CN116834005A - Method for planning obstacle avoidance path of mechanical arm in multi-obstacle environment - Google Patents
Method for planning obstacle avoidance path of mechanical arm in multi-obstacle environment Download PDFInfo
- Publication number
- CN116834005A CN116834005A CN202310845179.XA CN202310845179A CN116834005A CN 116834005 A CN116834005 A CN 116834005A CN 202310845179 A CN202310845179 A CN 202310845179A CN 116834005 A CN116834005 A CN 116834005A
- Authority
- CN
- China
- Prior art keywords
- mechanical arm
- obstacle
- model
- information
- determining
- 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 39
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 238000004088 simulation Methods 0.000 claims description 17
- 230000004888 barrier function Effects 0.000 claims description 14
- 238000010276 construction Methods 0.000 claims description 12
- 238000006073 displacement reaction Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 description 11
- 230000008859 change Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
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
- B25J9/1628—Programme controls characterised by the control loop
- B25J9/163—Programme controls characterised by the control loop learning, adaptive, model based, rule based expert control
Abstract
The invention provides a method for planning an obstacle avoidance path of a mechanical arm in a multi-obstacle environment, which comprises the following steps: acquiring state information of each joint of the current mechanical arm and a target position of the mechanical arm; based on a binocular vision system, acquiring multi-obstacle information between the mechanical arm and the target position; modeling according to the multi-obstacle information, and determining a multi-obstacle model; modeling according to the state information of each joint of the mechanical arm, and determining a mechanical arm model; constructing a simulated working scene according to the mechanical arm model and the multi-obstacle model and the corresponding position information thereof; and performing collision detection on the mechanical arm model and the multi-obstacle model through simulating a working scene, and determining the mechanical arm running path under no collision.
Description
Technical Field
The invention relates to the technical field of intelligent control, in particular to a planning method for an obstacle avoidance path of a mechanical arm in a multi-obstacle environment.
Background
Along with the continuous popularization of factory intelligence, the mechanical arm gradually becomes an indispensable component in the factory, and the production efficiency of the factory is greatly improved through the mechanical arm. However, as the devices inside the factory are gradually increased, the working environment is increasingly complex, more and more requirements are put on the working task of the mechanical arm, in order to prevent the mechanical arm from colliding with other devices in the working process, the mechanical arm collision scram control is adopted in the traditional mode, the scram control is to judge whether the mechanical arm collides by detecting the change of force or the abrupt change of joint current through a force sensor, and the obstacle needs to collide with the mechanical arm to trigger the scram, however, the mechanical arm collides with an article or person, and then the article is easily damaged, or the person is injured. After collision, the robot arm stops working, and if the robot arm is damaged, the robot arm can continue working, so that the working efficiency of the robot arm is reduced.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a planning method for an obstacle avoidance path of a mechanical arm in a multi-obstacle environment, which is used for solving the problems in the prior art.
A planning method for an obstacle avoidance path of a mechanical arm in a multi-obstacle environment comprises the following steps: acquiring state information of each joint of the current mechanical arm and a target position of the mechanical arm; based on a binocular vision system, acquiring multi-obstacle information between the mechanical arm and the target position; modeling according to the multi-obstacle information, and determining a multi-obstacle model; modeling according to the state information of each joint of the mechanical arm, and determining a mechanical arm model; constructing a simulated working scene according to the mechanical arm model and the multi-obstacle model and the corresponding position information thereof; and performing collision detection on the mechanical arm model and the multi-obstacle model through simulating a working scene, and determining the mechanical arm running path under no collision.
As an embodiment of the present invention, obtaining current state information of each joint of the mechanical arm and a target position of the mechanical arm includes: calculating state information of each joint of the current mechanical arm in space based on the positive kinematics of the mechanical arm; wherein the state information includes position information and posture information in the space; and determining the target position of the object to be grabbed by the mechanical arm according to a preset grabbing instruction.
As an embodiment of the present invention, based on a binocular vision system, acquiring multi-obstacle information between a robot arm and a target location includes: and acquiring image information of multiple obstacles between the mechanical arm and a target grabbing object at a target position according to two cameras of a binocular vision system arranged on the mechanical arm in advance.
