path corresponding to the candidate motion track, wherein the target starting point and the target end point are related to an operation point set by the mechanical arm in an actual scene or are respectively the starting point and the end point of the path corresponding to the candidate motion track;
determining a plurality of transition points in a path between the target start point and target end point;
determining a pose of the robotic arm at the transition point;
judging whether the mechanical arm generates collision or not based on the posture of the mechanical arm at the transition point, wherein collision objects which collide with the mechanical arm comprise the mechanical arm and other objects in the virtual scene;
determining a target transition point based on the judgment result, wherein the target transition point indicates that the mechanical arm does not collide when being positioned at the target transition point;
and planning a path based on the target transition point to obtain the multi-section smooth path.
Optionally, the performing integrated calculation on the multiple segments of smooth paths to obtain a continuous collision-free executable trajectory with the shortest execution time includes:
setting a time stamp for each smooth path in the multiple smooth paths to determine the speed and acceleration of the mechanical arm when the mechanical arm moves along each smooth path;
performing spline fitting on the multiple smooth paths for multiple times;
and determining a spline curve, the position of each track point and the executable track of which the motion speed and the acceleration of each joint of the mechanical arm are within the constraint range based on the fitting result.
Optionally, the method further comprises:
processing the fitting result based on a spline difference method;
and determining the executable track based on the processed fitting result, so that the motion speed and the acceleration of the mechanical arm are matched when the mechanical arm moves to the connecting point corresponding to the multiple sections of smooth paths along the executable track.
The invention also provides an electronic device, comprising:
the building module is used for building a virtual scene which corresponds to the actual scene and is unified with the actual scene according to the actual scene where the mechanical arm is located;
a determination module for determining a position of the robotic arm in the virtual scene;
the computing module is used for computing candidate motion tracks of the mechanical arm according to the virtual scene and the position of the mechanical arm in the virtual scene by combining a collision detection algorithm;
the segmentation processing module is used for carrying out segmentation processing on the path corresponding to the candidate motion track so as to filter and obtain multiple smooth paths, and no collision occurs when the mechanical arm moves on the basis of the multiple smooth paths;
and the integration module is used for performing integration calculation on the multiple sections of smooth paths to obtain a continuous collision-free executable track with the shortest execution time.
Based on the disclosure of the embodiment, the method has the advantages that the three-dimensional virtual scene corresponding to the actual scene is built, the environmental factors in the virtual scene are added into the collision detection of the mechanical arm trajectory planning, the obtained candidate motion trajectories are subjected to segmentation processing, and finally the obtained multiple smooth trajectories are subjected to integrated calculation to determine the collision-free executable trajectory with the shortest execution time. As the information of each type of obstacle in the operation space of the mechanical arm is led into the trajectory planning algorithm in the process of determining the executable trajectory, the calculated executable trajectory can effectively avoid static and dynamic obstacles of each type, collision is avoided, and the efficiency and the safety of the mechanical arm in grabbing tasks in a complex environment are obviously improved. In addition, the method of the invention obtains the executable track with smooth path and shortest execution time by carrying out segmentation processing and integration on the candidate motion tracks, thereby overcoming the defects of overlong path, unsmooth path and overlong execution time in the conventional track planning of long paths under multiple complex obstacles.
Drawings
Fig. 1 is a flowchart of a method for planning a dynamic obstacle avoidance trajectory of a mechanical arm in an embodiment of the present invention.
Fig. 2 is a flowchart of a method for planning a dynamic obstacle avoidance trajectory of a robot arm according to another embodiment of the present invention.
Fig. 3 is a flowchart of a method for planning a dynamic obstacle avoidance trajectory of a robot arm according to another embodiment of the present invention.
Fig. 4 is a flowchart of a method for planning a dynamic obstacle avoidance trajectory of a robot arm according to another embodiment of the present invention.
Fig. 5 is a flowchart of a method for planning a dynamic obstacle avoidance trajectory of a robot arm according to another embodiment of the present invention.
Fig. 6 is a flowchart of an actual application of the mechanical arm dynamic obstacle avoidance trajectory planning method in the embodiment of the present invention.
Fig. 7 is a block diagram of an electronic device according to an embodiment of the invention.
Detailed Description
The following detailed description of specific embodiments of the present invention is provided in connection with the accompanying drawings, which are not intended to limit the invention.
It will be understood that various modifications may be made to the embodiments disclosed herein. The following description is, therefore, not to be taken in a limiting sense, but is made merely as an exemplification of embodiments. Other modifications will occur to those skilled in the art within the scope and spirit of the disclosure.
The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the disclosure and, together with a general description of the disclosure given above, and the detailed description of the embodiments given below, serve to explain the principles of the disclosure.
These and other characteristics of the invention will become apparent from the following description of a preferred form of embodiment, given as a non-limiting example, with reference to the accompanying drawings.
It should also be understood that, although the invention has been described with reference to some specific examples, a person of skill in the art shall certainly be able to achieve many other equivalent forms of the invention, having the characteristics as set forth in the claims and hence all coming within the field of protection defined thereby.
The above and other aspects, features and advantages of the present disclosure will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.
Specific embodiments of the present disclosure are described hereinafter with reference to the accompanying drawings; however, it is to be understood that the disclosed embodiments are merely examples of the disclosure that may be embodied in various forms. Well-known and/or repeated functions and structures have not been described in detail so as not to obscure the present disclosure with unnecessary or unnecessary detail. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present disclosure in virtually any appropriately detailed structure.
The specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," which may each refer to one or more of the same or different embodiments in accordance with the disclosure.
