Collision detection and obstacle avoidance method and device for industrial robot and server

Abstract

The invention discloses a collision detection and obstacle avoidance method and device for an industrial robot and a server, and belongs to the technical field of robot collision detection. The method comprises the steps of determining the safety distance of the industrial robot; determining a parallel surface which takes the central point of the industrial robot as a circle center and the safe distance as a radius and is parallel to the driving surface of the industrial robot as a detection area; when the actual obstacle enters the detection area, motion information of the industrial robot and the actual obstacle is obtained, and collision detection is carried out; whether the industrial robot collides with the actual obstacle or not is judged according to the collision detection result, and if yes, an obstacle avoidance strategy is adopted for obstacle avoidance. According to the method, the industrial robot can at least predict possible collision in advance within a certain reaction time, so that effective and accurate obstacle avoidance of the industrial robot is achieved, and the situation that the industrial robot is damaged due to the fact that obstacle avoidance is not timely is avoided.

Description

Technical Field

[0001] The present application relates to the technical field of robot collision detection, and in particular to a collision detection and obstacle avoidance method, device and server for an industrial robot. Background Art

[0002] An industrial robot is an automatically controlled, reprogrammable, multi-purpose automation device that can realize various automatic execution functions through its own power and control capabilities. It can be used to replace manpower to complete some tasks. It plays an increasingly important role in today's society and is used more and more widely.

[0003] In actual working scenarios, industrial robots are bound to encounter obstacles. How to achieve collision detection and obstacle avoidance is an urgent problem to be solved. Existing collision detection methods include bounding box detection method, separating axis theorem detection method, depth buffer detection method, ray casting detection method and grid collision detection method.

[0004] These detection methods all perform detection when the industrial robot is about to collide with an obstacle, which may result in the industrial robot failing to avoid the obstacle in time and being damaged, and fail to achieve effective and accurate obstacle avoidance. Summary of the invention

[0005] The embodiments of the present application provide a collision detection and obstacle avoidance method, device and server for an industrial robot, which can solve the problem that the existing detection method may cause the industrial robot to fail to avoid obstacles in time and be damaged, and cannot achieve effective and accurate obstacle avoidance.

[0006] In order to achieve the above object, the technical solution of the embodiment of the present invention is:

[0007] In a first aspect, an embodiment of the present invention provides a collision detection and obstacle avoidance method for an industrial robot, comprising:

[0008] Determine safe distances for industrial robots;

[0009] Determine a detection area that is a plane parallel to the driving plane of the industrial robot and has a center point of the industrial robot as the center and a safety distance as the radius;

[0010] When an actual obstacle enters the detection area, obtaining motion information of the industrial robot and the actual obstacle and performing collision detection;

[0011] It is determined whether the industrial robot will collide with the actual obstacle according to the collision detection result, and if a collision occurs, an obstacle avoidance strategy is adopted to avoid the obstacle.

[0012] In combination with the first aspect, in a possible implementation manner, determining the safety distance of the industrial robot includes: determining the safety distance of the industrial robot includes:

[0013] The safety distance of the industrial robot is determined according to the maximum speed of the industrial robot, the maximum speed of an expected obstacle that may appear in the working scene of the industrial robot, and a preset reaction time.

[0014] In combination with the first aspect, in a possible implementation manner, the acquiring motion information of the industrial robot and the actual obstacle and performing collision detection includes:

[0015] Acquire a first movement speed and a first movement direction of the industrial robot, and generate two first line segments parallel to the first movement direction and having a length of a safety distance with two overall widest points of the industrial robot in the first movement direction as vertices;

[0016] Acquire the distance between the actual obstacle and the industrial robot, and the second movement speed and the second movement direction of the actual obstacle;

[0017] Generate a point cloud model image of the actual obstacle, and use the two widest points of the point cloud model image in the second motion direction as vertices to generate two second line segments parallel to the second motion direction and having a length of a safety distance;

[0018] A circle with the two first line segments, the front face of the industrial robot, and the center point of the industrial robot as the center and the safety distance as the radius forms a first area; a circle with the two second line segments, the front face of the actual obstacle, and the center point of the industrial robot as the center and the safety distance as the radius forms a second area. It is analyzed whether the first area and the second area overlap in the detection area.

[0019] In combination with the first aspect, in a possible implementation manner, obtaining the distance between the actual obstacle and the industrial robot, and the second movement speed and the second movement direction of the actual obstacle includes:

[0020] Using an onboard depth camera of the industrial robot to obtain the distance between the actual obstacle and the industrial robot;

[0021] A second movement speed of the actual obstacle is calculated based on the moving distance and time interval between two frames of the actual obstacle acquired by the airborne depth camera;

[0022] The second movement direction of the actual obstacle is obtained according to the movement state or the change of the feature point of the actual obstacle between two frames acquired by the airborne depth camera.

[0023] In combination with the first aspect, in a possible implementation, judging whether the industrial robot will collide with the actual obstacle according to the collision detection result, and adopting an obstacle avoidance strategy to avoid the obstacle if a collision occurs, includes:

[0024] When the first movement direction of the industrial robot is parallel to the second movement direction of the actual obstacle, the first area and the second area overlap in the detection area, the actual obstacle is located in front of the industrial robot and the first movement speed is greater than the second movement speed, or the actual obstacle is located behind the industrial robot and the first movement speed is less than the second movement speed, then if the current movement state is maintained in the detection area, the industrial robot and the actual obstacle will collide, and the obstacle avoidance strategy is to change the movement trajectory of the industrial robot;

[0025] When the first movement direction of the industrial robot is not parallel to the second movement direction of the actual obstacle, the first area overlaps with the second area in the detection area, and the time the industrial robot spends in and out of the overlapping area overlaps with the time the actual obstacle spends in and out of the overlapping area, then if the current movement state is maintained in the detection area, the industrial robot and the actual obstacle will collide, and the obstacle avoidance strategy is to adjust the first movement speed of the industrial robot.