As an embodiment of the present invention, modeling from multi-obstacle information, determining a multi-obstacle model includes: based on the envelope box model, the minimum envelope sphere model processing is adopted for the multi-obstacle information, and an envelope model of a plurality of obstacles is generated.
As an embodiment of the present invention, modeling according to state information of each joint of the mechanical arm, determining a mechanical arm model includes: based on the envelope box model, processing each joint of the mechanical arm by adopting a minimum envelope sphere model, and determining a first envelope model of each joint of the mechanical arm; processing the mechanical arm connecting rod by adopting a cylinder enveloping method model, and determining a second enveloping model of the mechanical arm connecting rod; and combining the first envelope model and the second envelope model according to the connection relation between the original joint of the mechanical arm and the connecting rod to determine the mechanical arm model.
As one embodiment of the present invention, constructing a simulated work scene according to a robot arm model and a multi-obstacle model and corresponding position information thereof includes: constructing an initial virtual scene, and determining relative position information of the mechanical arm model and the multi-obstacle model according to the position information corresponding to the mechanical arm model and the multi-obstacle model respectively; adding a mechanical arm model to any position of an initial virtual scene, determining actual positions of a plurality of obstacle models in the initial virtual scene according to relative position information by taking the mechanical arm model as an origin, and adding the plurality of obstacle models to corresponding actual positions in the initial virtual scene; and meanwhile, determining a second actual position of the grabbing object of the mechanical arm in the initial virtual scene according to the target position of the grabbing object of the mechanical arm and the relative positions of the mechanical arm model and the multi-obstacle model, and adding the simulation object to the corresponding second actual position in the initial virtual scene to complete the construction of the simulation working scene.
As an embodiment of the present invention, performing collision detection on a robot arm model and a multi-obstacle model by simulating a working scene, determining a robot arm travel path without collision includes: acquiring motion parameters of the mechanical arm, and controlling the mechanical arm model to simulate a plurality of mechanical arm running paths of a target object of a target position successfully grabbed by the mechanical arm under the condition of not colliding with the multi-obstacle model according to the motion parameters through simulating a working scene; and sequencing the path lengths from the mechanical arm to the target position in the multiple mechanical arm running paths, and determining the shortest path as the mechanical arm running path under collision.
As an embodiment of the present invention, a method for planning an obstacle avoidance path of a mechanical arm in a multi-obstacle environment further includes: whether the mechanical arm has a dynamic obstacle around the mechanical arm when the mechanical arm running path is executed is sensed in real time through a sensor arranged on the mechanical arm, if so, the mechanical arm running path is suspended, and the rest mechanical arm running paths are continuously executed until no dynamic obstacle exists around the mechanical arm running path.
As an embodiment of the present invention, a method for planning an obstacle avoidance path of a mechanical arm in a multi-obstacle environment further includes: when multiple mechanical arms simultaneously run, when any mechanical arm senses that dynamic obstacles exist around, first displacement information of the dynamic obstacles is obtained, and dynamic obstacle identity information is tried to be obtained; if the dynamic obstacle identity information is successfully acquired, inquiring a corresponding target moving place based on the obstacle identity information and the first displacement information, and predicting first travel route information of the dynamic obstacle through the first displacement information, wherein the first travel route information comprises travel information from the current position to a sensing range of leaving the current mechanical arm, and the travel information comprises a travel track and a travel speed; acquiring all first travel route information of a preset number of mechanical arms according to the dynamic obstacle identity information, and acquiring a target movement track of the dynamic obstacle according to all first travel route information, a target movement place and the dynamic obstacle identity information; predicting a second travelling speed of the subsequent dynamic obstacle according to travelling speeds in all the first travelling route information; determining a first time for the dynamic barrier to reach the periphery of the subsequent mechanical arm according to the second travelling speed and the target moving track; and controlling the corresponding mechanical arm to pause executing the mechanical arm running path in advance according to the first time and the target moving track until the dynamic obstacle passes, and continuing to execute the rest mechanical arm running paths.
