CN115781693A - Obstacle avoidance method and device for industrial robot, industrial robot and storage medium - Google Patents
Obstacle avoidance method and device for industrial robot, industrial robot and storage medium Download PDFInfo
- Publication number
- CN115781693A CN115781693A CN202310023942.0A CN202310023942A CN115781693A CN 115781693 A CN115781693 A CN 115781693A CN 202310023942 A CN202310023942 A CN 202310023942A CN 115781693 A CN115781693 A CN 115781693A
- Authority
- CN
- China
- Prior art keywords
- industrial robot
- obstacle
- working path
- obstacle avoidance
- path
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Manipulator (AREA)
- Numerical Control (AREA)
Abstract
The invention relates to the technical field of manipulators, in particular to an obstacle avoidance method and device of an industrial robot, the industrial robot and a storage medium, wherein the obstacle avoidance method of the industrial robot comprises the following steps: acquiring historical image data of an obstacle before the obstacle enters an obstacle avoidance range of the industrial robot, and inputting the historical image data into a track prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a predicted track of the obstacle; detecting whether the obstacle moves in the obstacle avoidance range based on the predicted track; if the obstacle moves in the obstacle avoidance range, replanning the first working path based on the obstacle information of the obstacle and the path point of the industrial robot; and if the obstacle does not move in the obstacle avoidance range, replanning the second working path based on the obstacle information, the obstacle avoidance distance of the industrial robot and the path point of the industrial robot. The invention realizes the improvement of the safety of the industrial robot in the operation process.
Description
Technical Field
The invention relates to the technical field of manipulators, in particular to an obstacle avoidance method and device for an industrial robot, the industrial robot and a storage medium.
Background
Industrial robots are multi-joint manipulators or multi-degree-of-freedom machine devices widely used in the industrial field, have a certain degree of automation, and can realize various industrial processing and manufacturing functions depending on the power energy and control capability of the industrial robots. The industrial robot integrates a plurality of disciplines such as mechanics, electronic informatics, automation, computer discipline, bionics and the like, and has the advantages of high production efficiency, good product quality, capability of continuously working in a severe environment and the like. Due to the characteristics, the industrial robot not only releases human beings from heavy physical labor, but also greatly improves the living conditions of people in various aspects of production and life, and is inevitably developed in the direction of intellectualization and densification in order to better serve the human beings.
At present, when an industrial robot is actually used for production, the industrial robot may encounter obstacles, especially in the production process of multi-robot cooperation and man-machine cooperation, and if the industrial robot cannot adjust the advancing route in time when detecting that the obstacles exist, the safety of the industrial robot may be affected.
Disclosure of Invention
The invention mainly aims to provide an obstacle avoidance method and device for an industrial robot, the industrial robot and a computer readable storage medium, and aims to improve the safety of the industrial robot.
In order to achieve the above object, the present invention provides an obstacle avoidance method for an industrial robot, which includes the following steps:
acquiring historical image data of an obstacle before the obstacle enters an obstacle avoidance range of the industrial robot, and inputting the historical image data into a track prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a predicted track of the obstacle, wherein the obstacle avoidance range is a range formed by taking the position of the industrial robot as a circle center and taking an obstacle avoidance distance of the industrial robot as a radius;
detecting whether the obstacle moves in the obstacle avoidance range or not based on the predicted track;
if the obstacle moves in the obstacle avoidance range, replanning a first working path based on the obstacle information of the obstacle and the path point of the industrial robot so as to control the industrial robot to operate according to the first working path;
and if the obstacle does not move in the obstacle avoidance range, replanning a second working path based on the obstacle information, the obstacle avoidance distance of the industrial robot and the path point of the industrial robot so as to control the industrial robot to operate according to the second working path.
Optionally, before the step of re-planning the first working path based on the obstacle information of the obstacle and the path point of the industrial robot, the method further comprises:
detecting whether the predicted track is consistent with the current working path of the industrial robot or not;
if the predicted track is consistent with the current working path, detecting whether the moving direction of the obstacle is the direction close to the industrial robot;
the step of re-planning a first working path based on obstacle information of the obstacle and a path point of the industrial robot comprises:
if the moving direction of the obstacle is the direction close to the industrial robot, determining a first deflection angle of the industrial robot based on obstacle information of the obstacle, and controlling the industrial robot to deflect the first deflection angle;
and replanning the first working path according to the pose of the industrial robot deflected by the first deflection angle and the path point of the industrial robot deflected by the first deflection angle.
Optionally, after the step of detecting whether the moving direction of the obstacle is a direction approaching the industrial robot, the method further comprises:
if the moving direction of the obstacle is not the direction close to the industrial robot, the moving speed of the obstacle is obtained;
reducing a moving speed of the industrial robot to be less than a moving speed of the obstacle;
and after the distance between the obstacle and the industrial robot with the reduced moving speed is larger than the obstacle avoidance distance of the industrial robot with the reduced moving speed, replanning a third working path based on the moving speed of the industrial robot with the reduced moving speed and the path point of the industrial robot with the reduced moving speed so as to control the industrial robot with the reduced moving speed to operate according to the third working path.
Optionally, after the step of detecting whether the predicted trajectory coincides with the current working path of the industrial robot, the method further comprises:
if the predicted track is inconsistent with the current working path, detecting whether the moving direction of the obstacle is a direction close to the current working path;
and if the moving direction of the obstacle is the direction close to the current working path, replanning a fourth working path based on the obstacle information of the obstacle, the moving direction of the obstacle and the path point of the industrial robot so as to control the industrial robot to work according to the fourth working path.
Optionally, the step of replanning a fourth working path based on the obstacle information of the obstacle, the moving direction of the obstacle and the path point of the industrial robot comprises:
determining a first yaw direction of the industrial robot based on the direction of movement of the obstacle;
determining a second deflection angle of the industrial robot based on obstacle information of the obstacle;
and after controlling the industrial robot to deflect according to the first deflection direction and the second deflection angle, replanning a fourth working path according to the position and the posture of the industrial robot after deflecting the second deflection angle and the path point of the industrial robot after deflecting the second deflection angle.
Optionally, the obstacle information includes shape information representing a size and a shape of the obstacle and position information representing a relative position of the obstacle with respect to the industrial robot;
the step of replanning a second working path based on the obstacle information, the obstacle avoidance distance of the industrial robot and the path point of the industrial robot includes:
determining a second yaw direction of the industrial robot based on the position information;
determining a third deflection angle of the industrial robot based on the shape information and the obstacle avoidance distance of the industrial robot;
and after controlling the industrial robot to deflect according to the second deflection direction and the third deflection angle, replanning a second working path according to the position and the attitude of the industrial robot after deflecting the third deflection angle and the path point of the industrial robot after deflecting the third deflection angle.