[0026] In combination with the first aspect, in a possible implementation manner, the changing the motion trajectory of the industrial robot includes:

[0027] Determine whether the overlapping area of ​​the first area and the second area is located on the left side, the center, or the right side of the first movement direction of the industrial robot, if it is located on the left side, the industrial robot deflects to the right by a preset deflection angle, if it is located in the center, the industrial robot deflects to the left or right by a preset deflection angle, and if it is located on the right side, the industrial robot deflects to the left by a preset deflection angle;

[0028] The calculation process of the preset deflection angle is as follows: a target point is set on the outside of the actual obstacle where the collision will occur, and the intersection of the second line segment of the actual obstacle on the collision side and the straight line passing through the frontmost point in the actual obstacle contour and perpendicular to the second movement direction is used as a reference point. The target point is separated from the reference point by a preset distance, and the third movement direction and the third movement speed of the target point are consistent with the second movement direction and the second movement speed of the actual obstacle. The calculation formula of the preset deflection angle θ is:

[0029]

[0030] In the formula, v1 is the first movement speed of the industrial robot, v2 is the current second movement speed of the actual obstacle, t is the movement time, l is the distance between the industrial robot and the actual obstacle, and △l is the preset distance between the target point and the outermost edge point of the actual obstacle.

[0031] In combination with the first aspect, in a possible implementation manner, adjusting the first movement speed of the industrial robot includes:

[0032] Identify whether the actual obstacle is another industrial robot. If the actual obstacle is the other industrial robot, and the priority of the other industrial robot is higher than that of the industrial robot, the obstacle avoidance strategy adopted by the industrial robot is deceleration. If the priority of the other industrial robot is lower than that of the industrial robot, the obstacle avoidance strategy adopted by the industrial robot is acceleration. The priority of the other industrial robot is equal to that of the industrial robot. The industrial robot accelerates or decelerates according to the priority from high to low in the direction of south>north>west>east;

[0033] If the actual obstacle is not the other industrial robot, the obstacle avoidance strategy of the industrial robot is to avoid the obstacle according to the priority of acceleration, deceleration or stopping from high to low.

[0034] In a second aspect, another embodiment of the present invention provides a collision detection and obstacle avoidance device for an industrial robot, comprising:

[0035] A first determination module is used to determine a safe distance of the industrial robot;

[0036] A second determination module determines that a parallel plane parallel to the driving plane of the industrial robot with the center point of the industrial robot as the center and the safety distance as the radius is a detection area;

[0037] An acquisition and detection module, used for acquiring motion information of the industrial robot and the actual obstacle and performing collision detection when the actual obstacle enters the detection area;

[0038] The judgment module is used to judge whether the industrial robot will collide with the actual obstacle according to the collision detection result, and if a collision occurs, an obstacle avoidance strategy is adopted to avoid the obstacle.

[0039] In a third aspect, another embodiment of the present invention provides a server, including: a memory and a processor;

[0040] The memory is used to store program instructions;

[0041] The processor is used to execute program instructions in the server, so that the server executes the above-mentioned collision detection and obstacle avoidance method for the industrial robot.

[0042] In a fourth aspect, another embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores executable instructions, and when a computer executes the executable instructions, the above-mentioned collision detection and obstacle avoidance method for an industrial robot can be implemented.

[0043] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0044] The collision detection and obstacle avoidance method of the industrial robot in the embodiment of the present application first determines the safe distance of the industrial robot. Then, the parallel plane parallel to the driving plane of the industrial robot with the center point of the industrial robot as the center and the safe distance as the radius is determined as the detection area. After that, when the actual obstacle enters the detection area, the motion information of the industrial robot and the actual obstacle is obtained and a collision detection is performed. Finally, it is determined whether the industrial robot and the actual obstacle will collide according to the collision detection result. If a collision occurs, an obstacle avoidance strategy is adopted to avoid the obstacle. The method of the present application can be used to determine whether there will be a collision in the future based on the motion state between the current industrial robot and the obstacle. Due to the determination of the safe distance, the industrial robot can at least predict possible collisions in advance within a certain reaction time, and when the actual obstacle enters the detection area, a collision detection is performed in time. If a collision occurs, an obstacle avoidance strategy is adopted in time to avoid the obstacle, thereby realizing effective and accurate obstacle avoidance of the industrial robot, and avoiding the situation where the industrial robot may be damaged due to untimely obstacle avoidance. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0046] Figure 1 A flowchart of a collision detection and obstacle avoidance method for an industrial robot provided in an embodiment of the present application;

[0047] Figure 2 A schematic diagram of safety distance calculation provided in an embodiment of the present application;

[0048] Figure 3 Schematic diagram of collision detection between an industrial robot and an actual obstacle provided in an embodiment of the present application Figure 1 ;

[0049] Figure 4Schematic diagram of collision detection between an industrial robot and an actual obstacle provided in an embodiment of the present application Figure 2 ;

[0050] Figure 5 Schematic diagram of collision detection between an industrial robot and an actual obstacle provided in an embodiment of the present application Figure 3 ;

[0051] Figure 6 A schematic diagram of calculating a preset deflection angle provided in an embodiment of the present application;

[0052] Figure 7 Schematic diagram of the obstacle avoidance strategy provided in the embodiment of the present application Figure 1 ;

[0053] Figure 8 Schematic diagram of the obstacle avoidance strategy provided in the embodiment of the present application Figure 2 ;

[0054] Fig. 9 A schematic diagram of an industrial robot and multiple actual obstacles provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Please refer to Figure 1 As shown, an embodiment of the present invention provides a collision detection and obstacle avoidance method for an industrial robot, including the following steps 1 to 4. The industrial robot can be used for operation in a factory environment.

[0057] Step 1: Determine the safe distance L of the industrial robot.

[0058] Among them, step 1 specifically includes: determining the safe distance L of the industrial robot according to the maximum speed of the industrial robot, the maximum speed of the expected obstacles that may appear in the working scene of the industrial robot, and the preset reaction time T.