As an embodiment of the present invention, a method for planning an obstacle avoidance path of a mechanical arm in a multi-obstacle environment further includes: when the dynamic obstacle reaches the next mechanical arm after the target movement track is determined, the second traveling speed of the subsequent dynamic obstacle is predicted again according to the traveling speed collected by the next mechanical arm and the target movement track, and the second time for the dynamic obstacle to reach the periphery of the subsequent mechanical arm is determined according to the second traveling speed and the target movement track which are predicted again.
The beneficial effects of the invention are as follows:
the invention provides a planning method for an obstacle avoidance path of a mechanical arm in a multi-obstacle environment, which adopts a virtual scene construction mode to simulate the occurrence of collision, adopts an intelligent obstacle avoidance method to determine the running path of the mechanical arm in no collision, does not need to detect the change of force or the abrupt change of joint current through a force sensor to judge whether the collision occurs, and reduces the loss caused by the way of sudden stop of the collision.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of a method for planning an obstacle avoidance path of a mechanical arm in a multi-obstacle environment according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating a construction process of a simulation work scene in a planning method of an obstacle avoidance path of a mechanical arm in a multi-obstacle environment according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating a process of determining a path of a robot in a method for planning a path of avoiding an obstacle in a robot in a multi-obstacle environment according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Referring to fig. 1, a method for planning an obstacle avoidance path of a mechanical arm in a multi-obstacle environment includes: s101, acquiring state information of each joint of a current mechanical arm and a target position of the mechanical arm; s102, acquiring multi-obstacle information between a mechanical arm and a target position based on a binocular vision system; s103, modeling is carried out according to the multi-obstacle information, and a multi-obstacle model is determined; s104, modeling is carried out according to the state information of each joint of the mechanical arm, and a mechanical arm model is determined; s105, constructing a simulation working scene according to the mechanical arm model and the multi-obstacle model and the corresponding position information thereof; s106, performing collision detection on the mechanical arm model and the multi-obstacle model through a simulation working scene, and determining a mechanical arm running path under no collision;
the working principle of the technical scheme is as follows: after the mechanical arm is mounted to a fixed position, before each start, the mechanical arm starts a mechanical arm obstacle avoidance path planning method under a multi-obstacle environment, and it is worth to say that the mechanical arm is further provided with a start and stop button, if the arrangement in a factory is unchanged, the mechanical arm can continue to execute according to the previous path planning, so that the cost is saved, when the path planning is started, the state information of each joint of the current mechanical arm and the target position of the mechanical arm are obtained, the state information of each joint of the current mechanical arm comprises the gesture and the position, and the target position of the mechanical arm is the target position of an object to be grabbed; then, obtaining multi-angle picture information of a plurality of barriers between the mechanical arm and the target object based on a binocular vision system arranged on or around the mechanical arm; modeling a plurality of obstacles according to the acquired multi-angle picture information, and determining models of the plurality of obstacles; modeling the mechanical arm according to the state information of each joint of the mechanical arm, and determining a mechanical arm model; then constructing a simulation working scene through a virtual scene construction mode and through a mechanical arm model, a multi-obstacle model and corresponding position information, wherein as is well known, path planning is to plan an execution path from the mechanical arm to a target object, so that the target object is certainly added into the construction simulation working scene, and therefore description is omitted, finally, collision detection is carried out on the mechanical arm model and the multi-obstacle model through the simulation working scene, and a mechanical arm running path under no collision is determined;
the beneficial effects of the technical scheme are as follows: through the technical scheme, the virtual scene construction mode is adopted to simulate collision, the intelligent obstacle avoidance method is adopted to determine the running path of the mechanical arm under no collision, whether the collision occurs or not is judged by detecting that the force is changed or the joint current is suddenly changed through the force sensor, the loss caused by the collision sudden stop mode is reduced, the route is planned in advance without judging once every time when the route is advanced by a distance, and the running speed of the mechanical arm is improved.