Optionally, before the step of acquiring historical image data of the obstacle before entering the obstacle avoidance range of the industrial robot, the method further comprises:
acquiring observed image data of an obstacle with a known motion track, and preprocessing the observed image data;
establishing a training data set based on the preprocessed observed image data;
inputting the training data set into an initial prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a prediction result;
and based on a loss function, adjusting model parameters in the initial prediction model according to the prediction result to obtain a track prediction model.
In addition, in order to achieve the above object, the present invention further provides an obstacle avoidance apparatus for an industrial robot, including:
the system comprises an acquisition module, a tracking module and a target detection module, wherein the acquisition module is used for acquiring historical image data of an obstacle before the obstacle enters an obstacle avoidance range of the industrial robot, and inputting the historical image data into a track prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a predicted track of the obstacle, and the obstacle avoidance range is a range formed by taking the position of the industrial robot as a circle center and taking an obstacle avoidance distance of the industrial robot as a radius;
the detection module is used for detecting whether the obstacle moves in the obstacle avoidance range or not based on the predicted track;
the planning module is used for replanning a first working path based on the obstacle information of the obstacle and the path point of the industrial robot if the obstacle moves in the obstacle avoidance range so as to control the industrial robot to operate according to the first working path;
and the planning module is further used for re-planning a second working path based on the obstacle information, the obstacle avoidance distance of the industrial robot and the path point of the industrial robot if the obstacle does not move in the obstacle avoidance range, so as to control the industrial robot to operate according to the second working path.
In addition, in order to achieve the above object, the present invention further provides an industrial robot, where the industrial robot includes a memory, a processor, and an obstacle avoidance program of the industrial robot stored in the memory and operable on the processor, and the obstacle avoidance program of the industrial robot implements the steps of the obstacle avoidance method of the industrial robot when executed by the processor.
In addition, in order to achieve the above object, the present invention further provides a computer readable storage medium, where an obstacle avoidance program of an industrial robot is stored, and when the obstacle avoidance program of the industrial robot is executed by a processor, the steps of the obstacle avoidance method of the industrial robot are implemented.
According to the method, historical image data before the obstacle enters an obstacle avoidance range of the industrial robot is obtained, the historical image data are input into a track prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a predicted track of the obstacle, the obstacle avoidance range is a range formed by taking the position of the industrial robot as a circle center and taking the obstacle avoidance distance of the industrial robot as a radius, whether the obstacle moves in the obstacle avoidance range is detected based on the predicted track, if the obstacle moves in the obstacle avoidance range, a first working path is replanned based on obstacle information of the obstacle and path points of the industrial robot, so that the industrial robot is controlled to work according to the first working path, and if the obstacle does not move in the obstacle avoidance range, a second working path is replanned based on the obstacle information, the obstacle avoidance distance of the industrial robot and the path points of the industrial robot, so that the industrial robot is controlled to work according to the second working path.
According to the method, different processing is carried out according to different states of the obstacles, the first working path is re-planned for the obstacles moving in the obstacle avoidance range of the industrial robot according to the obstacle information and the path points, the industrial robot is controlled to operate according to the re-planned first working path, the industrial robot can adapt to the moving state of the obstacles, collision between the industrial robot and the moving obstacles in follow-up operation caused by the fact that the re-planned working path is overlapped with the movement prediction path is avoided, and the working safety of the industrial robot is improved.
And the second working path is replanned to the obstacle fixed in the obstacle avoidance range of the industrial robot based on the obstacle avoidance distance and the obstacle information, the industrial robot is controlled to operate according to the replanned second working path, the industrial robot is prevented from colliding with the fixed obstacle, and the working safety of the industrial robot is improved.
In addition, the method and the device can predict the track of the obstacle based on the track prediction model so as to judge whether the obstacle moves in the obstacle avoidance range according to the predicted track, and compared with the method and the device for detecting the moving state of the obstacle through a sensor, the method and the device can improve the accuracy of judging the state of the obstacle, improve the accuracy of a re-planned working path when the industrial robot avoids the obstacle, and further improve the working safety of the industrial robot.
Drawings
Fig. 1 is a schematic flow chart of a first embodiment of an obstacle avoidance method of an industrial robot according to the present invention;
fig. 2 is a functional module schematic diagram of an obstacle avoidance device of an industrial robot according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an industrial robot according to an embodiment of the present invention.
The implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
An embodiment of the present invention provides an obstacle avoidance method for an industrial robot, and fig. 1 is a schematic flowchart of a first embodiment of the obstacle avoidance method for an industrial robot according to the present invention.
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application.
In this embodiment, the obstacle avoidance method for an industrial robot is applied to the industrial robot, and the industrial robot in this embodiment may be a multi-joint manipulator or a multi-degree-of-freedom machine device. Specifically, the obstacle avoidance method of the industrial robot of the embodiment includes:
step S10: acquiring historical image data of an obstacle before the obstacle enters an obstacle avoidance range of the industrial robot, and inputting the historical image data into a track prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a predicted track of the obstacle, wherein the obstacle avoidance range is a range formed by taking the position of the industrial robot as a circle center and taking an obstacle avoidance distance of the industrial robot as a radius;
in this embodiment, preset industrial robot need keep away the obstacle distance of keeping away the obstacle to industrial robot's the obstacle range of keeping away is determined as the radius with keeping away the obstacle distance for the centre of a circle to industrial robot place position.
In this embodiment, a person or an object appearing in the obstacle avoidance range of the industrial robot is referred to as an obstacle. After an obstacle appears within the obstacle avoidance range of the industrial robot, image data (hereinafter referred to as historical image data to distinguish) of the obstacle before entering the obstacle avoidance range of the industrial robot is acquired.
Historical image data is input into a track prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a predicted track of the obstacle, and the predicted track can be understood as the track after the obstacle enters the obstacle avoidance range of the industrial robot.
Step S20: detecting whether the obstacle moves in the obstacle avoidance range or not based on the predicted track;
in the embodiment, after the predicted track is obtained, whether the obstacle moves in the obstacle avoidance range is detected based on the predicted track.
Specifically, whether the obstacle moves after entering the obstacle avoidance range is detected based on the predicted track, which may be whether the obstacle moves after entering the obstacle avoidance range is detected based on the predicted track, and the specific detection process may be: detecting whether a predicted track of the obstacle shows the movement of the obstacle after entering the obstacle avoidance range, and if the predicted track shows the movement of the obstacle, determining that the obstacle moves after entering the obstacle avoidance range, namely determining that the obstacle moves in the obstacle avoidance range; and if the predicted track shows that the obstacle does not move, determining that the obstacle does not move after entering the obstacle avoidance range, namely determining that the obstacle does not move in the obstacle avoidance range.