[0059] The expected obstacles include other robots, walking personnel, working vehicles, animals, and still objects. Assuming that the maximum speed of the industrial robot is Mm / s, the maximum speed of the expected obstacles that may appear in the working scene of the industrial robot is Nm / s (M>N), and the preset reaction time T is set to 1s (of course, the preset reaction time T can also be 2s, 3s, etc., customized according to actual conditions), that is, the preset reaction time T of the industrial robot about to collide is at least 1s, such as Figure 2 As shown, the safety distance L = L1 + L2 = M × T + N × T = M × 1 + N × 1 = M + N, that is, at the safety distance L, the fastest collision time between the industrial robot and the expected obstacle is 1 second. Of course, since the maximum speed of the industrial robot and the maximum speed of the expected obstacles that may appear in the working scene of the industrial robot are selected when calculating the safety distance L, and in actual work, the speed of the industrial robot and the speed of the expected obstacles that may appear in the working scene of the industrial robot are both less than the maximum speed, the actual collision time is greater than 1 second, which buys more time for obstacle avoidance.

[0060] For example, if the maximum speed of the industrial robot is 1.2m / s, the maximum speed of the expected obstacles that may appear in the working scene of the industrial robot is 1.1m / s, and the preset reaction time is set to 1s, the safety distance L=L1+L2=1.2×1+1.1×1=2.3m, so that when the industrial robot and the actual obstacle are 2.3m apart, the industrial robot enters the detection state, and before the fastest collision, the industrial robot has at least 1s to adopt an obstacle avoidance strategy.

[0061] Step 2: Determine the detection area as a plane parallel to the driving surface of the industrial robot with the center point of the industrial robot as the center and the safety distance as the radius.

[0062] Step 3: When the actual obstacle enters the detection area, the motion information of the industrial robot and the actual obstacle is obtained and collision detection is performed. Specifically, when the actual obstacle enters the detection area, the industrial robot calculates and obtains the motion information of the industrial robot and the actual obstacle through its own onboard depth camera and onboard computer and performs collision detection. Compared with the existing collision detection method, the method of the present application can judge the possibility of future collision between the industrial robot and the obstacle based on the current motion state between the industrial robot and the obstacle. It can indirectly determine that the industrial robot can at least predict possible collisions in advance within the preset reaction time.

[0063] Among them, obtaining the motion information of the industrial robot and the actual obstacle and performing collision detection include:

[0064] Step 31: Obtain the first movement speed and the first movement direction of the industrial robot, such as Figures 3 to 6 As shown, two first line segments parallel to the first movement direction and having a length of a safety distance L are generated respectively with the two widest points of the industrial robot in the first movement direction as vertices.

[0065] Step 32: Obtain the distance between the actual obstacle and the industrial robot, and the second movement speed and second movement direction of the actual obstacle.

[0066] Specifically, step 32 includes:

[0067] Step 321: Use the onboard depth camera of the industrial robot to obtain the actual distance between the obstacle and the industrial robot. Of course, the determination of the safety distance needs to consider the detection distance of the onboard depth camera of the industrial robot and the computing power of the onboard computer to select the most appropriate safety distance L.

[0068] Combining the RGB-D image information of the industrial robot and the intrinsic and extrinsic parameters of the onboard depth camera, the coordinates of the pixel point in the effective world coordinate system under the coordinate The main principle of this process comes from the camera calibration principle and the Gaussian imaging formula in the lens projection model in optics: (u is the object distance, v is the distance, and f is the focal length, which indicates the distance from the focus to the optical center). According to the coordinate formula of the point from the world coordinate system to the pixel coordinate system: Among them, [u, v] is the input pixel coordinate, Z is the depth, the onboard depth camera can provide the value of Z, and the RGB image can obtain the pixel coordinate P uv = [u, v]. Then, according to the internal parameter formula, we can get the coordinates P = [X, Y, Z] in the airborne depth camera coordinates. Then, according to the rotation matrix R and translation vector t of the airborne depth camera, we can get the three-dimensional coordinates P of the point in the world coordinate system. w =[X w , Y w , Z w ].

[0069] The information obtained by the onboard depth camera of the industrial robot is used to generate a point cloud map corresponding to the actual obstacle. The (u, v) coordinates in the pixel coordinates are obtained through the RGB image, and the depth map directly provides the Z coordinate in the camera coordinates, that is, the distance between the industrial robot where the onboard depth camera is located and the actual obstacle.

[0070] Step 322: Calculate the second movement speed of the actual obstacle according to the distance and time interval between two frames of movement of the actual obstacle acquired by the onboard depth camera.

[0071] Step 323: Obtain a second moving direction of the actual obstacle according to the movement state or feature point change between two frames of the actual obstacle acquired by the onboard depth camera.

[0072] Step 33: Generate a point cloud model image of the actual obstacle, and continue to refer to Figures 3 to 6As shown, two second line segments parallel to the second movement direction and having a length of a safety distance L are generated with the two widest points of the point cloud model image in the second movement direction as vertices. Since the computing resources of the onboard computer are limited, the first area and the second area are composed of line segments having a length of the safety distance L, so that the industrial robot and the actual obstacle will not collide within the preset reaction time, and a certain amount of computing can be reduced, and the computing resources of the onboard computer are sufficient. Step 34: Two first line segments, the front side of the industrial robot (here, the front side is the side facing the direction of movement of the industrial robot; if the industrial robot moves forward, the front side is the front of the industrial robot; if the industrial robot moves backward, the front side is the back of the industrial robot), and a circle with the center point of the industrial robot as the center and the safety distance as the radius form a first area D1; two second line segments, the front side of the actual obstacle (here, the front side is the side facing the direction of movement of the actual obstacle; if the actual obstacle moves forward, the front side is the front of the actual obstacle; if the actual obstacle moves backward, the front side is the back of the actual obstacle), and a circle with the center point of the industrial robot as the center and the safety distance as the radius form a second area D2; analyze whether the first area D1 and the second area D2 overlap in the detection area.

[0073] Step 4: Determine whether the industrial robot will collide with the actual obstacle based on the collision detection results. If a collision occurs, an obstacle avoidance strategy is adopted to avoid the obstacle.

[0074] Specifically, step 4 includes:

[0075] like Figure 4 As shown, the first movement direction of the industrial robot is parallel to the second movement direction of the actual obstacle. If there is no overlap between the first area D1 and the second area D2, the industrial robot and the actual obstacle continue to maintain the current movement state, and no collision occurs in the detection area. It can be considered that the distance between the actual obstacle and the industrial robot is still "far", and the current state can be regarded as a safe state.

[0076] When the first movement direction of the industrial robot is parallel to the second movement direction of the actual obstacle, the first area D1 and the second area D2 overlap in the detection area (have overlapping areas or overlapping edges, and overlapping edges will produce friction collision), the actual obstacle is located in front of the industrial robot and the first movement speed of the industrial robot is less than the second movement speed of the actual obstacle, or the actual obstacle is located behind the industrial robot and the first movement speed of the industrial robot is greater than the second movement speed of the actual obstacle, then the industrial robot and the actual obstacle will not collide.

[0077] Step 41: Figure 5 , Figure 6As shown, when the first movement direction of the industrial robot is parallel to the second movement direction of the actual obstacle, the first area D1 and the second area D2 overlap in the detection area (have overlapping areas or overlapping edges, and overlapping edges will produce friction and collision), the actual obstacle is located in front of the industrial robot and the first movement speed is greater than the second movement speed, or the actual obstacle is located behind the industrial robot and the first movement speed is less than the second movement speed, then if the current movement state continues to be maintained in the detection area, the industrial robot and the actual obstacle will collide. The obstacle avoidance strategy is to change the motion trajectory of the industrial robot (that is, change the first motion direction, that is, the deflection angle. The deflection angle will vary according to the distance between the objects. When the distance difference is relatively large, the deflection angle is relatively small. A larger deflection angle is required when the distance is relatively close), that is, the obstacle avoidance strategy of changing the motion trajectory of the industrial robot by deflecting the first motion direction of the industrial robot by a preset deflection angle to achieve effective obstacle avoidance.

[0078] Among them, changing the motion trajectory of the industrial robot includes steps 411 to 412:

[0079] Step 411: Determine whether the overlapping area of ​​the first area D1 and the second area D2 is located on the left, center or right side of the first motion direction of the industrial robot. If it is located on the left side, the industrial robot deflects to the right by a preset deflection angle, such as Figure 6 As shown. Of course, if it is located on the left side, the industrial robot can also deflect to the left by the preset deflection angle, but the angle required for the preset deflection angle will be larger than the angle required for the preset deflection angle when deflecting to the right, and obstacle avoidance will take more time. If it is located in the center, the industrial robot deflects to the left or right by the preset deflection angle (at this time, the size of the preset deflection angle for deflection to the left or right is the same, so deflection to the left or right is the same). If it is located on the right side, the industrial robot deflects to the left by the preset deflection angle. Of course, if it is located on the right side, the industrial robot can also deflect to the right by the preset deflection angle, but the angle required for the preset deflection angle will be larger than the angle required for the preset deflection angle when deflecting to the left, and obstacle avoidance will take more time.

[0080] Step 412: The calculation process of the preset deflection angle is as follows: Figure 6As shown, a target point is set outside the actual obstacle where the collision will occur, and the intersection of the second line segment of the actual obstacle on the collision side and the straight line passing through the frontmost point in the actual obstacle contour and perpendicular to the second movement direction is used as the reference point. The target point and the reference point are separated by a preset distance △l (a suitable distance that can ensure that the industrial robot can safely pass by the side of the actual obstacle. As long as it is ensured that the industrial robot passes the target point when avoiding obstacles in subsequent movements, it is satisfied that the industrial robot will not collide with the actual obstacle). The third movement direction and the third movement speed of the target point are consistent with the second movement direction and the second movement speed of the actual obstacle, and the calculation formula of the preset deflection angle θ is:

[0081]

[0082] Wherein, v1 is the first movement speed of the industrial robot, θ1 is the angle of the current first movement direction of the industrial robot, v2 is the current second movement speed of the actual obstacle, θ2 is the angle of the current second movement direction of the actual obstacle (the actual obstacle and the industrial robot are in the same environment in the factory, and the starting horizontal height is the same, so θ2 at this time starts from the due west direction, that is, the angle between the movement direction and the due west direction is θ2), t is the movement time, l is the distance between the industrial robot and the actual obstacle, and △l is the preset distance between the target point and the outermost edge point of the actual obstacle.

[0083] In practice, the motion states of industrial robots and actual obstacles will constantly change and update, and the obstacle avoidance strategy of the industrial robot needs to be updated according to the latest updated state. Since the calculation is done using the onboard computer and onboard depth camera carried by the industrial robot, compared to the reinforcement learning method (for new environments, reinforcement learning methods require continuous learning, require large computing resources, and have relatively high learning costs. At the same time, their generalization ability is relatively poor. In addition, there are some subjective factors in the design and training process of their algorithms, such as the design of rewards, the selection of hyperparameters, and the adjustment of the experimental process. All of these need to be adjusted based on experience, contain too many subjective factors, are slow, and have poor accuracy), the method for calculating the preset deflection angle in this application is based on the principles of dynamics, has the advantages of accuracy and speed, and is a method for rational use of resources considering the computing resources carried by the industrial robot.

[0084] Figure 7 It shows that the first movement direction of the industrial robot is parallel to the second movement direction of the actual obstacle, the first area and the second area overlap, the overlapping area has overlapping edges, which will cause friction and collision, the overlapping area is located on the right side of the first movement direction of the industrial robot, and the industrial robot deflects to the left by a preset deflection angle to achieve effective obstacle avoidance.

[0085] Figure 8 It shows a schematic diagram in which the first movement direction of the industrial robot is parallel to the second movement direction of the actual obstacle, the first area and the second area overlap, the overlapping area has an overlapping area, the overlapping area is located on the right side of the first movement direction of the industrial robot, and the industrial robot deflects to the left by a preset deflection angle to achieve effective obstacle avoidance.

