Obstacle avoidance system for inspection robot and inspection robot

Abstract

The invention provides an obstacle avoidance system for an inspection robot and the inspection robot, and the system comprises a grid module which represents the working environment of the inspection robot as a two-dimensional grid chart on a preset plane; the channel module is used for calculating the radius of a safety channel for each grid unit according to the distance between the inspection robot and the obstacle; the boundary module is used for determining an expansion boundary of the grid unit by taking the central point of the grid unit as a circle center and the radius of the safety channel as a radius; and the path module is used for searching the shortest path from the starting point to the ending point in the extended boundary by adopting an A algorithm. According to the method, the real-time performance, the accuracy and the robustness of obstacle avoidance of the inspection robot are improved by combining technical means such as two-dimensional grid chart representation, safe channel calculation, extended boundary determination and A algorithm path planning.

Description

Technical Field

[0001] The present application belongs to the field of robot inspection, and in particular, relates to an obstacle avoidance system for an inspection robot and an inspection robot. Background Art

[0002] In the field of industrial automation and intelligent inspection, inspection robots play an increasingly important role. They are widely used in factories, warehouses, data centers, nuclear power plants and other environments to perform tasks such as monitoring, inspection and maintenance. However, these complex and changing working environments are often full of various obstacles, such as equipment, shelves, pipelines, etc., which poses a huge challenge to the autonomous navigation and obstacle avoidance of inspection robots.

[0003] Traditional obstacle avoidance methods, such as direct detection based on ultrasonic, infrared or laser sensors, can achieve obstacle avoidance functions to a certain extent, but they often have problems such as limited detection range, susceptibility to environmental interference, and high computational complexity. Especially in complex environments, these methods often cannot meet the requirements of inspection robots for real-time, accuracy and robustness. Summary of the invention

[0004] The purpose of this application is to overcome the technical problems in the above-mentioned prior art and to provide an obstacle avoidance system for an inspection robot and an inspection robot.

[0005] The present application provides an obstacle avoidance system for an inspection robot, comprising:

[0006] The grid module represents the working environment of the inspection robot as a two-dimensional grid map on a preset plane;

[0007] The channel module calculates the safe channel radius for each grid cell based on the distance between the inspection robot and the obstacle;

[0008] A boundary module, taking the center point of the grid unit as the center of the circle and the radius of the safety channel as the radius, determines the extension boundary of the grid unit;

[0009] The path module uses the A algorithm to search for the shortest path from the starting point to the end point within the extended boundary.

[0010] Optionally, the working environment of the inspection robot is represented as a two-dimensional grid diagram on a preset plane, including:

[0011] The grid unit size is preset according to the size and complexity of the inspection robot's working environment.

[0012] Optionally, a safe corridor radius is calculated for each grid cell, including:

[0013] The radius of the safety passage is calculated according to the shape and size of the obstacle and the size of the inspection robot.

[0014] Optionally, it also includes: updating obstacle information in real time, and recalculating the safe channel width and the optimal trajectory according to the updated obstacle information.

[0015] Optionally, it also includes:

[0016] Set multiple checkpoints on the optimal trajectory to monitor in real time whether the inspection robot moves along the optimal trajectory.

[0017] The present application also provides an inspection robot, including an obstacle avoidance system, the system comprising:

[0018] A module for representing the working environment of the inspection robot as a two-dimensional grid graph on a preset plane;

[0019] A module that calculates the safe passage radius for each grid cell based on the distance between the inspection robot and the obstacle;

[0020] A module for determining an extended boundary of the grid unit with the center point of the grid unit as the center of the circle and the radius of the safety passage as the radius;

[0021] The A algorithm is used to search for the shortest path from the starting point to the end point within the extended boundary, and is used as a module for the moving trajectory of the inspection robot.

[0022] Optionally, a module for representing the working environment of the inspection robot as a two-dimensional grid diagram on a preset plane includes:

[0023] The grid cell size is preset according to the size and complexity of the inspection robot's working environment.

[0024] Optionally, a module for calculating the safe corridor radius for each grid cell includes:

[0025] The unit of the safety channel radius is calculated according to the shape and size of the obstacle and the size of the inspection robot.

[0026] Optionally, the obstacle avoidance system further includes:

[0027] A module for updating obstacle information in real time, and a module for recalculating the safe channel width and optimal trajectory based on the updated obstacle information.

[0028] Optionally, the obstacle avoidance system further includes:

[0029] A module for setting multiple checkpoints on the optimal trajectory determined by the A algorithm, and a module for real-time monitoring whether the inspection robot moves along the optimal trajectory.