Step S30: if the obstacle moves in the obstacle avoidance range, replanning a first working path based on the obstacle information of the obstacle and the path point of the industrial robot so as to control the industrial robot to operate according to the first working path;
in this embodiment, when it is determined that the obstacle moves within the obstacle avoidance range, the working path is re-planned (hereinafter, referred to as a first working path to show distinction) based on the obstacle information of the obstacle and the path point of the industrial robot, so as to control the industrial robot to perform work according to the re-planned first working path.
In particular embodiments, the obstacle information may include shape information characterizing the size and shape of the obstacle; the obstacle information may also include position information indicative of a relative position of the obstacle with respect to the industrial robot, which may be, for example, an orientation of the obstacle with respect to the industrial robot.
In a specific embodiment, the obstacle information of the obstacle may be acquired by a sensor such as an image sensor, an ultrasonic positioning sensor, and an infrared sensor provided on the industrial robot.
Specifically, in an embodiment, it may be that path points that need to be added are determined based on the obstacle information (hereinafter, referred to as added points to illustrate differentiation), and the first working path of the industrial robot is re-planned according to the added points and the path points, and specifically, the process of determining the added points may be: determining the position of the industrial robot, determining the position of the obstacle according to the position of the industrial robot and the position information of the obstacle, and taking a point with the distance from the position of the obstacle as an obstacle avoidance distance as an additional point; in another embodiment, the yaw angle and the yaw direction of the industrial robot may be determined based on the obstacle information and the moving direction, and the first working path may be re-planned according to the pose and the path point of the industrial robot after the yaw, which is not limited herein.
Step S40: and if the obstacle does not move in the obstacle avoidance range, replanning a second working path based on the obstacle information, the obstacle avoidance distance of the industrial robot and the path point of the industrial robot so as to control the industrial robot to operate according to the second working path.
In this embodiment, if it is determined that the obstacle does not move within the obstacle avoidance range, the working path is re-planned (hereinafter, referred to as a second working path to be distinguished) based on the obstacle information of the obstacle, the obstacle avoidance range of the industrial robot, and the path point of the industrial robot, so as to control the industrial robot to perform the operation according to the re-planned second working path.
Specifically, in an embodiment, an additional point may be determined based on the obstacle information and the obstacle avoidance distance, and the second working path may be re-planned according to the additional point and the path point; in another embodiment, the deflection angle of the industrial robot may be determined based on the obstacle information and the obstacle avoidance distance, and the second working path may be re-planned according to the pose and the path point of the deflected industrial robot, which is not limited herein.
Further, in some possible embodiments, in the step S10: before the step of obtaining historical image data of an obstacle before the obstacle enters the obstacle avoidance range of the industrial robot, the obstacle avoidance method of the industrial robot further comprises the following steps:
step S50: acquiring observed image data of an obstacle with a known motion track, and preprocessing the observed image data;
in this embodiment, image data of an obstacle having a known movement trajectory (hereinafter, referred to as observed image data to distinguish the observed image data) is acquired, and the observed image data is preprocessed.
In particular embodiments, preprocessing observed image data may be data amplification of observed image data to expand sample volume; the pre-processing may also be image data enhancement of the observed image data.
Step S60: establishing a training data set based on the preprocessed observed image data;
a training data set is established based on the pre-processed observed image data to train an initial prediction model (hereinafter referred to as an initial prediction model to illustrate differentiation) through the training data set.
Step S70: inputting the training data set into an initial prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a prediction result;
and inputting the training data set into an initial prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a prediction result.
In a specific embodiment, the target Detection algorithm may be a YOLO (young Only Look one: united, real-Time Object Detection, which Only needs one convolutional neural network operation), specifically, in this embodiment, a YOLO5v algorithm may be adopted, specifically, a network structure of the YOLO5v algorithm includes four parts, i.e., an input end, a backbone network, a neck portion, and an output end, and an attention module is introduced after a first convolutional layer of the backbone network to form an initial prediction model constructed based on an attention mechanism and the target Detection algorithm.
Step S80: and based on a loss function, adjusting model parameters in the initial prediction model according to the prediction result to obtain a track prediction model.
And based on the loss function, adjusting model parameters in the initial prediction model according to the prediction result to obtain a track prediction model.
In this embodiment, historical image data of an obstacle before the obstacle enters an obstacle avoidance range of the industrial robot is acquired, the historical image data is input into a track prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a predicted track of the obstacle, whether the obstacle moves in the obstacle avoidance range is detected based on the predicted track, if the obstacle moves in the obstacle avoidance range, a first working path is re-planned based on obstacle information of the obstacle and path points of the industrial robot, so that the industrial robot is controlled to operate according to the first working path, and if the obstacle does not move in the obstacle avoidance range, a second working path is re-planned based on the obstacle information, the obstacle avoidance distance of the industrial robot and the path points of the industrial robot, so that the industrial robot is controlled to operate according to the second working path.
According to the method, different processing is carried out according to different states of the obstacles, the first working path is replanned for the obstacles moving in the obstacle avoidance range of the industrial robot according to the obstacle information and the path points, the industrial robot is controlled to operate according to the replanned first working path, the industrial robot can adapt to the moving state of the obstacles, collision between the industrial robot and the moving obstacles in subsequent operation due to the fact that the replanned working track and the movement prediction track are overlapped is avoided, and the working safety of the industrial robot is improved.
And the second working path is replanned to the obstacle fixed in the obstacle avoidance range of the industrial robot based on the obstacle avoidance distance and the obstacle information, the industrial robot is controlled to operate according to the replanned second working path, the industrial robot is prevented from colliding with the fixed obstacle, and the working safety of the industrial robot is improved.
Further, a second embodiment of the present invention is proposed based on the first embodiment, and in this embodiment, in the step S30: before the first working path is re-planned based on the obstacle information of the obstacle and the path point of the industrial robot, the obstacle avoidance method of the industrial robot further comprises the following steps:
step S90: detecting whether the predicted track is consistent with the current working path of the industrial robot or not;
in this embodiment, different processing is performed according to different states of the obstacle. Specifically, in the present embodiment, before the work path is re-planned based on the obstacle information of the obstacle and the path point of the industrial robot, it is detected whether the predicted trajectory coincides with the current work path of the industrial robot.