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
As shown in fig. 1, an embodiment of the present invention discloses a method for planning a dynamic obstacle avoidance trajectory of a robot arm, including:
s100, building a virtual scene which corresponds to the actual scene and is unified based on the actual scene where the mechanical arm is located;
s200, determining the position of the mechanical arm in a virtual scene;
s300, calculating to obtain a candidate motion track of the mechanical arm based on the virtual scene and the position of the mechanical arm in the virtual scene by combining a collision detection algorithm;
s400, automatically segmenting the path corresponding to the candidate motion track to obtain a plurality of sections of smooth paths through filtering, wherein the mechanical arm does not collide when moving based on the plurality of sections of smooth paths;
and S500, performing integrated calculation on the multiple sections of smooth paths to obtain a continuous collision-free executable track with the shortest execution time.
For example, a virtual scene is built based on an actual scene where the mechanical arm is located, and particularly static obstacles in the actual scene, such as a body part of the robot except the mechanical arm, a shelf, a stand column and the like in the environment, and dynamic obstacles, such as goods grabbed by a clamping jaw at the tail end of the mechanical arm, can be built in a three-dimensional model manner when the mechanical arm is mounted on the composite robot, so that the virtual scene unified with the actual scene is formed. Then, the position of the mechanical arm in the virtual scene is determined, or a starting point and an end point of the mechanical arm required to move in the actual scene are determined at the same time, and a corresponding position is determined in the virtual scene based on the starting point and the end point, which is not necessarily required, for example, when the mechanical arm moves circularly, or a trajectory required to be determined is the maximum trajectory that the mechanical arm can run in the actual scene, the step does not need to be determined. Further, after the position of the mechanical arm in the virtual scene is determined, each object/environment factor in the virtual scene is collided with the mechanical arm based on the virtual scene, the position of the mechanical arm and a collision detection algorithm to determine a candidate motion track, wherein the candidate motion track indicates that the mechanical arm does not collide with objects except for the mechanical arm in the virtual scene when moving based on the track, but the mechanical arm cannot be ensured to collide with the mechanical arm itself or the composite robot to which the mechanical arm belongs. That is, the candidate motion trajectory determined in this step does not belong to a smooth path and needs to be adjusted. After the candidate path is determined, the path corresponding to the candidate motion track is automatically segmented to obtain multiple smooth paths through filtering, no collision occurs when the mechanical arm moves based on the multiple smooth paths, namely, when the mechanical arm moves based on the multiple smooth paths, the mechanical arm cannot collide with an external object in a virtual scene, or a robot to which the mechanical arm belongs, or a joint of the mechanical arm and the joint, and the motion track is smooth. And finally, integrating the multiple sections of smooth paths by using a trajectory integration algorithm to form a continuous non-stop collision-free executable trajectory with the shortest execution time, namely the optimal motion trajectory of the mechanical arm.
Based on the above, the method has the advantages that the three-dimensional virtual scene corresponding to the actual scene is built, the environmental factors in the virtual scene are added into the collision detection of the mechanical arm trajectory planning, the obtained candidate motion trajectories are segmented, and finally the obtained multiple smooth trajectories are integrated and calculated to determine the collision-free executable trajectory with the shortest execution time. As the information of each type of obstacle in the operation space of the mechanical arm is led into the trajectory planning algorithm in the process of determining the executable trajectory, the calculated executable trajectory can effectively avoid static and dynamic obstacles of each type, collision is avoided, and the efficiency and the safety of the mechanical arm in grabbing tasks in a complex environment are obviously improved. In addition, the method of the invention obtains the executable track with smooth path and shortest execution time by carrying out segmentation processing and integration on the candidate motion tracks, thereby overcoming the defects of overlong path, unsmooth path and overlong execution time in the conventional track planning of long paths under multiple complex obstacles.
Specifically, as shown in fig. 2, in this embodiment, a virtual scene corresponding to the actual scene and unified based on the actual scene where the mechanical arm is located is built, including:
s101, building a virtual scene based on an actual scene;
s102, point cloud information of an actual scene is obtained;
s103, converting the point cloud information into a coordinate system corresponding to the mechanical arm;
s104, determining the position information of the target object in the actual scene based on the point cloud information after the coordinate system is converted, wherein the position information is the position information of the target object relative to the mechanical arm under the coordinate system corresponding to the mechanical arm;
and S105, adjusting the position of the target object in the virtual scene relative to the mechanical arm based on the position information of the target object so as to enable the virtual scene and the actual scene to be correspondingly unified.
Wherein, the point cloud information in the embodiment is obtained by shooting an actual scene through a 3D camera,
s103, converting the point cloud information into a coordinate system corresponding to the mechanical arm, wherein the step comprises the following steps:
s1031, constructing a rotation and translation matrix between a coordinate system corresponding to the 3D camera and a coordinate system corresponding to the mechanical arm;
and S1032, converting the point cloud information obtained by shooting through the 3D camera into a coordinate system corresponding to the mechanical arm based on the rotation and translation matrix.