In one embodiment, obtaining the current state information of each joint of the mechanical arm and the target position of the mechanical arm includes: calculating state information of each joint of the current mechanical arm in space based on the positive kinematics of the mechanical arm; wherein the state information includes position information and posture information in the space; determining a target position of an object to be grabbed by the mechanical arm according to a preset grabbing instruction;
the gesture information also comprises the gesture of the mechanical arm in any state in space;
the preset grabbing instruction is a control instruction which is input into the mechanical arm by a user in advance and comprises the target position of the object to be grabbed;
the beneficial effects of the technical scheme are as follows: through the technical scheme, basic data support is provided for path planning.
In one embodiment, based on a binocular vision system, acquiring multi-obstacle information between a robotic arm and a target location includes: acquiring image information of multiple obstacles between the mechanical arm and a target grabber at a target position according to two cameras of a binocular vision system arranged on the mechanical arm in advance;
the image information is different from the initial multi-angle image information acquired by the binocular vision system in that the image information is processed image information, namely, the data required by constructing an envelope model can be directly extracted from the image information;
it is worth to say that the binocular vision system can be arranged around the mechanical arm, and only the environmental information around the mechanical arm and the target object can be acquired;
the beneficial effects of the technical scheme are as follows: by the technical scheme, model data grabbing of the obstacle is completed.
In one embodiment, modeling from multi-obstacle information, determining a multi-obstacle model includes: based on the envelope box model, processing the multi-obstacle information by adopting a minimum envelope sphere model to generate an envelope model of a plurality of obstacles;
the beneficial effects of the technical scheme are as follows: through the technical scheme, the model construction of a plurality of barriers is completed, and the accuracy of simulating collision can be ensured to the greatest extent by adopting the minimum enclosing sphere model.
In one embodiment, modeling is performed according to state information of each joint of the mechanical arm, and determining a mechanical arm model includes: based on the envelope box model, processing each joint of the mechanical arm by adopting a minimum envelope sphere model, and determining a first envelope model of each joint of the mechanical arm; processing the mechanical arm connecting rod by adopting a cylinder enveloping method model, and determining a second enveloping model of the mechanical arm connecting rod; combining the first envelope model and the second envelope model according to the connection relation between the original joint of the mechanical arm and the connecting rod to determine a mechanical arm model;
when the minimum bounding sphere model is adopted for processing each joint of the mechanical arm, different minimum bounding spheres are determined based on different gesture information of each joint in space, the circle center is determined, all the minimum bounding spheres are overlapped, and finally, a straight line segment constructed by the farthest two points after the overlapping is used as the diameter of a first enveloping model of the current joint;
when the connecting rod is processed by adopting the cylindrical envelope model, the connecting end of the cylindrical envelope model and the joint envelope model is embedded into the joint envelope model by matching with the minimum envelope sphere of each joint, so that all the first envelope models are connected by taking the second envelope model as the connection, and the first envelope models are combined into an integral mechanical arm model;
the beneficial effects of the technical scheme are as follows: through the technical scheme, the mechanical arm model is built by adopting the envelope model in a mode of minimum error, so that the accuracy of simulating collision can be ensured to the greatest extent.
Referring to fig. 2, in one embodiment, constructing a simulated work scene according to a robot arm model and a multi-obstacle model and corresponding position information thereof includes: s201, constructing an initial virtual scene, and determining relative position information of the mechanical arm model and the multi-obstacle model according to the position information corresponding to the mechanical arm model and the multi-obstacle model respectively; s202, adding a mechanical arm model to any position of an initial virtual scene, determining actual positions of a plurality of obstacle models in the initial virtual scene according to relative position information by taking the mechanical arm model as an origin, and adding the plurality of obstacle models to corresponding actual positions in the initial virtual scene; s203, determining a second actual position of the grabbing object of the mechanical arm in the initial virtual scene according to the target position of the grabbing object of the mechanical arm and the relative positions of the mechanical arm model and the multi-obstacle model, and adding the simulation object to the corresponding second actual position in the initial virtual scene to complete the construction of the simulation work scene;
the working principle of the technical scheme is as follows: the construction of the simulated working scene is realized based on a virtual scene construction mode, firstly, an initial virtual scene is constructed, and the initial virtual scene is a blank scene without any model; then determining relative position information of the mechanical arm model and the multi-obstacle model according to the position information corresponding to the mechanical arm model and the multi-obstacle model respectively, and considering the direction and the distance during determination; after the relative position information is determined, adding the mechanical arm model to any position of an initial virtual scene, setting the central position of the mechanical arm model as an origin, determining the actual positions of a plurality of barrier models in the initial virtual scene according to the relative position information, and finally adding the plurality of barrier models to the corresponding actual positions in the initial virtual scene to finish the addition of the mechanical arm model and the barrier models, and finally determining the second actual position of the grabbing object of the mechanical arm in the initial virtual scene according to the target position of the grabbing object of the mechanical arm and the relative positions of the mechanical arm model and the plurality of barrier models; after the position is determined, adding a simulation target object to a corresponding second actual position in the initial virtual scene to complete the construction of a simulation work scene;
the beneficial effects of the technical scheme are as follows: by the technical scheme, the virtual scene is constructed, and the collision possibility of the traditional mode is reduced by simulating the path planning through the virtual scene.