Step A10: if the predicted track is consistent with the current working path, detecting whether the moving direction of the obstacle is the direction close to the industrial robot;
in this embodiment, whether the predicted trajectory is consistent with the current working path of the industrial robot is detected. If the predicted track is consistent with the current working path, whether the moving direction of the obstacle is the direction close to the industrial robot or not is detected, and different processing is carried out on the industrial robot according to whether the moving direction of the obstacle is the direction close to the industrial robot or not.
In a specific embodiment, detecting whether the moving direction of the obstacle is a direction approaching the industrial robot may be performed according to a historical moving state and a predicted trajectory of the obstacle, which is not described herein in detail.
The step S30: replanning a first working path based on obstacle information of the obstacle and path points of the industrial robot may comprise:
step S301: if the moving direction of the obstacle is the direction close to the industrial robot, determining a first deflection angle of the industrial robot based on obstacle information of the obstacle, and controlling the industrial robot to deflect the first deflection angle;
in the present embodiment, after detecting whether the moving direction of the obstacle is the direction approaching the industrial robot, if the moving direction of the obstacle is the direction approaching the industrial robot, the yaw angle of the industrial robot (hereinafter referred to as the first yaw angle for indication) is determined based on the obstacle information, and the industrial robot is controlled to yaw by the first yaw angle.
Step S302: and replanning the first working path according to the pose of the industrial robot deflected by the first deflection angle and the path point of the industrial robot deflected by the first deflection angle.
In this embodiment, after the industrial robot is controlled to deflect by the first deflection angle, the first working path is re-planned according to the pose of the industrial robot after deflecting by the first deflection angle and the path point of the industrial robot after deflecting by the first deflection angle.
Further, in some possible embodiments, in the step a10: after detecting whether the moving direction of the obstacle is the direction approaching the industrial robot, the obstacle avoidance method of the industrial robot further includes:
step A20: if the moving direction of the obstacle is not the direction close to the industrial robot, the moving speed of the obstacle is obtained;
in this embodiment, whether the predicted trajectory is consistent with the current working path of the industrial robot or not is detected, and whether the moving direction of the obstacle is the direction close to the industrial robot or not is detected when the predicted trajectory is consistent with the current working path.
Specifically, in this embodiment, if the moving direction of the obstacle is not the direction approaching the industrial robot, the moving direction of the obstacle is determined to be the direction away from the industrial robot, and the moving speed of the obstacle is acquired at this time.
Step A30: reducing a moving speed of the industrial robot to be less than a moving speed of the obstacle;
in this embodiment, the moving direction of the obstacle is not the direction close to the industrial robot, and the moving speed of the obstacle is obtained. After the moving speed of the obstacle is obtained, the moving speed of the industrial robot is reduced to be smaller than that of the obstacle, and therefore the situation that the industrial robot collides with the obstacle due to the fact that the moving speed of the industrial robot is too fast is avoided.
Further, in an embodiment, when the moving direction of the obstacle is not the direction close to the industrial robot and the moving speed of the obstacle is greater than that of the industrial robot, the moving speed of the industrial robot may be maintained unchanged.
Step A40: and after the distance between the obstacle and the industrial robot with the reduced moving speed is larger than the obstacle avoidance distance of the industrial robot with the reduced moving speed, replanning a third working path based on the moving speed of the industrial robot with the reduced moving speed and the path point of the industrial robot with the reduced moving speed so as to control the industrial robot with the reduced moving speed to operate according to the third working path.
In this embodiment, after the moving speed of the obstacle is obtained, the moving speed of the industrial robot is reduced to be smaller than the moving speed of the obstacle, and after the distance between the obstacle and the industrial robot with the reduced moving speed is greater than the obstacle avoidance distance of the industrial robot, a working path (hereinafter, referred to as a third working path to indicate the division) is re-planned based on the moving speed of the industrial robot with the reduced moving speed and the path point of the industrial robot with the reduced moving speed, so as to control the industrial robot to perform work according to the third working path.
In this embodiment, when the moving direction of barrier is for keeping away from industrial robot's direction, realized industrial robot and kept away from the barrier. Simultaneously be different from industrial robot and plan work path again after deflecting or supplementing the path point, this embodiment industrial robot's work path's change is less, can reduce industrial robot's resource consumption.
Further, in some possible embodiments, in the step S90: after detecting whether the predicted track is consistent with the current working path of the industrial robot or not, the obstacle avoidance method of the industrial robot further comprises the following steps:
step A50: if the predicted track is inconsistent with the current working path, detecting whether the moving direction of the obstacle is a direction close to the current working path;
in this embodiment, it is detected whether the predicted trajectory is consistent with the current working path of the industrial robot. And if the predicted track is inconsistent with the current working path, detecting whether the moving direction of the obstacle is the direction close to the current working path or not so as to carry out different plans on the path of the industrial robot according to the moving direction of the obstacle.
Step A60: and if the moving direction of the obstacle is the direction close to the current working path, replanning a fourth working path based on the obstacle information of the obstacle, the moving direction of the obstacle and the path point of the industrial robot so as to control the industrial robot to work according to the fourth working path.
In this embodiment, whether the predicted trajectory is consistent with the current working path of the industrial robot is detected, and if the predicted trajectory is inconsistent with the current working path, whether the moving direction of the obstacle is a direction approaching the current working path is detected.
Specifically, in this embodiment, when the moving direction of the obstacle is a direction approaching the current working path, the working path is re-planned based on the obstacle information of the obstacle, the moving direction of the obstacle, and the path point of the industrial robot (hereinafter, referred to as a fourth working path for distinction) to control the industrial robot to perform work according to the fourth working path.
In the embodiment, path planning is performed again on the industrial robot when the predicted track is inconsistent with the current working path and the moving direction of the obstacle is the obstacle close to the current working path, so that obstacle avoidance of the industrial robot is realized; the path planning is not carried out on the industrial robot when the predicted track is inconsistent with the current working path and the moving direction of the obstacle is the obstacle far away from the current working path, so that the obstacle avoidance of the industrial robot is realized, and the resource consumption of the industrial robot can be reduced.
Further, in some possible embodiments, in the step a60: replanning a fourth working path based on obstacle information of the obstacle, a moving direction of the obstacle and a path point of the industrial robot, comprising:
step A601: determining a first yaw direction of the industrial robot based on the moving direction of the obstacle;
in this embodiment, the deflection angle and the deflection direction of the industrial robot are determined based on the obstacle information and the obstacle avoidance distance, and the first working path is re-planned according to the pose and the path point of the industrial robot after deflection.
Specifically, in the present embodiment, the yaw direction of the industrial robot is determined based on the moving direction of the obstacle (hereinafter referred to as a first yaw direction for distinction). In a specific embodiment, the first yaw direction of the industrial robot may be a direction opposite to a moving direction of the obstacle to avoid collision of the industrial robot with the obstacle.