For example, in this embodiment, a virtual scene corresponding to a field environment 1:1 needs to be built based on an actual scene of the mechanical arm work, and the relative position of the mechanical arm and the actual environment is well positioned. Taking the composite robot as an example, after the composite robot with the mechanical arm reaches a designated position in an actual scene, in order to keep the actual scene consistent with a virtual scene, as shown in fig. 6, the composite robot can be implemented in actual application by the following steps:
1) establishing a three-dimensional model of the surrounding environment where the mechanical arm is located, and establishing objects/environment factors which are possibly interfered and collided with the mechanical arm in a scene in a virtual scene in a ratio of 1: 1;
2) calibrating a coordinate system of a 3D camera and a mechanical arm base/a composite robot base, acquiring point cloud information of an actual scene by using the 3D camera, converting the point cloud information acquired by the 3D camera into the coordinate system of the mechanical arm base, specifically calculating a rotation and translation matrix between the coordinate system of the 3D camera and the coordinate system of the mechanical arm base in advance, and converting the point cloud information acquired by the 3D camera into the coordinate system of the mechanical arm base based on the matrix;
3) based on point cloud information which is acquired by a 3D camera and reflects an actual scene, various environmental factors are divided and identified, such as objects/environmental factors in an environment, such as cabinets, columns and the like, are respectively identified, the position information of the objects/environmental factors in the actual scene is determined, then the relative positions of the environmental factors in a virtual environment relative to a mechanical arm base coordinate system are adjusted based on the position information in the actual scene, and the built virtual scene is ensured to be corresponding and uniform with the actual scene.
Further, as shown in fig. 3, in this embodiment, calculating a candidate motion trajectory of the mechanical arm based on the virtual scene and the position of the mechanical arm in the virtual scene by combining a collision detection algorithm includes:
s301, determining the position of the three-dimensional model of the mechanical arm in a virtual scene;
s302, performing first collision detection on at least a three-dimensional model of a mechanical arm and three-dimensional models of objects around the mechanical arm in a virtual scene to determine a candidate three-dimensional model, wherein the candidate three-dimensional model comprises a target three-dimensional model which collides with the three-dimensional model of the mechanical arm;
s303, performing second collision detection on the candidate three-dimensional model and the three-dimensional model of the mechanical arm at least to obtain a target three-dimensional model through filtering, wherein the precision of the second collision detection is higher than that of the first collision detection;
and S304, planning to obtain a candidate motion track based on the position of the target three-dimensional model in the virtual scene and the position of the three-dimensional model which is not collided with the three-dimensional model of the mechanical arm.
Optionally, in this embodiment, performing a first collision detection on at least a three-dimensional model of a mechanical arm in a virtual scene and a three-dimensional model of an object located around the mechanical arm to determine a candidate three-dimensional model includes:
s3031, bounding box detection is carried out on at least the three-dimensional model of the mechanical arm in the virtual scene and the three-dimensional model of the object around the mechanical arm so as to determine candidate three-dimensional models with overlapped bounding boxes.
Performing second collision detection on at least the candidate three-dimensional model and the three-dimensional model of the mechanical arm to obtain a target three-dimensional model through filtering, wherein the second collision detection comprises the following steps:
s3041, at least carrying out collision detection on the candidate three-dimensional model and the grid on the surface of the three-dimensional model of the mechanical arm so as to determine a target grid overlapped with the grid on the surface of the three-dimensional model of the mechanical arm;
and indicating the three-dimensional model where the target grid is located as the target three-dimensional model.
For example, in this embodiment, collision detection is performed on the mechanical arm and other environmental factors at each track point on the path to determine whether the current position can move, if no collision occurs, it indicates that the position point can move, and the position point should be retained temporarily, and if a collision occurs, it indicates that the position point cannot move, and the position point needs to be discarded. Continuing with FIG. 6, specifically:
firstly, performing first collision detection on all or at least three-dimensional models around the mechanical arm in the virtual scene, wherein the first collision detection can be specifically selected as bounding box detection and can also be performed by other algorithms of the same type. The bounding box detection method is adopted as a rough detection method in the embodiment, so that intersection test detection can be rapidly executed on a virtual scene. When the method is applied, an axisymmetric bounding box (AABB type) can be selected for detection. However, the accuracy of bounding box detection is slightly low, so that after the bounding box detection is finished, if the two bounding boxes are found to be overlapped, the collision between the two objects/three-dimensional models cannot be definitely determined, because the shapes of the objects/three-dimensional models are irregular, even if the objects/three-dimensional models are overlapped, the two objects can be relative to each other, and the collision between the two objects cannot be determined. But when there is no overlap between two bounding boxes, it is certain that there is no collision between objects, so that a large number of disjoint elements can be excluded.
And secondly, detecting collision among the elements. After determining the bounding boxes that intersect each other in the first step, it is not possible to determine whether a collision between the objects/three-dimensional models actually occurs, so that the bounding boxes that have caused the collision are subjected to a further, more detailed second collision detection. In the embodiment, the second collision detection is realized by further collision detection on the elements in the object/three-dimensional model. When the system is applied, the grid of the surface of the three-dimensional model is used as a collision detection element, and then all the grids on the surface of the three-dimensional model respectively positioned in different bounding boxes are subjected to collision detection so as to determine whether any two grids are overlapped, namely whether collision occurs.
And if the collision exists between the primitives, determining that the collision occurs between the objects of the primitives, otherwise, determining that the collision does not occur between the two objects, and using the collision as a candidate track point of the track plan.
After all the candidate track points are determined, a candidate motion track is formed based on the candidate track points, and when the mechanical arm moves based on the candidate motion track, the mechanical arm does not collide with surrounding objects. That is, in the present embodiment, the coarse-grained bounding box collision detection and the fine-grained triangular patch (primitive) collision detection are performed in sequence, and it is determined that a collision occurs between the robot arm and another object only when a collision occurs in the bounding box and a collision also occurs in the triangular patch.
As shown in fig. 4, in this embodiment, automatically performing segmentation processing on the path corresponding to the candidate motion trajectory to obtain multiple smooth paths through filtering includes:
s401, determining a target starting point and a target end point when the mechanical arm moves in a path corresponding to the candidate motion track, wherein the target starting point and the target end point are related to an operation point set by the mechanical arm in an actual scene or are respectively a starting point and an end point of the path corresponding to the candidate motion track;
s402, determining a plurality of transition points in a path between a target starting point and a target end point;
s403, determining the posture of the mechanical arm at the transition point;
s404, judging whether the mechanical arm collides based on the posture of the mechanical arm at the transition point, wherein the collision objects colliding with the mechanical arm comprise the mechanical arm and other objects in the virtual scene;
s405, determining a target transition point based on the judgment result, wherein the target transition point indicates that the mechanical arm does not collide when being positioned at the target transition point;
and S406, planning the path based on the target transition point to obtain a multi-section smooth path.
For example, a target starting point and a target end point when the mechanical arm moves are determined in the path corresponding to the candidate motion trajectory, where the target starting point and the target end point are related to an operation point set by the mechanical arm in an actual scene, such as an operation point manually set by the mechanical arm when the mechanical arm is actually used, the mechanical arm needs to reciprocate between the set operation points, and the like, or the system directly defaults that the two points are respectively a starting point and an end point of the path corresponding to the candidate motion trajectory, and the method is not particularly determined. In practical application, a plurality of obstacles may be experienced from a target starting point to a target end point executed by a mechanical arm, a path is also relatively long, and in order to quickly calculate a collision-free executable trajectory from the starting point to the end point, and simultaneously ensure the quality of the path, and achieve the shortest optimal path as much as possible, the system performs automatic segmentation processing on the path from the target starting point to the target end point, specifically comprising:
firstly, uniformly finding out transition points from corresponding paths according to the length from a target starting point to a target end point;
secondly, solving the form of the mechanical arm at a transition point, including the joint state, in a robot inverse solution mode;
thirdly, judging whether the mechanical arm collides with the self structure or the composite robot where the mechanical arm is located or not, even with surrounding objects when the mechanical arm is at a transition point, if so, readjusting and searching for the transition point meeting the requirement, wherein the transition point meeting the requirement refers to a position point where the mechanical arm cannot generate any collision when the mechanical arm is at the transition point;
and fourthly, carrying out segmentation processing on the candidate motion trail, and specifically solving each segmented path through an RRT (fast search random tree) algorithm to obtain a multi-segment smooth path.
Through the four steps, the system can solve the collision-free path from the target starting point to the target end point, the quality of the path can be ensured to a great extent, and the problem of solving the edge angle path or the unsmooth path of the long path is avoided.
In the embodiment, on the premise of ensuring no collision, the candidate motion trajectory is subjected to uniform segmentation calculation to obtain multiple smooth paths, and each smooth path can better meet the requirement of the optimal trajectory, namely can be used for forming an executable trajectory and meets the requirement of the executable trajectory.
Further, as shown in fig. 5, in the present embodiment, the performing an integrated calculation on multiple smooth paths to obtain a continuous collision-free executable trajectory with the shortest execution time includes:
s501, setting a time stamp for each smooth path in the multiple smooth paths to determine the speed and the acceleration of the mechanical arm when the mechanical arm moves along each smooth path;
s502, performing spline fitting on the multi-section smooth path for multiple times;
and S503, determining the spline curve, the position of each track point, and the executable track of which the motion speed and the acceleration of each joint of the mechanical arm are within the constraint range based on the fitting result.
In addition, the method in this embodiment further includes:
s504, processing the fitting result based on a spline difference method;
and S505, determining an executable track based on the processed fitting result, so that the motion speed and the acceleration of the mechanical arm are matched when the mechanical arm moves to the connecting point of the corresponding multiple sections of smooth paths along the executable track.
For example, with continued reference to fig. 6, the collision-free paths found through the foregoing steps are all piecewise paths, but the velocities and accelerations of the start point and the end point in the piecewise paths are all zero. If the method is directly implemented on the mechanical arm, the phenomenon that the mechanical arm stops when moving to a transition point occurs, so that the motion track of the mechanical arm is a section of track and is discontinuous. In order to solve the problem, the system needs to connect multiple segments of smooth paths, and recalculate the speed, the acceleration, the timestamp and the like of each track point in the multiple segments of smooth paths to form a complete track which can ensure the smooth motion of the mechanical arm. In a practical production environment, the operation of the mechanical arm is more required to quickly complete the grabbing task, so the shortest execution time is used as the target of optimizing the connection subsection track in the embodiment, and the method comprises the following steps:
firstly, setting a time stamp for a track point/position point of each smooth path in a plurality of sections of smooth paths, so as to determine the speed and the acceleration of the mechanical arm when the mechanical arm moves along each smooth path and constrain the speed and the acceleration;
and secondly, carrying out multi-time spline fitting on the multi-section smooth path, and if carrying out repeated fitting on cubic splines, finding out the tracks meeting all preset constraints through repeated execution, namely executing the tracks. After the steps are completed, the system sets a timestamp for each track point, and the speed and the acceleration of each joint in the mechanical arm are determined, the determined track, the spline curve of the track point and the position of each track point are continuous, and the speed and the acceleration of each joint in the mechanical arm are in the corresponding constraint range when the track is executed.
Alternatively, in order to match the velocities and accelerations at the connection points of the multi-segment smooth path, the movements may be made at the positions of the penultimate and positive second points in the executable trajectory. For example, two additional points are added in the executable trajectory using a cubic spline difference algorithm to leave the executable trajectory unaffected. If no point is added, the speed of the mechanical arm is accelerated when the track is executed, and in practical application, the penultimate position point and the positive second position point of the executable track need to be checked for many times.
In this embodiment, the track integration processing is performed on the segmented short path through the above steps, and a path with the shortest execution time can be calculated, so that multiple smooth paths are connected into a whole executable track based on the path, and the path can be directly implemented on the mechanical arm.
As shown in fig. 7, another embodiment of the present invention also provides an electronic device, including:
the building module is used for building a virtual scene which corresponds to the actual scene and is unified with the actual scene according to the actual scene where the mechanical arm is located;
the determining module is used for determining the position of the mechanical arm in the virtual scene;
the computing module is used for computing candidate motion tracks of the mechanical arm according to the virtual scene and the position of the mechanical arm in the virtual scene by combining a collision detection algorithm;
the segmentation processing module is used for automatically segmenting the path corresponding to the candidate motion track so as to filter and obtain a plurality of smooth paths, and no collision occurs when the mechanical arm moves on the basis of the plurality of smooth paths;
and the integration module is used for performing integration calculation on the multiple sections of smooth paths to obtain a continuous collision-free executable track with the shortest execution time.
Optionally, the building module builds a virtual scene corresponding to the actual scene and unified with the actual scene based on the actual scene where the mechanical arm is located, and the building module includes:
building the virtual scene based on the actual scene;
acquiring point cloud information of the actual scene;
converting the point cloud information to a coordinate system corresponding to the mechanical arm;
determining the position information of the target object in the actual scene based on the point cloud information after the coordinate system is converted, wherein the position information is the position information of the target object relative to the mechanical arm under the coordinate system corresponding to the mechanical arm;
and adjusting the position of the target object relative to the mechanical arm in the virtual scene based on the position information of the target object, so that the virtual scene is corresponding to the actual scene uniformly.
Optionally, the point cloud information is obtained by shooting the actual scene through a 3D camera,
the building module converts the point cloud information to a coordinate system corresponding to the mechanical arm, and the building module comprises:
constructing a rotational translation matrix between a coordinate system corresponding to the 3D camera and a coordinate system corresponding to the mechanical arm;
and converting point cloud information obtained by shooting through the 3D camera to a coordinate system corresponding to the mechanical arm based on the rotation and translation matrix.
Optionally, the calculating module calculates, based on the virtual scene and the position of the mechanical arm in the virtual scene, and by combining a collision detection algorithm, a candidate motion trajectory of the mechanical arm, including:
determining a position of a three-dimensional model of the robotic arm in the virtual scene;
performing first collision detection on at least a three-dimensional model of the mechanical arm and three-dimensional models of objects located around the mechanical arm in the virtual scene to determine candidate three-dimensional models, wherein the candidate three-dimensional models comprise target three-dimensional models which collide with the three-dimensional model of the mechanical arm;
performing second collision detection on at least the candidate three-dimensional model and the three-dimensional model of the mechanical arm to obtain the target three-dimensional model through filtering, wherein the precision of the second collision detection is higher than that of the first collision detection;
and planning to obtain the candidate motion trail based on the position of the target three-dimensional model in the virtual scene and the position of the three-dimensional model which is not collided with the three-dimensional model of the mechanical arm.
Optionally, the performing at least a first collision detection on the three-dimensional model of the mechanical arm in the virtual scene and the three-dimensional model of the object located around the mechanical arm to determine a candidate three-dimensional model includes:
and at least carrying out bounding box detection on the three-dimensional model of the mechanical arm in the virtual scene and the three-dimensional model of the object around the mechanical arm so as to determine the candidate three-dimensional model with overlapped bounding boxes.
Optionally, the performing at least second collision detection on the candidate three-dimensional model and the three-dimensional model of the mechanical arm to obtain the target three-dimensional model by filtering includes:
performing collision detection on at least the candidate three-dimensional model and a grid on the surface of the three-dimensional model of the mechanical arm to determine a target grid which is overlapped with the grid on the surface of the three-dimensional model of the mechanical arm;
and indicating the three-dimensional model in which the target grid is positioned as the target three-dimensional model.
Optionally, the automatically segmenting the path corresponding to the candidate motion trajectory by the segmentation processing module to obtain a plurality of smooth paths through filtering includes:
determining a target starting point and a target end point when the mechanical arm moves in the path corresponding to the candidate motion track, wherein the target starting point and the target end point are related to an operation point set by the mechanical arm in an actual scene or are respectively the starting point and the end point of the path corresponding to the candidate motion track;
determining a plurality of transition points in a path between the target start point and target end point;
determining a pose of the robotic arm at the transition point;
judging whether the mechanical arm generates collision or not based on the posture of the mechanical arm at the transition point, wherein collision objects which collide with the mechanical arm comprise the mechanical arm and other objects in the virtual scene;
determining a target transition point based on the judgment result, wherein the target transition point indicates that the mechanical arm does not collide when being positioned at the target transition point;
and planning a path based on the target transition point to obtain the multi-section smooth path.
Optionally, the integrating module performs an integration calculation on the multiple segments of smooth paths to obtain a continuous collision-free executable trajectory with a shortest execution time, including:
setting a time stamp for each smooth path in the multiple smooth paths to determine the speed and acceleration of the mechanical arm when the mechanical arm moves along each smooth path;
performing spline fitting on the multiple smooth paths for multiple times;
and determining a spline curve, the position of each track point and the executable track of which the motion speed and the acceleration of each joint of the mechanical arm are within the constraint range based on the fitting result.
Optionally, the integration module is further configured to:
processing the fitting result based on a spline difference method;
and determining the executable track based on the processed fitting result, so that the motion speed and the acceleration of the mechanical arm are matched when the mechanical arm moves to the connecting point corresponding to the multiple sections of smooth paths along the executable track.
Further, another embodiment of the present invention further provides an electronic device, including:
one or more processors;
a memory configured to store one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors are enabled to implement the method for planning the dynamic obstacle avoidance trajectory of the mechanical arm.
An embodiment of the present application further provides a storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method for planning a dynamic obstacle avoidance trajectory of a mechanical arm as described above. It should be understood that each solution in this embodiment has a corresponding technical effect in the foregoing method embodiments, and details are not described here.
Further, embodiments of the present invention also provide a computer program product, tangibly stored on a computer-readable medium and comprising computer-executable instructions that, when executed, cause at least one processor to perform a processing method, such as the embodiments described above. It should be understood that each solution in this embodiment has a corresponding technical effect in the foregoing method embodiments, and details are not described here.
It should be noted that the computer storage media of the present application can be computer readable signal media or computer readable storage media or any combination of the two. The computer readable medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access storage media (RAM), a read-only storage media (ROM), an erasable programmable read-only storage media (EPROM or flash memory), an optical fiber, a portable compact disc read-only storage media (CD-ROM), an optical storage media piece, a magnetic storage media piece, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, antenna, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
It should be understood that although the present application has been described in terms of various embodiments, not every embodiment includes only a single embodiment, and such description is for clarity purposes only, and those skilled in the art will recognize that the embodiments described herein may be combined as suitable to form other embodiments, as will be appreciated by those skilled in the art.
The above embodiments are only exemplary embodiments of the present invention, and are not intended to limit the present invention, and the scope of the present invention is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present invention, and such modifications and equivalents should also be considered as falling within the scope of the present invention.
Claims (10)
1. A mechanical arm dynamic obstacle avoidance trajectory planning method is characterized by comprising the following steps:
building a virtual scene corresponding to the actual scene and unified with the actual scene based on the actual scene where the mechanical arm is located;
determining a position of the robotic arm in the virtual scene;
calculating to obtain a candidate motion track of the mechanical arm based on the virtual scene and the position of the mechanical arm in the virtual scene by combining a collision detection algorithm;
performing segmentation processing on the path corresponding to the candidate motion track to obtain a plurality of smooth paths through filtering, wherein the mechanical arm does not collide when moving based on the plurality of smooth paths;
and performing integrated calculation on the multiple sections of smooth paths to obtain a continuous collision-free executable track with the shortest execution time.
2. The method according to claim 1, wherein the building of the virtual scene corresponding to the actual scene based on the actual scene where the mechanical arm is located comprises:
building the virtual scene based on the actual scene;
acquiring point cloud information of the actual scene;
converting the point cloud information to a coordinate system corresponding to the mechanical arm;
determining the position information of the target object in the actual scene based on the point cloud information after the coordinate system is converted, wherein the position information is the position information of the target object relative to the mechanical arm under the coordinate system corresponding to the mechanical arm;
and adjusting the position of the target object relative to the mechanical arm in the virtual scene based on the position information of the target object, so that the virtual scene is corresponding to the actual scene uniformly.
3. The method of claim 2, wherein the point cloud information is obtained by a 3D camera capturing the actual scene,
the converting the point cloud information to a coordinate system corresponding to the mechanical arm comprises the following steps:
constructing a rotational translation matrix between a coordinate system corresponding to the 3D camera and a coordinate system corresponding to the mechanical arm;
and converting point cloud information obtained by shooting through the 3D camera to a coordinate system corresponding to the mechanical arm based on the rotation and translation matrix.
4. The method of claim 1, wherein calculating candidate motion trajectories of the mechanical arm based on the virtual scene, the position of the mechanical arm in the virtual scene, and a collision detection algorithm comprises:
determining a position of a three-dimensional model of the robotic arm in the virtual scene;
performing first collision detection on at least a three-dimensional model of the mechanical arm and three-dimensional models of objects located around the mechanical arm in the virtual scene to determine candidate three-dimensional models, wherein the candidate three-dimensional models comprise target three-dimensional models which collide with the three-dimensional model of the mechanical arm;
performing second collision detection on at least the candidate three-dimensional model and the three-dimensional model of the mechanical arm to obtain the target three-dimensional model through filtering, wherein the precision of the second collision detection is higher than that of the first collision detection;
and planning to obtain the candidate motion trail based on the position of the target three-dimensional model in the virtual scene and the position of the three-dimensional model which is not collided with the three-dimensional model of the mechanical arm.
5. The method of claim 4, wherein the performing at least a first collision detection on the three-dimensional model of the robotic arm and the three-dimensional models of objects located around the robotic arm in the virtual scene to determine candidate three-dimensional models comprises:
and at least carrying out bounding box detection on the three-dimensional model of the mechanical arm in the virtual scene and the three-dimensional model of the object around the mechanical arm so as to determine the candidate three-dimensional model with overlapped bounding boxes.
6. The method of claim 4, wherein the performing at least a second collision detection on the candidate three-dimensional model and the three-dimensional model of the robotic arm to filter the target three-dimensional model comprises:
performing collision detection on at least the candidate three-dimensional model and a grid on the surface of the three-dimensional model of the mechanical arm to determine a target grid which is overlapped with the grid on the surface of the three-dimensional model of the mechanical arm;
and indicating the three-dimensional model in which the target grid is positioned as the target three-dimensional model.
7. The method according to claim 1, wherein automatically segmenting the path corresponding to the candidate motion trajectory to obtain a multi-segment smooth path through filtering comprises:
determining a target starting point and a target end point when the mechanical arm moves in the path corresponding to the candidate motion track, wherein the target starting point and the target end point are related to an operation point set by the mechanical arm in an actual scene or are respectively the starting point and the end point of the path corresponding to the candidate motion track;
determining a plurality of transition points in a path between the target start point and target end point;
determining a pose of the robotic arm at the transition point;
judging whether the mechanical arm generates collision or not based on the posture of the mechanical arm at the transition point, wherein collision objects which collide with the mechanical arm comprise the mechanical arm and other objects in the virtual scene;
determining a target transition point based on the judgment result, wherein the target transition point indicates that the mechanical arm does not collide when being positioned at the target transition point;
and planning a path based on the target transition point to obtain the multi-section smooth path.
8. The method of claim 1, wherein the performing the integrated computation on the multiple smooth segments to obtain a continuous collision-free executable trajectory with the shortest execution time comprises:
setting a time stamp for each smooth path in the multiple smooth paths to determine the speed and acceleration of the mechanical arm when the mechanical arm moves along each smooth path;
performing spline fitting on the multiple smooth paths for multiple times;
and determining a spline curve, the position of each track point and the executable track of which the motion speed and the acceleration of each joint of the mechanical arm are within the constraint range based on the fitting result.
9. The method of claim 8, further comprising:
processing the fitting result based on a spline difference method;
and determining the executable track based on the processed fitting result, so that the motion speed and the acceleration of the mechanical arm are matched when the mechanical arm moves to the connecting point corresponding to the multiple sections of smooth paths along the executable track.
10. An electronic device, comprising:
the building module is used for building a virtual scene which corresponds to the actual scene and is unified with the actual scene according to the actual scene where the mechanical arm is located;
a determination module for determining a position of the robotic arm in the virtual scene;
the computing module is used for computing candidate motion tracks of the mechanical arm according to the virtual scene and the position of the mechanical arm in the virtual scene by combining a collision detection algorithm;
the segmentation processing module is used for carrying out segmentation processing on the path corresponding to the candidate motion track so as to filter and obtain multiple smooth paths, and no collision occurs when the mechanical arm moves on the basis of the multiple smooth paths;
and the integration module is used for performing integration calculation on the multiple sections of smooth paths to obtain a continuous collision-free executable track with the shortest execution time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110712139.9A CN113246143A (en) | 2021-06-25 | 2021-06-25 | Mechanical arm dynamic obstacle avoidance trajectory planning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110712139.9A CN113246143A (en) | 2021-06-25 | 2021-06-25 | Mechanical arm dynamic obstacle avoidance trajectory planning method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113246143A true CN113246143A (en) | 2021-08-13 |
Family
ID=77189727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110712139.9A Pending CN113246143A (en) | 2021-06-25 | 2021-06-25 | Mechanical arm dynamic obstacle avoidance trajectory planning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113246143A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113478492A (en) * | 2021-09-07 | 2021-10-08 | 成都博恩思医学机器人有限公司 | Method and system for avoiding collision of mechanical arms, robot and storage medium |
| CN113487655A (en) * | 2021-09-07 | 2021-10-08 | 成都博恩思医学机器人有限公司 | Indoor model generation method, electronic equipment and storage medium |
| CN114851211A (en) * | 2022-07-07 | 2022-08-05 | 国网瑞嘉(天津)智能机器人有限公司 | Method, device, server and storage medium for planning boom track |
| CN114986524A (en) * | 2022-08-08 | 2022-09-02 | 中国科学院自动化研究所 | Mechanical arm track planning method and device based on brain-computer interface and electronic equipment |
| CN117444989A (en) * | 2023-12-25 | 2024-01-26 | 常州微亿智造科技有限公司 | Collision detection method and device for path planning |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5056031A (en) * | 1988-11-12 | 1991-10-08 | Kabushiki Kaisha Toyota Chuo Kenyusho | Apparatus for detecting the collision of moving objects |
| CN107803831A (en) * | 2017-09-27 | 2018-03-16 | 杭州新松机器人自动化有限公司 | A kind of AOAAE bounding volume hierarchy (BVH)s collision checking method |
| CN107980109A (en) * | 2017-01-04 | 2018-05-01 | 深圳配天智能技术研究院有限公司 | Robot motion's method for planning track and relevant apparatus |
| CN110340890A (en) * | 2019-06-27 | 2019-10-18 | 北京控制工程研究所 | A kind of space manipulator overall situation is without touching Trajectory Planning System |
| CN111002308A (en) * | 2019-12-05 | 2020-04-14 | 南京理工大学 | Industrial mechanical arm path planning method based on segmented multistage polynomial interpolation |
| CN111504328A (en) * | 2020-05-22 | 2020-08-07 | 梅卡曼德（北京）机器人科技有限公司 | Robot motion planning method, path planning method, grabbing method and device |
| CN111515503A (en) * | 2020-04-30 | 2020-08-11 | 华东理工大学 | Non-collision path planning method for arc welding robot |
| CN112356033A (en) * | 2020-11-09 | 2021-02-12 | 中国矿业大学 | Mechanical arm path planning method integrating low-difference sequence and RRT algorithm |
| CN112549016A (en) * | 2020-10-21 | 2021-03-26 | 西安工程大学 | Mechanical arm motion planning method |
| CN112659126A (en) * | 2020-12-23 | 2021-04-16 | 广东工业大学 | Industrial robot track segment transition method based on non-uniform B-spline curve |
| CN113001551A (en) * | 2021-03-18 | 2021-06-22 | 青岛九维华盾科技研究院有限公司 | Fast collision detection method based on octree structure segmentation |
-
2021
- 2021-06-25 CN CN202110712139.9A patent/CN113246143A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5056031A (en) * | 1988-11-12 | 1991-10-08 | Kabushiki Kaisha Toyota Chuo Kenyusho | Apparatus for detecting the collision of moving objects |
| CN107980109A (en) * | 2017-01-04 | 2018-05-01 | 深圳配天智能技术研究院有限公司 | Robot motion's method for planning track and relevant apparatus |
| CN107803831A (en) * | 2017-09-27 | 2018-03-16 | 杭州新松机器人自动化有限公司 | A kind of AOAAE bounding volume hierarchy (BVH)s collision checking method |
| CN110340890A (en) * | 2019-06-27 | 2019-10-18 | 北京控制工程研究所 | A kind of space manipulator overall situation is without touching Trajectory Planning System |
| CN111002308A (en) * | 2019-12-05 | 2020-04-14 | 南京理工大学 | Industrial mechanical arm path planning method based on segmented multistage polynomial interpolation |
| CN111515503A (en) * | 2020-04-30 | 2020-08-11 | 华东理工大学 | Non-collision path planning method for arc welding robot |
| CN111504328A (en) * | 2020-05-22 | 2020-08-07 | 梅卡曼德（北京）机器人科技有限公司 | Robot motion planning method, path planning method, grabbing method and device |
| CN112549016A (en) * | 2020-10-21 | 2021-03-26 | 西安工程大学 | Mechanical arm motion planning method |
| CN112356033A (en) * | 2020-11-09 | 2021-02-12 | 中国矿业大学 | Mechanical arm path planning method integrating low-difference sequence and RRT algorithm |
| CN112659126A (en) * | 2020-12-23 | 2021-04-16 | 广东工业大学 | Industrial robot track segment transition method based on non-uniform B-spline curve |
| CN113001551A (en) * | 2021-03-18 | 2021-06-22 | 青岛九维华盾科技研究院有限公司 | Fast collision detection method based on octree structure segmentation |
Non-Patent Citations (1)
| Title |
|---|
| 刘宇轩: "工业机器人虚拟仿真中混合层次包围盒碰撞检测技术的研究与应用", 中国优秀硕士学位论文全文数据库 信息科技辑, pages 140 - 854 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113478492A (en) * | 2021-09-07 | 2021-10-08 | 成都博恩思医学机器人有限公司 | Method and system for avoiding collision of mechanical arms, robot and storage medium |
| CN113487655A (en) * | 2021-09-07 | 2021-10-08 | 成都博恩思医学机器人有限公司 | Indoor model generation method, electronic equipment and storage medium |
| CN113487655B (en) * | 2021-09-07 | 2022-03-01 | 成都博恩思医学机器人有限公司 | Indoor model generation method, electronic equipment and storage medium |
| CN113478492B (en) * | 2021-09-07 | 2022-05-17 | 成都博恩思医学机器人有限公司 | Method and system for avoiding collision of mechanical arms, robot and storage medium |
| CN114851211A (en) * | 2022-07-07 | 2022-08-05 | 国网瑞嘉(天津)智能机器人有限公司 | Method, device, server and storage medium for planning boom track |
| CN114851211B (en) * | 2022-07-07 | 2022-09-23 | 国网瑞嘉(天津)智能机器人有限公司 | Method, device, server and storage medium for planning track of boom |
| CN114986524A (en) * | 2022-08-08 | 2022-09-02 | 中国科学院自动化研究所 | Mechanical arm track planning method and device based on brain-computer interface and electronic equipment |
| CN117444989A (en) * | 2023-12-25 | 2024-01-26 | 常州微亿智造科技有限公司 | Collision detection method and device for path planning |
| CN117444989B (en) * | 2023-12-25 | 2024-03-22 | 常州微亿智造科技有限公司 | Collision detection method and device for path planning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113246143A (en) | Mechanical arm dynamic obstacle avoidance trajectory planning method and device | |
| US11192250B1 (en) | Methods and apparatus for determining the pose of an object based on point cloud data | |
| WO2021232669A1 (en) | Robot motion planning method, path planning method, grabbing method and devices thereof | |
| CN108818530B (en) | Mechanical arm grabbing scattered stacking piston motion planning method based on improved RRT algorithm | |
| Song et al. | CAD-based pose estimation design for random bin picking using a RGB-D camera | |
| CN109434836B (en) | Manipulator artificial potential field space path planning method combined with ball tree model | |
| JP7433609B2 (en) | Method and computational system for object identification | |
| CN108733065B (en) | Obstacle avoidance method and device for robot and robot | |
| CN111216125B (en) | Obstacle avoidance method and system of moving mechanical arm device facing narrow passage | |
| CN102393646B (en) | Multilayered dynamic collision detecting method and system for blade production line | |
| CN112405541B (en) | Laser 3D precision cutting double-robot cooperative operation method | |
| CN111982127A (en) | Lightweight-3D obstacle avoidance method | |
| Luo et al. | Hybrid eye-to-hand and eye-in-hand visual servo system for parallel robot conveyor object tracking and fetching | |
| CN110561420A (en) | Arm profile constraint flexible robot track planning method and device | |
| CN113232025B (en) | Mechanical arm obstacle avoidance method based on proximity perception | |
| US20230419531A1 (en) | Apparatus and method for measuring, inspecting or machining objects | |
| US10035264B1 (en) | Real time robot implementation of state machine | |
| Mironov et al. | Fast kNN-based Prediction for the Trajectory of a Thrown Body | |
| WO2021217341A1 (en) | Obstacle avoidance method, moveable platform, control device, and storage medium | |
| Schaub et al. | 6-dof grasp detection for unknown objects | |
| JP2778430B2 (en) | Three-dimensional position and posture recognition method based on vision and three-dimensional position and posture recognition device based on vision | |
| Kanellakis et al. | Guidance for autonomous aerial manipulator using stereo vision | |
| Lei et al. | Unknown object grasping using force balance exploration on a partial point cloud | |
| JP2023041731A (en) | Method and computing system for performing robot motion planning and repository detection | |
| 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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zhu Minghan Inventor before: Shi Peng Inventor before: Zhu Minghan |
|
| CB03 | Change of inventor or designer information |