Referring to fig. 3, in one embodiment, determining a robot travel path without collision by performing collision detection on a robot model and a multi-obstacle model through simulating a working scene includes: s301, acquiring motion parameters of the mechanical arm, and controlling the mechanical arm model to simulate a plurality of mechanical arm running paths of a target object of a target position successfully grabbed by the mechanical arm under the condition of not colliding with a multi-obstacle model according to the motion parameters by simulating a working scene; s302, sorting path lengths from the mechanical arm to a target position in a plurality of mechanical arm running paths, and determining a shortest path as a mechanical arm running path under collision;
controlling the simulation operation of the mechanical arm model in a simulation working scene according to motion parameters, wherein the motion parameters comprise, but are not limited to, state information of each joint and the like;
when the running path of the mechanical arm is simulated, the simulation motion is performed by determining the operable space of the mechanical arm;
comparing the movement area of the mechanical arm model with the spherical area of the obstacle model, if no coincidence occurs, acquiring and executing a running path by the mechanical arm according to a nearby principle, and if coincidence occurs, replacing the travelling direction information and continuously executing;
the motion region comprises a first envelope model region at the joint and a second envelope model region at the link;
the beneficial effects of the technical scheme are as follows: through the technical scheme, the planning of the running path is simulated and completed on the premise of no real collision, the risk of collision test is reduced, meanwhile, the mechanical arm following the planned path does not need to run in a one-step one-detection mode, and the running efficiency of the mechanical arm is improved.
In one embodiment, the method for planning the obstacle avoidance path of the mechanical arm in the multi-obstacle environment further comprises the following steps: sensing whether a dynamic obstacle exists around the mechanical arm when the mechanical arm runs along the path or not in real time through a sensor arranged on the mechanical arm, if so, suspending the execution of the mechanical arm running along the path until no dynamic obstacle exists around the path, and continuing to execute the rest mechanical arm running along the path;
the sensor is preferably arranged at the front end of the mechanical arm, and the sensor can adopt an infrared distance sensor, a thermal imaging sensor and other sensors with sensing functions;
if the stopping time is too long, an alarm is sent out;
the beneficial effects of the technical scheme are as follows: through the technical scheme, the influence of dynamic barriers on the mechanical arm is reduced, and meanwhile, when a manager does not set a re-planning path after the arrangement and updating of the articles in the factory, the collision possibility can be reduced through the scheme.