Step A602: determining a second deflection angle of the industrial robot based on obstacle information of the obstacle;
in the present embodiment, based on the obstacle information of the obstacle, the second deflection angle of the industrial robot is determined, and the deflection angle of the industrial robot in the first deflection direction is determined (hereinafter referred to as the second deflection angle for clarity).
Step A603: and after controlling the industrial robot to deflect according to the first deflection direction and the second deflection angle, replanning a fourth working path according to the position and the posture of the industrial robot after deflecting the second deflection angle and the path point of the industrial robot after deflecting the second deflection angle.
In this embodiment, after the first deflection direction and the second deflection angle are determined, the industrial robot is controlled to deflect according to the first deflection direction and the second deflection angle, and after the industrial robot is controlled to deflect according to the first deflection direction and the second deflection angle, the fourth working path is re-planned according to the pose of the industrial robot after deflecting by the second deflection angle and the path point of the industrial robot after deflecting by the second deflection angle.
Further, in some possible embodiments, the obstacle information includes shape information representing a size and a shape of the obstacle and position information representing a relative position of the obstacle with respect to the industrial robot. In the present embodiment, in step S40: replanning a second working path based on the obstacle information of the obstacle, the obstacle avoidance range of the industrial robot and the path point of the industrial robot, comprising:
step S401: determining a second yaw direction of the industrial robot based on the position information;
in this embodiment, the deflection angle and the deflection direction of the industrial robot are determined based on the position information determination and the obstacle avoidance distance in the obstacle information, and the second working path is resumed according to the pose and the path point of the deflected industrial robot.
Specifically, in the present embodiment, based on the position information in the obstacle information, the yaw direction of the industrial robot (hereinafter referred to as a second yaw direction for distinction) is determined, and in a specific embodiment, the second yaw direction of the industrial robot may be opposite to the orientation of the obstacle with respect to the industrial robot.
Step S402: determining a third deflection angle of the industrial robot based on the shape information and the obstacle avoidance distance of the industrial robot;
in this embodiment, based on the shape information and the obstacle avoidance distance in the obstacle information, the deflection angle of the industrial robot (hereinafter referred to as a third deflection angle to distinguish the objects) is determined so that the obstacle is not within the obstacle avoidance distance of the industrial robot.
Step S403: and after controlling the industrial robot to deflect according to the second deflection direction and the third deflection angle, replanning a second working path according to the position and the attitude of the industrial robot after deflecting the third deflection angle and the path point of the industrial robot after deflecting the third deflection angle.
In this embodiment, after the second deflection direction and the third deflection angle are determined, the industrial robot deflects according to the second deflection direction and the third deflection angle.
And after controlling the industrial robot to deflect according to the second deflection direction and the third deflection angle, replanning a second working path according to the position and posture of the industrial robot after deflecting the third deflection angle and the path point of the industrial robot after deflecting the third deflection angle.
In this embodiment, different processing is performed according to different movement states of the obstacle, and the third working path is newly planned for an industrial robot whose predicted trajectory is the same as the current working path and whose movement direction of the obstacle is not the direction close to the industrial robot, so as to control the industrial robot to perform work according to the third working path. And replanning the fourth working path for the industrial robot with the predicted track inconsistent with the current working path and the moving direction of the obstacle close to the current working path so as to control the industrial robot to work according to the fourth working path. The phenomenon that the industrial robot collides with a moving obstacle in subsequent operation due to the fact that the re-planned working track and the movement prediction track are overlapped is avoided, and the working safety of the industrial robot is improved.
Meanwhile, the path planning is not carried out on the industrial robot again for the obstacles in other moving states in the obstacle avoidance distance, so that the industrial robot is prevented from avoiding the obstacles, and the resource consumption of the industrial robot is reduced.
In addition, the invention also provides an obstacle avoidance device of an industrial robot, and referring to fig. 2, fig. 2 is a functional module schematic diagram of the obstacle avoidance device of the industrial robot according to the embodiment of the invention. The obstacle avoidance device of the industrial robot comprises:
the system comprises an acquisition module 10, a tracking module and a target detection module, wherein the acquisition module is used for acquiring historical image data of an obstacle before the obstacle enters an obstacle avoidance range of the industrial robot, and inputting the historical image data into a track prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a predicted track of the obstacle, and the obstacle avoidance range is a range formed by taking the position of the industrial robot as a circle center and taking an obstacle avoidance distance of the industrial robot as a radius;
a detecting module 20, configured to detect whether the obstacle moves within the obstacle avoidance range based on the predicted track;
the planning module 30 is configured to, if the obstacle moves within the obstacle avoidance range, re-plan a first working path based on the obstacle information of the obstacle and a path point of the industrial robot, so as to control the industrial robot to perform work according to the first working path;
the planning module 30 is further configured to, if the obstacle does not move within the obstacle avoidance range, re-plan a second working path based on the obstacle information, the obstacle avoidance distance of the industrial robot, and the path point of the industrial robot, so as to control the industrial robot to perform work according to the second working path.
Further, the detecting module 20 is further configured to:
detecting whether the predicted track is consistent with the current working path of the industrial robot or not;
if the predicted track is consistent with the current working path, detecting whether the moving direction of the obstacle is the direction close to the industrial robot;
the planning module 30 is further configured to:
if the moving direction of the obstacle is the direction close to the industrial robot, determining a first deflection angle of the industrial robot based on obstacle information of the obstacle, and controlling the industrial robot to deflect the first deflection angle;
and replanning the first working path according to the pose of the industrial robot deflected by the first deflection angle and the path point of the industrial robot deflected by the first deflection angle.
Further, the planning module 30 is further configured to:
if the moving direction of the obstacle is not the direction close to the industrial robot, acquiring the moving speed of the obstacle;
reducing a moving speed of the industrial robot to be less than a moving speed of the obstacle;
and after the distance between the obstacle and the industrial robot with the reduced moving speed is larger than the obstacle avoidance distance of the industrial robot with the reduced moving speed, replanning a third working path based on the moving speed of the industrial robot with the reduced moving speed and the path point of the industrial robot with the reduced moving speed so as to control the industrial robot with the reduced moving speed to operate according to the third working path.
Further, the planning module 30 is further configured to:
if the predicted track is inconsistent with the current working path, detecting whether the moving direction of the obstacle is a direction close to the current working path;
and if the moving direction of the obstacle is the direction close to the current working path, replanning a fourth working path based on the obstacle information of the obstacle, the moving direction of the obstacle and the path point of the industrial robot so as to control the industrial robot to work according to the fourth working path.