[0086] The first moving direction of the industrial robot is not parallel to the second moving direction of the actual obstacle. If the first area D1 and the second area D2 do not overlap in the detection area, the industrial robot and the actual obstacle will not collide temporarily.

[0087] Step 42: When the first movement direction of the industrial robot is not parallel to the second movement direction of the actual obstacle, the first area D1 and the second area D2 overlap in the detection area, and the time length of the industrial robot entering and exiting the overlapping area overlaps with the time length of the actual obstacle entering and exiting the overlapping area (calculate whether there is a possibility of collision in the overlapping area based on the first movement speed of the industrial robot, the second movement speed of the actual obstacle, and the distance between the industrial robot and the actual obstacle. For example, assuming that the calculated time length of the industrial robot entering and exiting the overlapping area is 0.5s to 0.8s, if the calculated time length of the actual obstacle entering and exiting the overlapping area is 0.3s to 0.4s, the industrial robot will not collide with the actual obstacle; if the calculated time length of the actual obstacle entering and exiting the overlapping area is 0.6s to 0.7s, the industrial robot will not collide with the actual obstacle; If the time it takes for the obstacle to enter and exit the overlapping area is 0.35s to 0.5s, the industrial robot will collide with the actual obstacle; if the time it takes for the actual obstacle to enter and exit the overlapping area is calculated to be 0.5s to 0.6s, the industrial robot will collide with the actual obstacle; if the time it takes for the actual obstacle to enter and exit the overlapping area is calculated to be 0.8s to 0.9s, the industrial robot will collide with the actual obstacle; if the time it takes for the actual obstacle to enter and exit the overlapping area is calculated to be 0.85s to 1s, the industrial robot will not collide with the actual obstacle. ) If the current motion state is maintained within the detection area, the industrial robot will collide with the actual obstacle, and the obstacle avoidance strategy is to adjust the first motion speed of the industrial robot.

[0088] Wherein, adjusting the first movement speed of the industrial robot includes steps 421 to 422:

[0089] Step 421: Identify whether the actual obstacle is another industrial robot. Specifically, identify whether the actual obstacle that the industrial robot is about to collide with is another industrial robot based on the RGB image. Industrial robots with different priorities have different RGB images (through the onboard depth camera, target detection methods such as yolo can be used to identify whether the actual obstacle is another robot with different priorities, assuming that other industrial robots with different priorities have differences in color or shape, etc.).

[0090] If the actual obstacle is another industrial robot, and the priority of the other industrial robot is higher than this industrial robot (the priority of the industrial robot is its factory setting attribute), then the obstacle avoidance strategy adopted by this industrial robot is deceleration. If the priority of other industrial robots is lower than this industrial robot, then the obstacle avoidance strategy adopted by this industrial robot is acceleration, that is, by changing the speed, the industrial robot and the actual obstacle pass through the overlapping area one after the other. This obstacle avoidance strategy is more efficient. The priority of other industrial robots is equal to this industrial robot, and this industrial robot accelerates or decelerates according to the priority from high to low in the direction of south> north> west> east.

[0091] Specifically, if the priority of other industrial robots is equal to this industrial robot, whether this industrial robot accelerates or decelerates, other industrial robots as actual obstacles will also make the same obstacle avoidance strategy, and the obstacle avoidance strategy will fail. Therefore, for other robots with the same priority, acceleration or deceleration is determined according to the direction. Acceleration or deceleration is performed according to the priority from high to low in the direction of south> north> west> east. For example, if the first movement direction of the industrial robot is north-east, and the second movement direction of other industrial robots with the same priority as actual obstacles is north-west, the obstacle avoidance strategy of this industrial robot is deceleration. If other robots with the same priority also have the same local obstacle avoidance system, the obstacle avoidance strategy they make is acceleration. The first movement direction of the industrial robot is east-south, and the second movement direction of other industrial robots with the same priority as actual obstacles is west-south, then the obstacle avoidance strategy of this industrial robot is deceleration. The first movement direction of the industrial robot is east-south, and the second movement direction of other industrial robots with the same priority as actual obstacles is west-north, then the obstacle avoidance strategy of this industrial robot is deceleration. The first movement direction of the industrial robot is east-south, and the second movement direction of other industrial robots with the same priority as actual obstacles is west-north, then the obstacle avoidance strategy of this industrial robot is deceleration.

[0092] Step 422: If the actual obstacle is not another industrial robot, the obstacle avoidance strategy of this industrial robot is to avoid the obstacle according to the priority of acceleration, deceleration or stopping from high to low. Specifically, when the industrial robot is close to the overlapping area and cannot avoid the obstacle by accelerating, the obstacle avoidance strategy adopted by the industrial robot is deceleration. In the same case, the efficiency of the acceleration obstacle avoidance strategy is higher than the deceleration obstacle avoidance strategy, and the efficiency of the deceleration obstacle avoidance strategy is higher than the direct stop obstacle avoidance strategy (because if it stops directly, it is necessary to consider that the industrial robot stops in advance, or the restart speed of the industrial robot will cause it to be relatively slow).

[0093] The collision detection and obstacle avoidance method of the industrial robot in the embodiment of the present application first determines the safe distance of the industrial robot. Then, the parallel plane parallel to the driving plane of the industrial robot with the center point of the industrial robot as the center and the safe distance as the radius is determined as the detection area. After that, when the actual obstacle enters the detection area, the motion information of the industrial robot and the actual obstacle is obtained and a collision detection is performed. Finally, it is determined whether the industrial robot and the actual obstacle will collide according to the collision detection result. If a collision occurs, an obstacle avoidance strategy is adopted to avoid the obstacle. The method of the present application can be used to determine whether there will be a collision in the future based on the motion state between the current industrial robot and the obstacle. Due to the determination of the safe distance, the industrial robot can at least predict possible collisions in advance within a certain reaction time, and when the actual obstacle enters the detection area, a collision detection is performed in time. If a collision occurs, an obstacle avoidance strategy is adopted in time to avoid the obstacle, thereby realizing effective and accurate obstacle avoidance of the industrial robot, and avoiding the situation where the industrial robot may be damaged due to untimely obstacle avoidance.