In one embodiment, the method for planning the obstacle avoidance path of the mechanical arm in the multi-obstacle environment further comprises the following steps: when multiple mechanical arms simultaneously run, when any mechanical arm senses that dynamic obstacles exist around, first displacement information of the dynamic obstacles is obtained, and dynamic obstacle identity information is tried to be obtained; if the dynamic obstacle identity information is successfully acquired, inquiring a corresponding target moving place based on the obstacle identity information and the first displacement information, and predicting first travel route information of the dynamic obstacle through the first displacement information, wherein the first travel route information comprises travel information from the current position to a sensing range of leaving the current mechanical arm, and the travel information comprises a travel track and a travel speed; acquiring all first travel route information of a preset number of mechanical arms according to the dynamic obstacle identity information, and acquiring a target movement track of the dynamic obstacle according to all first travel route information, a target movement place and the dynamic obstacle identity information; predicting a second travelling speed of the subsequent dynamic obstacle according to travelling speeds in all the first travelling route information; determining a first time for the dynamic barrier to reach the periphery of the subsequent mechanical arm according to the second travelling speed and the target moving track; controlling the corresponding mechanical arm to pause executing the mechanical arm running path in advance according to the first time and the target moving track until the dynamic obstacle passes, and continuing to execute the rest mechanical arm running paths;
the dynamic obstacle identity information comprises other intelligent devices existing in the factory;
if the dynamic obstacle identity information is not successfully acquired, continuing to execute the dynamic obstacle avoidance method;
the target moving place is preferably stored in a database in advance, and screening can be performed according to the identity information of the obstacle and the first displacement information;
the preset number of mechanical arms is preferably the number of mechanical arms capable of preliminarily determining the target movement track;
the size of the sensing range of the mechanical arm is related to the performance of the sensor;
the beneficial effects of the technical scheme are as follows: through the technical scheme, the obstacle avoidance data is provided for the obstacle avoidance of the subsequent mechanical arm in advance by predicting the target movement track, the obstacle avoidance planning can be made in advance before the dynamic obstacle comes, the dependence on the sensor performance is reduced, the sensor cost is further reduced, and meanwhile, the possibility of collision is further reduced by adopting a prediction mode.
In one embodiment, the method for planning the obstacle avoidance path of the mechanical arm in the multi-obstacle environment further comprises the following steps: when the dynamic barrier reaches the next mechanical arm after the target movement track is determined, re-predicting a second travelling speed of the subsequent dynamic barrier according to the travelling speed acquired by the next mechanical arm and the target movement track, and determining a second time for the dynamic barrier to reach the periphery of the subsequent mechanical arm according to the re-predicted second travelling speed and the target movement track;
the method comprises the steps of firstly determining a target moving track, then acquiring actual travelling information of a dynamic obstacle according to a subsequent mechanical arm, and further performing secondary verification on predicted information;
during verification, the method also comprises the step of verifying the accuracy of the target moving track, namely judging whether the mechanical arm which detects the dynamic obstacle at present is the mechanical arm contained in the prediction information;
the determination mode of the dynamic barrier is determined by identifying identity information;
the beneficial effects of the technical scheme are as follows: through the technical scheme, the prediction information is repeatedly verified in a mode of updating the dynamic obstacle information in real time, and meanwhile, the prediction information is adjusted according to the deviation between the prediction information and the actual information, so that the accuracy of the prediction information is improved, and the possibility of collision is further reduced.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. The method for planning the obstacle avoidance path of the mechanical arm in the multi-obstacle environment is characterized by comprising the following steps of: acquiring state information of each joint of the current mechanical arm and a target position of the mechanical arm; based on a binocular vision system, acquiring multi-obstacle information between the mechanical arm and the target position; modeling according to the multi-obstacle information, and determining a multi-obstacle model; modeling according to the state information of each joint of the mechanical arm, and determining a mechanical arm model; constructing a simulated working scene according to the mechanical arm model and the multi-obstacle model and the corresponding position information thereof; and performing collision detection on the mechanical arm model and the multi-obstacle model through simulating a working scene, and determining the mechanical arm running path under no collision.
2. The method for planning the obstacle avoidance path of the mechanical arm in the multi-obstacle environment according to claim 1, wherein the step of obtaining the state information of each joint of the current mechanical arm and the target position of the mechanical arm comprises the following steps: calculating state information of each joint of the current mechanical arm in space based on the positive kinematics of the mechanical arm; wherein the state information includes position information and posture information in the space; and determining the target position of the object to be grabbed by the mechanical arm according to a preset grabbing instruction.
3. The method for planning an obstacle avoidance path of a manipulator in a multi-obstacle environment according to claim 1, wherein acquiring multi-obstacle information between the manipulator and a target position based on a binocular vision system comprises: and acquiring image information of multiple obstacles between the mechanical arm and a target grabbing object at a target position according to two cameras of a binocular vision system arranged on the mechanical arm in advance.