Further, the planning module 30 is further configured to:
determining a first yaw direction of the industrial robot based on the direction of movement of the obstacle;
determining a second deflection angle of the industrial robot based on obstacle information of the obstacle;
and after controlling the industrial robot to deflect according to the first deflection direction and the second deflection angle, replanning a fourth working path according to the position and the posture of the industrial robot after deflecting the second deflection angle and the path point of the industrial robot after deflecting the second deflection angle.
Further, the obstacle information includes shape information representing a size and a shape of the obstacle and position information representing a relative position of the obstacle with respect to the industrial robot;
the planning module 30 is further configured to:
determining a second yaw direction of the industrial robot based on the position information;
determining a third deflection angle of the industrial robot based on the shape information and the obstacle avoidance distance of the industrial robot;
and after controlling the industrial robot to deflect according to the second deflection direction and the third deflection angle, replanning a second working path according to the position and the attitude of the industrial robot after deflecting the third deflection angle and the path point of the industrial robot after deflecting the third deflection angle.
Further, above-mentioned industrial robot's obstacle avoidance device still includes the training module, and the training module is used for:
acquiring observed image data of an obstacle with a known motion trail, and preprocessing the observed image data;
establishing a training data set based on the preprocessed observed image data;
inputting the training data set into an initial prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a prediction result;
and based on a loss function, adjusting model parameters in the initial prediction model according to the prediction result to obtain a track prediction model.
The method comprises the following steps of carrying out the obstacle avoidance method of the industrial robot when each functional module of the obstacle avoidance device of the industrial robot runs.
In addition, the invention also provides an industrial robot. Referring to fig. 3, fig. 3 is a schematic structural diagram of an industrial robot according to an embodiment of the present invention. The industrial robot provided by the embodiment of the invention can be equipment for locally operating an obstacle avoidance system of the industrial robot.
As shown in fig. 3, an industrial robot according to an embodiment of the present invention may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., a Wi-Fi interface).
A memory 1005 is provided on the industrial robot body, and the memory 1005 stores a program that realizes a corresponding operation when executed by the processor 1001. The memory 1005 is also used for storing parameters for use by the industrial robot. The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001 described previously.
It will be appreciated by those skilled in the art that the construction of the industrial robot shown in fig. 3 does not constitute a limitation of the industrial robot and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
As shown in fig. 3, a memory 1005 as a storage medium may include therein an operating system, a network processing module, a user interface module, and an obstacle avoidance program of an industrial robot.
In the industrial robot shown in fig. 3, the processor 1001 may be configured to call an obstacle avoidance program of the industrial robot stored in the memory 1005, and perform the following operations:
acquiring historical image data of an obstacle before the obstacle enters an obstacle avoidance range of the industrial robot, and inputting the historical image data into a track prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a predicted track of the obstacle, wherein the obstacle avoidance range is a range formed by taking the position of the industrial robot as a circle center and taking an obstacle avoidance distance of the industrial robot as a radius;
detecting whether the obstacle moves in the obstacle avoidance range or not based on the predicted track;
if the obstacle moves in the obstacle avoidance range, replanning a first working path based on the obstacle information of the obstacle and the path point of the industrial robot so as to control the industrial robot to operate according to the first working path;
and if the obstacle does not move in the obstacle avoidance range, replanning a second working path based on the obstacle information, the obstacle avoidance distance of the industrial robot and the path point of the industrial robot so as to control the industrial robot to operate according to the second working path.
Further, before the step operation of replanning the first working path based on the obstacle information of the obstacle and the path point of the industrial robot, the processor 1001 may be further configured to call an obstacle avoidance program of the industrial robot stored in the memory 1005, and perform the following operations:
detecting whether the predicted track is consistent with the current working path of the industrial robot or not;
if the predicted track is consistent with the current working path, detecting whether the moving direction of the obstacle is a direction close to the industrial robot or not;
the operation of re-planning a first working path based on obstacle information of the obstacle and a path point of the industrial robot, comprising:
if the moving direction of the obstacle is the direction close to the industrial robot, determining a first deflection angle of the industrial robot based on obstacle information of the obstacle, and controlling the industrial robot to deflect the first deflection angle;
and replanning the first working path according to the pose of the industrial robot deflected by the first deflection angle and the path point of the industrial robot deflected by the first deflection angle.
Further, after the operation of detecting whether the moving direction of the obstacle is a direction approaching the industrial robot, the processor 1001 may be further configured to call an obstacle avoidance program of the industrial robot stored in the memory 1005, and perform the following operations:
if the moving direction of the obstacle is not the direction close to the industrial robot, the moving speed of the obstacle is obtained;
reducing a moving speed of the industrial robot to be less than a moving speed of the obstacle;
and after the distance between the obstacle and the industrial robot with the reduced moving speed is larger than the obstacle avoidance distance of the industrial robot with the reduced moving speed, replanning a third working path based on the moving speed of the industrial robot with the reduced moving speed and the path point of the industrial robot with the reduced moving speed so as to control the industrial robot with the reduced moving speed to operate according to the third working path.
Further, after the operation of detecting whether the predicted trajectory is consistent with the current working path of the industrial robot, the processor 1001 may be further configured to call an obstacle avoidance program of the industrial robot stored in the memory 1005, and perform the following operations:
if the predicted track is inconsistent with the current working path, detecting whether the moving direction of the obstacle is a direction close to the current working path;
and if the moving direction of the obstacle is the direction close to the current working path, replanning a fourth working path based on the obstacle information of the obstacle, the moving direction of the obstacle and the path point of the industrial robot so as to control the industrial robot to work according to the fourth working path.
Further, the operation of replanning a fourth working path based on the obstacle information of the obstacle, the moving direction of the obstacle, and the path point of the industrial robot includes:
determining a first yaw direction of the industrial robot based on the moving direction of the obstacle;
determining a second deflection angle of the industrial robot based on obstacle information of the obstacle;
and after controlling the industrial robot to deflect according to the first deflection direction and the second deflection angle, replanning a fourth working path according to the position and the posture of the industrial robot after deflecting the second deflection angle and the path point of the industrial robot after deflecting the second deflection angle.
Further, the obstacle information includes shape information representing a size and a shape of the obstacle and position information representing a relative position of the obstacle with respect to the industrial robot;
the operation of replanning a second working path based on the obstacle information, the obstacle avoidance distance of the industrial robot, and the path point of the industrial robot includes:
determining a second yaw direction of the industrial robot based on the position information;
determining a third deflection angle of the industrial robot based on the shape information and the obstacle avoidance distance of the industrial robot;
and after controlling the industrial robot to deflect according to the second deflection direction and the third deflection angle, replanning a second working path according to the position and the attitude of the industrial robot after deflecting the third deflection angle and the path point of the industrial robot after deflecting the third deflection angle.