[0030] The beneficial effects of this application are:

[0031] Invention point 1: Calculation of secure channels

[0032] Invention point 2: Safe channel planning based on safe channel radius

[0033] Invention point 3: Optimal path planning based on safe passage

[0034] The present application provides an obstacle avoidance system for a patrol robot, including: a grid module, which represents the working environment of the patrol robot as a two-dimensional grid map on a preset plane; a channel module, which calculates the safe channel radius for each grid unit according to the distance between the patrol robot and the obstacle; a boundary module, which determines the extended boundary of the grid unit with the center point of the grid unit as the center of the circle and the safe channel radius as the radius; and a path module, which uses the A algorithm to search for the shortest path from the starting point to the end point within the extended boundary. The present application improves the real-time, accuracy and robustness of the patrol robot's obstacle avoidance by combining technical means such as two-dimensional grid map representation, safe channel calculation, extended boundary determination and A algorithm path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of the obstacle avoidance system structure of the inspection robot in this application;

[0036] Figure 2 It is a schematic diagram of the structure of the inspection robot in this application. DETAILED DESCRIPTION

[0037] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that various forms of implementing the present disclosure should not be limited by the embodiments set forth herein. On the contrary, the embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0038] Please refer to Figure 1 As shown, the present application provides an obstacle avoidance system for an inspection robot, comprising:

[0039] The grid module 101 represents the working environment of the inspection robot as a two-dimensional grid map on a preset plane;

[0040] First, the grid module senses the surrounding environment through its onboard sensors (such as cameras, lidars) to obtain the shape, size, and distribution of obstacles. The size of each grid unit is predetermined based on the perceived environmental information and the size and motion characteristics of the inspection robot. After the size of the grid unit is determined, a two-dimensional grid map covering the entire working environment is generated based on the boundaries and shape of the environment. Each grid unit has a unique identifier and stores the coordinates of its center point and whether it contains obstacles.

[0041] The grid is set on a preset plane, and the preset plane is a plane whose height value is the maximum value of the ground height statistics in the surrounding environment.

[0042] For example, the working environment of the grid module is a 10m x 10m square area with some irregular obstacles. The laser radar scans the entire environment to obtain the location and shape information of the obstacles. Considering the size and motion characteristics of the inspection robot, square grid units with a side length of 1m are used for division. In this way, the entire environment will be divided into 10 x 10 = 100 grid units.

[0043] According to the boundaries and shapes of the environment, a 10×10 two-dimensional grid map is generated. Each grid cell has a unique identifier (such as G1, G2, ..., G100) and stores its center point coordinates (such as the center point coordinates of G1 are (0.5, 0.5)). At the same time, according to the scanning results of the lidar, the grid cells containing obstacles are marked.

[0044] The resulting two-dimensional grid image is represented as an image, where each grid cell corresponds to a pixel in the image. Grid cells containing obstacles can be represented by different colors or markers. The length and width of each grid in the two-dimensional grid are preset, and the obstacles, drones and objects are determined based on the grid.

[0045] The channel module 102 calculates the safe channel radius for each grid unit according to the distance between the inspection robot and the obstacle;

[0046] The channel module 102 is responsible for calculating the safe channel radius for each grid unit according to the distance between the inspection robot and the obstacle. The safe channel radius is the minimum distance that the robot needs to maintain during movement to ensure that it will not collide with obstacles.

[0047] For each grid cell occupied by an obstacle, calculate its center point. Determine the edge points of the obstacle in each grid cell. Calculate the distance from the grid center point to each edge point, and select the maximum value as the candidate obstacle radius value for the grid cell.

[0048] Among all grid cells occupied by obstacles, the largest candidate value is selected as the radius of the obstacle, expressed as follows:

[0049]

[0050] Among them, G is the set of grid cells occupied by obstacles, (x c ,y c )The center point of each grid cell is, and P is the set of edge points of the obstacle in each grid cell.

[0051] In a grid environment, this robot radius is a fixed value that is used to ensure that the robot does not collide with obstacles when moving. Specifically, determine the physical radius of the robot, that is, the distance from its outermost point to the center. For safety reasons, add an additional safety margin:

[0052] The calculation of the safe channel radius is based on the following factors: the size of the robot, the size and shape of the obstacle, the robot's motion characteristics (motion speed, acceleration), and the complexity of the environment (narrow channels, dense obstacles).

[0053] The formula for calculating the safe passage radius is as follows:

[0054]

[0055] Among them, k v and k a is the coefficient related to velocity and acceleration, R safe is the radius of the safe passage, R robot is the robot's radius, R obstacle is the radius of the obstacle, v robot is the robot's movement speed,

[0056] a robot is the acceleration of the robot, margin is the additional safety margin, C env is a quantitative indicator of environmental complexity).

[0057] The C env The calculation formula is as follows:

[0058]

[0059] Among them, w N and w D (and w N +w D =1) is the weight of the two factors of narrowness and obstacle density.

[0060] The steps to determine the obstacle radius are as follows:

[0061] Determine which grid cells are occupied by the obstacle. For each grid cell occupied by the obstacle, determine the projected shape of the obstacle in the grid cell. For the obstacle projected shape in each grid cell, calculate the longest distance from the center point of the grid to the edge of the shape as the obstacle radius.

[0062] The boundary module 103 determines the extended boundary of the grid unit with the center point of the grid unit as the center and the radius of the safety channel as the radius;

[0063] Assume that the grid where the obstacle is located is a square grid unit with a side length of 1 meter, and its center point is located at the coordinate (3,3). According to the complexity of the environment and the characteristics of the robot, the radius of the safe channel is calculated to be 0.5 meters. The boundary module 103 draws a circle with a center point of (3,3) meters and a radius of 0.5 meters. This circle defines the extended boundary of the grid unit. Any position outside this boundary is an area where the robot can move safely.

[0064] Furthermore, consider an irregularly shaped grid cell, such as a triangular area, whose center point is calculated by geometric methods and is assumed to be (4, 2.5) meters.

[0065] Similarly, based on the complexity of the environment and the characteristics of the robot, the radius of the safe passage is calculated to be 0.75 meters. The boundary module 103 draws a circle with a radius of 0.75 meters and a center point of (4, 2.5) meters. This extended boundary ensures the safe movement of the robot within the irregular grid unit.

[0066] Furthermore, in a dynamic environment, the size and shape of the grid cells remain unchanged, but the safe passage radius is updated in real time according to the movement of obstacles.

[0067] Assume that at a certain point in time, due to a moving obstacle approaching the grid cell, the radius of the safety channel is reduced from the original 0.5 meter to 0.3 meter. The boundary module 103 will recalculate the expansion boundary according to the new safety channel radius (0.3 meter).

[0068] The path module 104 uses the A algorithm to search for the shortest path from the starting point to the end point within the extended boundary.

[0069] The A algorithm is a heuristic search algorithm that combines the advantages of depth-first search and breadth-first search. It introduces a heuristic evaluation function to guide the search process, thereby efficiently finding the shortest path between two points. The key to the A algorithm lies in its heuristic evaluation function, which usually consists of two parts: the actual cost g(n) and the heuristic cost h(n).

[0070] Actual cost g(n): the actual cost from the starting node to the current node.

[0071] Heuristic cost h(n): the estimated travel cost from the current node to the target node. Commonly used heuristic functions include Euclidean distance and Manhattan distance.

[0072] The A* algorithm calculates the f(n)=g(n)+h(n) value of each node and preferentially selects the node with the smallest f value for expansion, thereby gradually approaching the target node and ultimately finding the shortest path.

[0073] Step 1. In the path module 104, two lists are created: Open List and Closed List. The Open List is used to store nodes to be examined, and the Closed List is used to store nodes that have been examined. The starting point is added to the Open List, and its g value is set to 0, the h value is calculated according to the heuristic function, and the f value is the sum of the g value and the h value.

[0074] Step 2: When the Open List is not empty, select the node with the smallest f value from the Open List as the current node. Check whether the current node is the target node. If so, end the search and trace back from the target node to the starting point to build the shortest path. If the current node is not the target node, add it to the Closed List and examine all its neighboring nodes.

[0075] Step 3: For each neighbor node, calculate its g value, h value, and f value. If the neighbor node is already in the Open List and the newly calculated g value is smaller than the original g value, update its g value, f value, and parent node information. If the neighbor node is not in the Open List, add it to the Open List and set the corresponding g value, h value, and parent node information.

[0076] Step 4: Repeat steps 2 and 3 until the target node is found or the Open List is empty (indicating that the path cannot be found).

[0077] In path planning, the extension boundary is determined by the boundary module based on the center point of the grid cell and the radius of the safe channel. When the path module performs the A* algorithm search within the extension boundary, it ensures that the search process does not exceed this boundary. Before adding a neighbor node to the Open List, check whether the node is within the extension boundary. If it is not within the boundary, the node is ignored and is not added or calculated in the future.