4. The method for planning an obstacle avoidance path of a robotic arm in a multi-obstacle environment of claim 1, wherein modeling based on multi-obstacle information determines a multi-obstacle model, comprising: based on the envelope box model, the minimum envelope sphere model processing is adopted for the multi-obstacle information, and an envelope model of a plurality of obstacles is generated.
5. The method for planning an obstacle avoidance path of a manipulator in a multi-obstacle environment according to claim 1, wherein modeling is performed according to state information of each joint of the manipulator, and determining a manipulator model comprises: based on the envelope box model, processing each joint of the mechanical arm by adopting a minimum envelope sphere model, and determining a first envelope model of each joint of the mechanical arm; processing the mechanical arm connecting rod by adopting a cylinder enveloping method model, and determining a second enveloping model of the mechanical arm connecting rod; and combining the first envelope model and the second envelope model according to the connection relation between the original joint of the mechanical arm and the connecting rod to determine the mechanical arm model.
6. The method for planning an obstacle avoidance path of a manipulator in a multi-obstacle environment according to claim 1, wherein constructing a simulated work scene according to the manipulator model and the multi-obstacle model and the corresponding position information thereof comprises: constructing an initial virtual scene, and determining relative position information of the mechanical arm model and the multi-obstacle model according to the position information corresponding to the mechanical arm model and the multi-obstacle model respectively; adding a mechanical arm model to any position of an initial virtual scene, determining actual positions of a plurality of obstacle models in the initial virtual scene according to relative position information by taking the mechanical arm model as an origin, and adding the plurality of obstacle models to corresponding actual positions in the initial virtual scene; and meanwhile, determining a second actual position of the grabbing object of the mechanical arm in the initial virtual scene according to the target position of the grabbing object of the mechanical arm and the relative positions of the mechanical arm model and the multi-obstacle model, and adding the simulation object to the corresponding second actual position in the initial virtual scene to complete the construction of the simulation working scene.
7. The method for planning an obstacle avoidance path of a manipulator in a multi-obstacle environment according to claim 1, wherein determining a manipulator travel path without collision by performing collision detection on a manipulator model and a multi-obstacle model by simulating a working scene comprises: acquiring motion parameters of the mechanical arm, and controlling the mechanical arm model to simulate a plurality of mechanical arm running paths of a target object of a target position successfully grabbed by the mechanical arm under the condition of not colliding with the multi-obstacle model according to the motion parameters through simulating a working scene; and sequencing the path lengths from the mechanical arm to the target position in the multiple mechanical arm running paths, and determining the shortest path as the mechanical arm running path under collision.
8. The method for planning an obstacle avoidance path of a robotic arm in a multi-obstacle environment of claim 1, further comprising: whether the mechanical arm has a dynamic obstacle around the mechanical arm when the mechanical arm running path is executed is sensed in real time through a sensor arranged on the mechanical arm, if so, the mechanical arm running path is suspended, and the rest mechanical arm running paths are continuously executed until no dynamic obstacle exists around the mechanical arm running path.
9. The method for planning an obstacle avoidance path of a robotic arm in a multi-obstacle environment of claim 8, further comprising: when multiple mechanical arms simultaneously run, when any mechanical arm senses that dynamic obstacles exist around, first displacement information of the dynamic obstacles is obtained, and dynamic obstacle identity information is tried to be obtained; if the dynamic obstacle identity information is successfully acquired, inquiring a corresponding target moving place based on the obstacle identity information and the first displacement information, and predicting first travel route information of the dynamic obstacle through the first displacement information, wherein the first travel route information comprises travel information from the current position to a sensing range of leaving the current mechanical arm, and the travel information comprises a travel track and a travel speed; acquiring all first travel route information of a preset number of mechanical arms according to the dynamic obstacle identity information, and acquiring a target movement track of the dynamic obstacle according to all first travel route information, a target movement place and the dynamic obstacle identity information; predicting a second travelling speed of the subsequent dynamic obstacle according to travelling speeds in all the first travelling route information; determining a first time for the dynamic barrier to reach the periphery of the subsequent mechanical arm according to the second travelling speed and the target moving track; and controlling the corresponding mechanical arm to pause executing the mechanical arm running path in advance according to the first time and the target moving track until the dynamic obstacle passes, and continuing to execute the rest mechanical arm running paths.
10. The method for planning an obstacle avoidance path of a robotic arm in a multi-obstacle environment of claim 9, further comprising: when the dynamic obstacle reaches the next mechanical arm after the target movement track is determined, the second traveling speed of the subsequent dynamic obstacle is predicted again according to the traveling speed collected by the next mechanical arm and the target movement track, and the second time for the dynamic obstacle to reach the periphery of the subsequent mechanical arm is determined according to the second traveling speed and the target movement track which are predicted again.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310845179.XA CN116834005A (en) | 2023-07-11 | 2023-07-11 | Method for planning obstacle avoidance path of mechanical arm in multi-obstacle environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310845179.XA CN116834005A (en) | 2023-07-11 | 2023-07-11 | Method for planning obstacle avoidance path of mechanical arm in multi-obstacle environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116834005A true CN116834005A (en) | 2023-10-03 |
Family
ID=88172351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310845179.XA Pending CN116834005A (en) | 2023-07-11 | 2023-07-11 | Method for planning obstacle avoidance path of mechanical arm in multi-obstacle environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116834005A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117067220A (en) * | 2023-10-16 | 2023-11-17 | 广州上诺生物技术有限公司 | Neural network-based blood bank mechanical arm collision-free path planning method |
| 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 |
-
2023
- 2023-07-11 CN CN202310845179.XA patent/CN116834005A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117067220A (en) * | 2023-10-16 | 2023-11-17 | 广州上诺生物技术有限公司 | Neural network-based blood bank mechanical arm collision-free path planning method |
| CN117067220B (en) * | 2023-10-16 | 2024-01-02 | 广州上诺生物技术有限公司 | Neural network-based blood bank mechanical arm collision-free path planning method |
| 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 |
|---|---|---|
| CN116834005A (en) | Method for planning obstacle avoidance path of mechanical arm in multi-obstacle environment | |
| CN108908331B (en) | Obstacle avoidance method and system for super-redundant flexible robot and computer storage medium | |
| KR101859350B1 (en) | Virtual safety cages for robotic devices | |
| WO2021063247A1 (en) | Obstacle avoidance method and apparatus, electronic device and storage medium | |
| US8352074B2 (en) | Path planning apparatus and method of robot | |
| EP3667450B1 (en) | Mobile body and method for control of mobile body | |
| CN111693050B (en) | Indoor medium and large robot navigation method based on building information model | |
| WO2008032673A1 (en) | Moving device | |
| US20180173232A1 (en) | System and method for sensing the driving environment of a motor vehicle | |
| JP2018512323A (en) | Method and apparatus for monitoring a target trajectory to be followed by a vehicle for collisions to occur | |
| US20220057804A1 (en) | Path determination method | |
| KR20210063791A (en) | System for mapless navigation based on dqn and slam considering characteristic of obstacle and processing method thereof | |
| CN106918434B (en) | A kind of six degree of freedom captive trajectory testing method of online avoidance | |
| CN103900510A (en) | Detection path modeling method of coordinate measuring machine | |
| US20240043034A1 (en) | Method and system for conditional operation of an autonomous agent | |
| JPH05297944A (en) | Obstacle avoiding system for mobile robot | |
| CN112936288A (en) | Robot action safety detection method and device, electronic equipment and storage medium | |
| CN112327848A (en) | Robot obstacle avoidance method and device, storage medium and electronic equipment | |
| CN110549375A (en) | protective door anti-collision method and system for mechanical arm | |
| CN115885226A (en) | Method and apparatus for simulating an Automated Guided Vehicle (AGV) system | |
| US11919171B2 (en) | Robot controller | |
| CN109934918B (en) | Multi-robot collaborative map reconstruction method based on visual and tactile fusion mechanism | |
| Isrofi et al. | Automated Guided Vehicle (AGV) Navigation Control using Matrix Method Applying Radio Frequency Identification (RFID) Point Address | |
| Kidiraliev et al. | Using optical sensors for industrial robot-human interactions in a Gazebo environment | |
| CN117798925A (en) | Intelligent control method for mobile robot |
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 |