Further, before the operation of acquiring the historical image data of the obstacle before entering the obstacle avoidance range of the industrial robot, the processor 1001 may be further configured to call an obstacle avoidance program of the industrial robot stored in the memory 1005, and perform the following operations:
acquiring observed image data of an obstacle with a known motion trail, and preprocessing the observed image data;
establishing a training data set based on the preprocessed observed image data;
inputting the training data set into an initial prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a prediction result;
and based on a loss function, adjusting model parameters in the initial prediction model according to the prediction result to obtain a track prediction model.
In addition, the invention also provides a computer readable storage medium, the computer readable storage medium stores an obstacle avoidance program of the industrial robot, and the obstacle avoidance program of the industrial robot realizes the steps of the obstacle avoidance method of the industrial robot when being executed by a processor.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or system comprising the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention or the portions contributing to the prior art may be embodied in the form of a software product, which is stored in a computer readable storage medium (such as ROM/RAM, magnetic disk, optical disk) as mentioned above and includes several instructions for enabling an industrial robot (which may be a mobile phone, a computer, a server, or a network device, etc.) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes performed by the present invention or directly or indirectly applied to other related technical fields are also included in the scope of the present invention.
Claims (10)
1. An obstacle avoidance method of an industrial robot is characterized by comprising the following steps:
acquiring historical image data of an obstacle before the obstacle enters an obstacle avoidance range of the industrial robot, and inputting the historical image data into a track prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a predicted track of the obstacle, wherein the obstacle avoidance range is a range formed by taking the position of the industrial robot as a circle center and taking an obstacle avoidance distance of the industrial robot as a radius;
detecting whether the obstacle moves in the obstacle avoidance range or not based on the predicted track;
if the obstacle moves in the obstacle avoidance range, replanning a first working path based on the obstacle information of the obstacle and the path point of the industrial robot so as to control the industrial robot to operate according to the first working path;
and if the obstacle does not move in the obstacle avoidance range, replanning a second working path based on the obstacle information, the obstacle avoidance distance of the industrial robot and the path point of the industrial robot so as to control the industrial robot to operate according to the second working path.
2. An obstacle avoidance method for an industrial robot according to claim 1, wherein before the step of replanning the first working path based on the obstacle information of the obstacle and the path point of the industrial robot, the method further comprises:
detecting whether the predicted track is consistent with the current working path of the industrial robot or not;
if the predicted track is consistent with the current working path, detecting whether the moving direction of the obstacle is the direction close to the industrial robot;
the step of re-planning a first working path based on obstacle information of the obstacle and a path point of the industrial robot comprises:
if the moving direction of the obstacle is the direction close to the industrial robot, determining a first deflection angle of the industrial robot based on obstacle information of the obstacle, and controlling the industrial robot to deflect the first deflection angle;
and replanning the first working path according to the pose of the industrial robot deflected by the first deflection angle and the path point of the industrial robot deflected by the first deflection angle.
3. An obstacle avoidance method for an industrial robot according to claim 2, wherein after said step of detecting whether the moving direction of the obstacle is a direction approaching the industrial robot, the method further comprises:
if the moving direction of the obstacle is not the direction close to the industrial robot, the moving speed of the obstacle is obtained;
reducing a moving speed of the industrial robot to be less than a moving speed of the obstacle;
and after the distance between the obstacle and the industrial robot with the reduced moving speed is larger than the obstacle avoidance distance of the industrial robot with the reduced moving speed, replanning a third working path based on the moving speed of the industrial robot with the reduced moving speed and the path point of the industrial robot with the reduced moving speed so as to control the industrial robot with the reduced moving speed to operate according to the third working path.
4. An obstacle avoidance method for an industrial robot according to claim 2, wherein after said step of detecting whether said predicted trajectory coincides with a current working path of said industrial robot, said method further comprises:
if the predicted track is inconsistent with the current working path, detecting whether the moving direction of the obstacle is a direction close to the current working path;
and if the moving direction of the obstacle is the direction close to the current working path, replanning a fourth working path based on the obstacle information of the obstacle, the moving direction of the obstacle and the path point of the industrial robot so as to control the industrial robot to work according to the fourth working path.
5. An obstacle avoidance method for an industrial robot according to claim 4, wherein the step of replanning a fourth working path based on the obstacle information of the obstacle, the moving direction of the obstacle and the path point of the industrial robot comprises:
determining a first yaw direction of the industrial robot based on the moving direction of the obstacle;
determining a second deflection angle of the industrial robot based on obstacle information of the obstacle;
and after controlling the industrial robot to deflect according to the first deflection direction and the second deflection angle, replanning a fourth working path according to the position and the posture of the industrial robot after deflecting the second deflection angle and the path point of the industrial robot after deflecting the second deflection angle.
6. An obstacle avoidance method for an industrial robot according to claim 1, wherein the obstacle information includes shape information representing a size and a shape of the obstacle and position information representing a relative position of the obstacle with respect to the industrial robot;
the step of replanning a second working path based on the obstacle information, the obstacle avoidance distance of the industrial robot and the path point of the industrial robot comprises:
determining a second yaw direction of the industrial robot based on the position information;
determining a third deflection angle of the industrial robot based on the shape information and the obstacle avoidance distance of the industrial robot;
and after controlling the industrial robot to deflect according to the second deflection direction and the third deflection angle, replanning a second working path according to the position and the attitude of the industrial robot after deflecting the third deflection angle and the path point of the industrial robot after deflecting the third deflection angle.
7. An obstacle avoidance method for an industrial robot according to any of claims 1 to 6, wherein prior to said step of acquiring historical image data of an obstacle before entering an obstacle avoidance range of the industrial robot, said method further comprises:
acquiring observed image data of an obstacle with a known motion track, and preprocessing the observed image data;
establishing a training data set based on the preprocessed observed image data;
inputting the training data set into an initial prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a prediction result;
and based on a loss function, adjusting model parameters in the initial prediction model according to the prediction result to obtain a track prediction model.