[0094] In short, in practice, when the distance between the industrial robot and the obstacle is greater than the safety distance L, that is, the obstacle is outside the detection area, the industrial robot is in a relatively safe state, at least within the next preset reaction time (such as 1s) there is no possibility of collision. If the obstacle outside the detection area changes its motion state, even if it collides with the industrial robot, there is at least a preset reaction time for effective obstacle avoidance.

[0095] When the distance between the industrial robot and the obstacle is less than or equal to the safety distance L, that is, when the obstacle enters the detection area, the industrial robot enters the detection state and starts to implement collision detection. If the actual obstacle in the detection area changes its motion state, the possible collision situation can be calculated based on the motion state and the appropriate obstacle avoidance strategy can be selected.

[0096] At the same time, the status will be continuously updated according to the distance between the industrial robot and the actual obstacle. For example, when the distance between the industrial robot and the actual obstacle is getting closer and closer, and the actual obstacle enters the detection area from outside the detection area, the industrial robot immediately enters the detection state to detect the motion information of the industrial robot and the actual obstacle that has just entered the detection area. For the actual obstacle in the detection area, the industrial robot will always detect its motion information, including the distance between the industrial robot and the actual obstacle, the second motion direction and the second motion speed of the actual obstacle. According to the continuously updated status, the possibility of collision between the industrial robot and the actual obstacle is judged, and then different obstacle avoidance strategies are given.

[0097] When there is more than one actual obstacle in the safety zone, the collision situation is analyzed based on the current actual obstacle and the motion state of the industrial robot: if the actual obstacle may collide with the industrial robot at different times, different obstacle avoidance strategies are adopted for different actual obstacles. This is equivalent to multiple actual obstacles that may collide with the industrial robot one after another. The actual obstacle that may collide with the industrial robot first is processed first, and then the obstacle avoidance strategy for the next actual obstacle that is close is selected based on the state calculation after obstacle avoidance.

[0098] A more complicated situation is that actual obstacles in different states may collide with the industrial robot at the same time in the safe area. At this time, the processing strategy for the industrial robot is to accelerate, decelerate, or stop directly. Because the distance between the actual obstacle and the industrial robot is relatively close, a collision may occur within the next few frames. Therefore, the priority of the obstacle avoidance strategy is to accelerate, decelerate, stop, and change the motion trajectory. The obstacle avoidance strategy gives priority to changing the speed of the industrial robot to avoid collision, thereby achieving relatively higher obstacle avoidance efficiency. Fig. 9 A schematic diagram of an industrial robot and multiple actual obstacles provided in an embodiment of the present application.

[0099] The collision detection and obstacle avoidance method for an industrial robot provided by an embodiment of the present invention predicts the possibility and situation of a collision based on the previous and current motion states, and provides different obstacle avoidance strategies based on the change and update of the motion state and the situation where a collision may occur, thereby achieving effective obstacle avoidance. Through its own onboard depth camera and onboard computer, and using the current motion information of the industrial robot and the actual obstacle area, efficient and accurate collision detection and obstacle avoidance can be achieved under limited computing resources. To a certain extent, the collision between the robot and the obstacle can be predicted in advance to avoid problems such as the robot not having enough time to detect the collision and make appropriate obstacle avoidance due to problems such as close distance or inaccurate measurement.

[0100] This method avoids the problem of different robots in the factory not being able to coordinate operations well due to different systems. It can accurately determine in advance whether there is a possibility of collision. It makes good use of the limited resources of the robot itself to improve efficiency and predict collisions in advance based on previous motion states to achieve effective local obstacle avoidance. The method of the present application can prepare a certain buffer in the detection area through advance monitoring. As long as the direction changes, the obstacle avoidance strategy will also change, thereby improving the robot's obstacle avoidance efficiency in a dynamic environment.

[0101] Another embodiment of the present invention provides a collision detection and obstacle avoidance device for an industrial robot, comprising:

[0102] The first determination module is used to determine the safe distance of the industrial robot.

[0103] The first determination module is specifically used to determine the safe distance of the industrial robot according to the maximum speed of the industrial robot, the maximum speed of the expected obstacles that may appear in the working scene of the industrial robot, and the preset reaction time.

[0104] The second determination module determines that a parallel plane parallel to the driving plane of the industrial robot with the center point of the industrial robot as the center and the safety distance as the radius is the detection area.

[0105] The acquisition and detection module is used to acquire the motion information of the industrial robot and the actual obstacle and perform collision detection when the actual obstacle enters the detection area.

[0106] The acquisition and detection modules specifically include:

[0107] The first acquisition submodule is used to acquire a first movement speed and a first movement direction of the industrial robot, and to generate two first line segments parallel to the first movement direction and having a length of a safety distance L, with the two widest points on the first movement direction of the industrial robot as vertices.

[0108] The second acquisition submodule is used to acquire the distance between the actual obstacle and the industrial robot, and the second movement speed and the second movement direction of the actual obstacle.

[0109] The second acquisition submodule is specifically used to use the onboard depth camera of the industrial robot to obtain the distance between the actual obstacle and the industrial robot; calculate the second movement speed of the actual obstacle based on the moving distance and time interval between two frames of the actual obstacle obtained by the onboard depth camera; obtain the second movement direction of the actual obstacle based on the movement state or feature point change between two frames of the actual obstacle obtained by the onboard depth camera.

[0110] The generation submodule is used to generate a point cloud model image of the actual obstacle, and to generate two second line segments parallel to the second movement direction and with a length of a safety distance L, taking the two widest points of the point cloud model image in the second movement direction as vertices.

[0111] The analysis submodule is used to form a first area with two first line segments, the front of the industrial robot, and the center point of the industrial robot as the center and a circle with a safety distance as the radius, and to form a second area with two second line segments, the front of the actual obstacle, and the center point of the industrial robot as the center and a circle with a safety distance as the radius, and to analyze whether the first area and the second area overlap in the detection area.

[0112] The judgment module is used to judge whether the industrial robot will collide with the actual obstacle based on the collision detection results. If a collision occurs, an obstacle avoidance strategy is adopted to avoid the obstacle.

[0113] The judgment module is specifically used for when the first movement direction of the industrial robot is parallel to the second movement direction of the actual obstacle, the first area and the second area overlap in the detection area, the actual obstacle is located in front of the industrial robot and the first movement speed is greater than the second movement speed, or the actual obstacle is located behind the industrial robot and the first movement speed is less than the second movement speed, then if the current movement state is maintained in the detection area, the industrial robot and the actual obstacle will collide, and the obstacle avoidance strategy is to change the movement trajectory of the industrial robot.

[0114] Among them, changing the motion trajectory of the industrial robot includes: determining whether the overlapping area of ​​the first area and the second area is located on the left, center or right side of the first motion direction of the industrial robot, if it is located on the left side, the industrial robot deflects to the right by a preset deflection angle, if it is located in the center, the industrial robot deflects to the left or right by a preset deflection angle, and if it is located on the right side, the industrial robot deflects to the left by a preset deflection angle; the calculation process of the preset deflection angle is: setting a target point on the outside where the actual obstacle will collide, taking the intersection of the second line segment of the actual obstacle on the collision side and the straight line passing through the frontmost point in the contour of the actual obstacle and perpendicular to the second motion direction as the reference point, the target point is separated from the reference point by a preset distance, the third motion direction and the third motion speed of the target point are consistent with the second motion direction and the second motion speed of the actual obstacle, and the calculation formula of the preset deflection angle θ is:

[0115]

[0116] Wherein, v1 is the first movement speed of the industrial robot, v2 is the current second movement speed of the actual obstacle, t is the movement time, l is the distance between the industrial robot and the actual obstacle, and △l is the preset distance between the target point and the outermost edge point of the actual obstacle.

[0117] The judgment module is also specifically used for when the first movement direction of the industrial robot is not parallel to the second movement direction of the actual obstacle, the first area and the second area overlap in the detection area, and the length of time the industrial robot enters and exits the overlapping area overlaps with the length of time the actual obstacle enters and exits the overlapping area, then if the current movement state is maintained in the detection area, the industrial robot and the actual obstacle will collide, and the obstacle avoidance strategy is to adjust the first movement speed of the industrial robot.

[0118] Among them, adjusting the first movement speed of the industrial robot includes: identifying whether the actual obstacle is another industrial robot. If the actual obstacle is another industrial robot, and the priority of the other industrial robot is higher than this industrial robot, the obstacle avoidance strategy adopted by this industrial robot is deceleration. If the priority of other industrial robots is lower than this industrial robot, the obstacle avoidance strategy adopted by this industrial robot is acceleration. The priority of other industrial robots is equal to this industrial robot. This industrial robot accelerates or decelerates according to the priority from high to low in the direction of south>north>west>east; if the actual obstacle is not another industrial robot, the obstacle avoidance strategy of this industrial robot is to avoid the obstacle according to the priority from high to low of acceleration, deceleration or stopping.

[0119] Another embodiment of the present invention provides a server, comprising: a memory and a processor. The memory is used to store program instructions. The processor is used to execute the program instructions in the server, so that the server executes the above-mentioned collision detection and obstacle avoidance method for the industrial robot.

[0120] Yet another embodiment of the present invention provides a computer-readable storage medium, which stores executable instructions. When a computer executes the executable instructions, the above-mentioned collision detection and obstacle avoidance method for an industrial robot can be implemented.

[0121] The above storage media include but are not limited to random access memory (RAM), read-only memory (ROM), cache, hard disk drive (HDD) or memory card. The memory can be used to store computer program instructions.

[0122] Although the present application provides method operation steps such as embodiments or flow charts, more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in this embodiment is only one way of executing the order of many steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in the order of the method shown in this embodiment or the accompanying drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment).

[0123] The devices or modules described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. For the convenience of description, the above devices are described in various modules according to their functions. When implementing this application, the functions of each module can be implemented in the same or multiple software and / or hardware. Of course, the module that implements a certain function can also be implemented by combining multiple sub-modules or sub-units.

[0124] The method, device or module in the present application can be implemented in the form of a computer-readable program code. The controller can be implemented in any appropriate manner. For example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (English: Application Specific Integrated Circuit; Abbreviation: ASIC), a programmable logic controller and an embedded microcontroller. Examples of controllers include but are not limited to the following microcontrollers: ARC 625D, AtmelAT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included in it for implementing various functions can also be regarded as structures within the hardware component. Or even, the means for realizing various functions may be regarded as both a software module for realizing the method and a structure within a hardware component.

[0125] Some modules in the apparatus of the present application may be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0126] It can be known from the description of the above implementation mode that a person skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary hardware. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, or it can be reflected in the implementation process of data migration. The computer software product can be stored in a storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a mobile terminal, a server, or a network device, etc.) to execute the methods of each embodiment of the present application or some parts of the embodiments.

[0127] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. All or part of this application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, mobile communication terminals, multi-processor systems, microprocessor-based systems, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0128] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some or all of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the present application.

Claims

1. A collision detection and obstacle avoidance method for an industrial robot, characterized in that: include: Determine safe distances for industrial robots; Determine a detection area that is a plane parallel to the driving plane of the industrial robot and has a center point of the industrial robot as the center and a safety distance as the radius; When an actual obstacle enters the detection area, obtaining motion information of the industrial robot and the actual obstacle and performing collision detection; It is determined whether the industrial robot will collide with the actual obstacle according to the collision detection result, and if a collision occurs, an obstacle avoidance strategy is adopted to avoid the obstacle.

2. The collision detection and obstacle avoidance method for an industrial robot according to claim 1, characterized in that: Determining the safe distance of the industrial robot includes: The safety distance of the industrial robot is determined according to the maximum speed of the industrial robot, the maximum speed of an expected obstacle that may appear in the working scene of the industrial robot, and a preset reaction time.

3. The collision detection and obstacle avoidance method for an industrial robot according to claim 1, characterized in that: The obtaining of motion information between the industrial robot and the actual obstacle and performing collision detection includes: Acquire a first movement speed and a first movement direction of the industrial robot, and generate two first line segments parallel to the first movement direction and having a length of a safety distance with two overall widest points of the industrial robot in the first movement direction as vertices; Acquire the distance between the actual obstacle and the industrial robot, and the second movement speed and the second movement direction of the actual obstacle; Generate a point cloud model image of the actual obstacle, and use the two widest points of the point cloud model image in the second motion direction as vertices to generate two second line segments parallel to the second motion direction and having a length of a safety distance; A circle with the two first line segments, the front face of the industrial robot, and the center point of the industrial robot as the center and the safety distance as the radius forms a first area; a circle with the two second line segments, the front face of the actual obstacle, and the center point of the industrial robot as the center and the safety distance as the radius forms a second area. It is analyzed whether the first area and the second area overlap in the detection area.

4. The method for collision detection and obstacle avoidance of an industrial robot according to claim 3, characterized in that: The obtaining of the distance between the actual obstacle and the industrial robot, and the second movement speed and the second movement direction of the actual obstacle includes: Using the onboard depth camera of the industrial robot to obtain the distance between the actual obstacle and the industrial robot; A second movement speed of the actual obstacle is calculated based on the moving distance and time interval between two frames of the actual obstacle acquired by the airborne depth camera; The second movement direction of the actual obstacle is obtained according to the movement state or the change of the feature point of the actual obstacle between two frames acquired by the airborne depth camera.

5. The method for collision detection and obstacle avoidance of an industrial robot according to claim 3, characterized in that: The determining, based on the collision detection result, whether the industrial robot will collide with the actual obstacle, and adopting an obstacle avoidance strategy to avoid the obstacle if a collision occurs, includes: When the first movement direction of the industrial robot is parallel to the second movement direction of the actual obstacle, the first area and the second area overlap in the detection area, the actual obstacle is located in front of the industrial robot and the first movement speed is greater than the second movement speed, or the actual obstacle is located behind the industrial robot and the first movement speed is less than the second movement speed, then if the current movement state is maintained in the detection area, the industrial robot and the actual obstacle will collide, and the obstacle avoidance strategy is to change the movement trajectory of the industrial robot; When the first movement direction of the industrial robot is not parallel to the second movement direction of the actual obstacle, the first area overlaps with the second area in the detection area, and the time the industrial robot spends in and out of the overlapping area overlaps with the time the actual obstacle spends in and out of the overlapping area, then if the current movement state is maintained in the detection area, the industrial robot and the actual obstacle will collide, and the obstacle avoidance strategy is to adjust the first movement speed of the industrial robot.

6. The method for collision detection and obstacle avoidance of an industrial robot according to claim 5, characterized in that: The changing the motion trajectory of the industrial robot comprises: Determine whether the overlapping area of ​​the first area and the second area is located on the left side, the center, or the right side of the first movement direction of the industrial robot, if it is located on the left side, the industrial robot deflects to the right by a preset deflection angle, if it is located in the center, the industrial robot deflects to the left or right by a preset deflection angle, and if it is located on the right side, the industrial robot deflects to the left by a preset deflection angle; The calculation process of the preset deflection angle is as follows: a target point is set on the outside of the actual obstacle where the collision will occur, and the intersection of the second line segment of the actual obstacle on the collision side and the straight line passing through the frontmost point in the actual obstacle contour and perpendicular to the second movement direction is used as a reference point. The target point is separated from the reference point by a preset distance, and the third movement direction and the third movement speed of the target point are consistent with the second movement direction and the second movement speed of the actual obstacle. The calculation formula of the preset deflection angle θ is: In the formula, v1 is the first movement speed of the industrial robot, v2 is the current second movement speed of the actual obstacle, t is the movement time, l is the distance between the industrial robot and the actual obstacle, and △l is the preset distance between the target point and the outermost edge point of the actual obstacle.

7. The collision detection and obstacle avoidance method for an industrial robot according to claim 5 or 6, characterized in that: The adjusting the first movement speed of the industrial robot includes: Identify whether the actual obstacle is another industrial robot. If the actual obstacle is the other industrial robot, and the priority of the other industrial robot is higher than that of the industrial robot, the obstacle avoidance strategy adopted by the industrial robot is deceleration. If the priority of the other industrial robot is lower than that of the industrial robot, the obstacle avoidance strategy adopted by the industrial robot is acceleration. The priority of the other industrial robot is equal to that of the industrial robot. The industrial robot accelerates or decelerates according to the priority from high to low in the direction of south>north>west>east; If the actual obstacle is not the other industrial robot, the obstacle avoidance strategy of the industrial robot is to avoid the obstacle according to the priority of acceleration, deceleration or stopping from high to low.

8. A collision detection and obstacle avoidance device for an industrial robot, characterized in that: include: A first determination module is used to determine a safe distance of the industrial robot; A second determination module determines that a parallel plane parallel to the driving plane of the industrial robot with the center point of the industrial robot as the center and the safety distance as the radius is a detection area; An acquisition and detection module, used for acquiring motion information of the industrial robot and the actual obstacle and performing collision detection when the actual obstacle enters the detection area; The judgment module is used to judge whether the industrial robot will collide with the actual obstacle according to the collision detection result, and if a collision occurs, an obstacle avoidance strategy is adopted to avoid the obstacle.

9. A server, characterized in that: include: Memory and processor; The memory is used to store program instructions; The processor is used to execute program instructions in the server, so that the server executes the collision detection and obstacle avoidance method for an industrial robot as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores executable instructions, and when a computer executes the executable instructions, the collision detection and obstacle avoidance method for an industrial robot as claimed in any one of claims 1 to 7 can be implemented.

Images