[0078] Assume that in a two-dimensional grid environment, the coordinates of the starting point are (0,0), the coordinates of the end point are (10,10), the side length of the grid unit is 1 meter, and the radius of the safe passage is 0.5 meters. The path module first determines the expansion boundary based on the information provided by the boundary module, and then executes the A* algorithm to search for the shortest path within the boundary. During the search process, the path module considers the center point of each grid unit as a potential path node and selects the optimal expansion direction based on the heuristic evaluation function. Finally, the path module will find a shortest path from the starting point to the end point that is completely within the expansion boundary.

[0079] like Figure 2 As shown, the present application also provides an inspection robot, including an obstacle avoidance system, the obstacle avoidance system including:

[0080] S201, representing the working environment of the inspection robot as a module of a two-dimensional grid diagram on a preset plane;

[0081] S202, a module for calculating the radius of a safe passage for each grid unit according to the distance between the inspection robot and the obstacle;

[0082] S203, a module for determining an extended boundary of the grid unit with the center point of the grid unit as the center of the circle and the radius of the safety passage as the radius;

[0083] S204, using algorithm A to search for the shortest path from the starting point to the end point within the extended boundary, and using the algorithm as a module for the moving trajectory of the inspection robot.

[0084] Furthermore, a module for representing the working environment of the inspection robot as a two-dimensional grid diagram on a preset plane includes:

[0085] The grid cell size is preset according to the size and complexity of the inspection robot's working environment.

[0086] Furthermore, a module for calculating the safe passage radius for each grid cell includes:

[0087] The unit of the safety channel radius is calculated according to the shape and size of the obstacle and the size of the inspection robot.

[0088] Furthermore, the obstacle avoidance system further comprises:

[0089] A module for updating obstacle information in real time, and a module for recalculating the safe channel width and optimal trajectory based on the updated obstacle information.

[0090] Furthermore, the obstacle avoidance system further comprises:

[0091] A module for setting multiple checkpoints on the optimal trajectory determined by the A algorithm, and a module for real-time monitoring whether the inspection robot moves along the optimal trajectory.

[0092] The above are only specific embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An obstacle avoidance system for an inspection robot, characterized in that: include: The grid module represents the working environment of the inspection robot as a two-dimensional grid map on a preset plane; The channel module calculates the safe channel radius for each grid cell based on the distance between the inspection robot and the obstacle; A boundary module, taking the center point of the grid unit as the center of the circle and the radius of the safety channel as the radius, determines the extension boundary of the grid unit; The path module uses the A algorithm to search for the shortest path from the starting point to the end point within the extended boundary.

2. An obstacle avoidance system for an inspection robot according to claim 1, characterized in that: The working environment of the inspection robot is represented as a two-dimensional grid diagram on a preset plane, including: The grid unit size is preset according to the size and complexity of the inspection robot's working environment.

3. The obstacle avoidance system for an inspection robot according to claim 1, characterized in that: Calculate the safe corridor radius for each grid cell, including: The radius of the safety passage is calculated according to the shape and size of the obstacle and the size of the inspection robot.

4. The obstacle avoidance system for an inspection robot according to claim 1, characterized in that: Also includes: Obstacle information is updated in real time, and the safe channel width and optimal trajectory are recalculated based on the updated obstacle information.

5. The obstacle avoidance system for an inspection robot according to claim 1, characterized in that: Also includes: Set multiple checkpoints on the optimal trajectory to monitor in real time whether the inspection robot moves along the optimal trajectory.

6. A patrol robot, characterized in that: Includes an obstacle avoidance system comprising: A module for representing the working environment of the inspection robot as a two-dimensional grid graph on a preset plane; A module that calculates the safe passage radius for each grid cell based on the distance between the inspection robot and the obstacle; A module for determining an extended boundary of the grid unit with the center point of the grid unit as the center of the circle and the radius of the safety passage as the radius; The A algorithm is used to search for the shortest path from the starting point to the end point within the extended boundary, and is used as a module for the moving trajectory of the inspection robot.

7. The inspection robot according to claim 6, characterized in that: The module that represents the working environment of the inspection robot as a two-dimensional grid map on a preset plane includes: The grid cell size is preset according to the size and complexity of the inspection robot's working environment.

8. The inspection robot according to claim 6, characterized in that: A module that calculates the safe corridor radius for each grid cell, including: The unit of the safety channel radius is calculated according to the shape and size of the obstacle and the size of the inspection robot.

9. The inspection robot according to claim 6, characterized in that: The obstacle avoidance system also includes: A module for updating obstacle information in real time, and a module for recalculating the safe channel width and optimal trajectory based on the updated obstacle information.

10. The inspection robot according to claim 6, characterized in that: The obstacle avoidance system also includes: A module for setting multiple checkpoints on the optimal trajectory determined by the A algorithm, and a module for real-time monitoring whether the inspection robot moves along the optimal trajectory.

Images