8. The utility model provides an industrial robot keeps away barrier device which characterized in that, industrial robot's keeps away barrier device includes:
the system comprises an acquisition module, a tracking module and a target detection module, wherein the acquisition module is used for acquiring historical image data of an obstacle before the obstacle enters an obstacle avoidance range of the industrial robot, and inputting the historical image data into a track prediction model constructed based on an attention mechanism and a target detection algorithm to obtain a predicted track of the obstacle, and the obstacle avoidance range is a range formed by taking the position of the industrial robot as a circle center and taking an obstacle avoidance distance of the industrial robot as a radius;
the detection module is used for detecting whether the obstacle moves in the obstacle avoidance range or not based on the predicted track;
the planning module is used for replanning a first working path based on the obstacle information of the obstacle and the path point of the industrial robot if the obstacle moves in the obstacle avoidance range so as to control the industrial robot to operate according to the first working path;
and the planning module is further used for re-planning a second working path based on the obstacle information, the obstacle avoidance distance of the industrial robot and the path point of the industrial robot if the obstacle does not move in the obstacle avoidance range, so as to control the industrial robot to operate according to the second working path.
9. An industrial robot, characterized in that it comprises: memory, a processor and an obstacle avoidance program for an industrial robot stored on said memory and being operable on said processor, said obstacle avoidance program for an industrial robot being configured to implement the steps of the obstacle avoidance method for an industrial robot according to any of the claims 1 to 7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon an obstacle avoidance program of an industrial robot, which when executed by a processor implements the steps of the obstacle avoidance method of an industrial robot according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310023942.0A CN115781693B (en) | 2023-01-09 | 2023-01-09 | Obstacle avoidance method and device for industrial robot, industrial robot and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310023942.0A CN115781693B (en) | 2023-01-09 | 2023-01-09 | Obstacle avoidance method and device for industrial robot, industrial robot and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115781693A true CN115781693A (en) | 2023-03-14 |
| CN115781693B CN115781693B (en) | 2023-05-26 |
Family
ID=85428779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310023942.0A Active CN115781693B (en) | 2023-01-09 | 2023-01-09 | Obstacle avoidance method and device for industrial robot, industrial robot and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115781693B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942181A (en) * | 2019-11-13 | 2020-03-31 | 北京三快在线科技有限公司 | Method and device for predicting obstacle track |
| CN111376253A (en) * | 2018-12-29 | 2020-07-07 | 深圳市优必选科技有限公司 | Robot route planning method and device, robot and safety management |
| CN111626097A (en) * | 2020-04-09 | 2020-09-04 | 吉利汽车研究院（宁波）有限公司 | Method and device for predicting future trajectory of obstacle, electronic equipment and storage medium |
| CN112651374A (en) * | 2021-01-04 | 2021-04-13 | 东风汽车股份有限公司 | Future trajectory prediction method based on social information and automatic driving system |
| US20210201504A1 (en) * | 2019-12-31 | 2021-07-01 | Baidu Usa Llc | Vehicle trajectory prediction model with semantic map and lstm |
| CN114152257A (en) * | 2021-10-21 | 2022-03-08 | 南京航空航天大学 | Ship prediction navigation method based on attention mechanism and environment perception LSTM |
| CN114647248A (en) * | 2022-05-23 | 2022-06-21 | 风林科技(深圳)有限公司 | Robot obstacle avoidance method, electronic device and readable storage medium |
-
2023
- 2023-01-09 CN CN202310023942.0A patent/CN115781693B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111376253A (en) * | 2018-12-29 | 2020-07-07 | 深圳市优必选科技有限公司 | Robot route planning method and device, robot and safety management |
| CN110942181A (en) * | 2019-11-13 | 2020-03-31 | 北京三快在线科技有限公司 | Method and device for predicting obstacle track |
| US20210201504A1 (en) * | 2019-12-31 | 2021-07-01 | Baidu Usa Llc | Vehicle trajectory prediction model with semantic map and lstm |
| CN111626097A (en) * | 2020-04-09 | 2020-09-04 | 吉利汽车研究院（宁波）有限公司 | Method and device for predicting future trajectory of obstacle, electronic equipment and storage medium |
| CN112651374A (en) * | 2021-01-04 | 2021-04-13 | 东风汽车股份有限公司 | Future trajectory prediction method based on social information and automatic driving system |
| CN114152257A (en) * | 2021-10-21 | 2022-03-08 | 南京航空航天大学 | Ship prediction navigation method based on attention mechanism and environment perception LSTM |
| CN114647248A (en) * | 2022-05-23 | 2022-06-21 | 风林科技(深圳)有限公司 | Robot obstacle avoidance method, electronic device and readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王唯鉴等: "移动机器人行人避让策略强化学习研究" * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115781693B (en) | 2023-05-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108762264B (en) | Dynamic obstacle avoidance method of robot based on artificial potential field and rolling window | |
| US10759051B2 (en) | Architecture and methods for robotic mobile manipulation system | |
| Fox et al. | The dynamic window approach to collision avoidance | |
| US5570285A (en) | Method and apparatus for avoiding obstacles by a robot | |
| JP2019123022A (en) | Robot control device and automatic assembly system | |
| US11604469B2 (en) | Route determining device, robot, and route determining method | |
| US11498587B1 (en) | Autonomous machine motion planning in a dynamic environment | |
| CN103722565A (en) | Self-collision monitoring system for humanoid robot and monitoring method thereof | |
| AU2021101646A4 (en) | Man-machine cooperative safe operation method based on cooperative trajectory evaluation | |
| CN112894758A (en) | Robot cleaning control system, method and device and computer equipment | |
| US11768499B2 (en) | Method for generating intersection point pattern recognition model using sensor data of mobile robot and intersection point pattern recognition system | |
| CN112631269A (en) | Autonomous mobile robot and control program for autonomous mobile robot | |
| US11478932B2 (en) | Handling assembly comprising a handling device for carrying out at least one work step, method, and computer program | |
| CN214846390U (en) | Dynamic environment obstacle avoidance system based on automatic guided vehicle | |
| Chinag et al. | Robot navigation in dynamic environments using fuzzy logic and trajectory prediction table | |
| CN113848893A (en) | Robot navigation method, device, equipment and storage medium | |
| CN115781693B (en) | Obstacle avoidance method and device for industrial robot, industrial robot and storage medium | |
| Nasti et al. | Obstacle avoidance during robot navigation in dynamic environment using fuzzy controller | |
| CN114847809B (en) | Environment exploration method and device for cleaning robot, cleaning robot and medium | |
| Palm et al. | Fuzzy Modeling and Control for Intention Recognition in Human-robot Systems. | |
| Hong et al. | Mobile robot control architecture for reflexive avoidance of moving obstacles | |
| Tzafestas | Teleplanning by human demonstration for VR-based teleoperation of a mobile robotic assistant | |
| CN112757274B (en) | Human-computer cooperative operation oriented dynamic fusion behavior safety algorithm and system | |
| Huang et al. | CEASE: Collision-Evaluation-based Active Sense System for Collaborative Robotic Arms | |
| Kang et al. | Real-time human motion estimation for human robot collaboration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |