An artificial intelligence robot path planning method

Abstract

The present invention provides an artificial intelligence robot path planning method, which belongs to the field of path planning and solves the problem of complex path planning. The method is specifically as follows: step S1: acquiring parameter information and position information; step S2: constructing an initial route according to the position information; moving according to the initial route, and performing obstacle avoidance when contacting an obstacle; acquiring the position after obstacle avoidance to obtain a node position; step S3: constructing a connectivity graph according to the node position to perform route planning; acquiring a feasible path in combination with energy capacity; step S4: performing collision detection on the feasible path, performing a waiting operation according to the detection result, and calculating the completion time of the robot; and statistically calculating the route with the shortest completion time to form a final path plan. The present invention provides a route reference for robot movement by planning the robot path, and ensures the safety and stability of the robot movement by using the reference route.

Description

Technical Field

[0001] The present invention discloses an artificial intelligence robot path planning method, which relates to the field of path planning. Background Art

[0002] The existing robot path planning methods have the following shortcomings:

[0003] Obstacle handling is not very real-time: Existing robot path planning methods handle obstacles in advance by directly judging the obstacle's condition and determining how the robot will handle it. This makes it impossible to judge what is happening in real time during the robot's movement.

[0004] Single factor considered: Existing robot path planning methods mainly plan the shortest path, with little consideration of other factors, such as energy consumption along the path and the robot's movement time;

[0005] Path planning results: Most path planning methods focus on planning the path of a single individual, which is not very adaptable. They are unable to cope with the impact of multiple individuals, and the planned path is not comprehensive. Summary of the Invention

[0006] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide an artificial intelligence robot path planning method, aiming to solve the complex problem of path planning.

[0007] In order to achieve the above object, the present invention is implemented through the following technical solution: a path planning method for an artificial intelligence robot, the planning method comprising:

[0008] Step S1: Obtain robot parameter information and obtain the position information of the robot and the target point;

[0009] Step S2: Based on the position information of the robot and the target point, an initial route is constructed; obstacles encountered by the robot during its movement along the initial route are acquired, and obstacle avoidance operations are performed based on the robot's parameter information; the position after obstacle avoidance is acquired to obtain the node position;

[0010] Step S3: Based on the node positions, a connectivity graph is constructed, and a route is planned for the connectivity graph to obtain a traversal route; based on the robot's parameter information, the robot's energy capacity is obtained, and combined with the traversal route, a feasible path for the robot is obtained;

[0011] Step S4: Analyze whether a collision occurs on the robot's feasible path, perform a waiting operation on the robot based on the analysis results, and record the waiting time; calculate the robot's movement time; obtain the completion time based on the waiting time and movement time, calculate the feasible routes based on the completion time, extract the feasible route with the shortest completion time, and plan the path for the robot.

[0012] Furthermore, the specific steps of step S1 are as follows:

[0013] Step S11: Test the battery capacity of the robot multiple times, calculate the average of the test results, and obtain the energy capacity of the robot; obtain the robot's stride height and stride length;

[0014] Step S12: Perform m tests on n related robots to test their moving time t at a distance of jl meters; eliminate outliers in the time t according to the isolation forest algorithm; calculate the mean of the test results to obtain the robot's moving speed sd;

[0015] Step S13: The robot's parameter information is composed of the robot's energy capacity, the robot's leaping height, the robot's stride length, and the robot's moving speed.

[0016] Furthermore, the specific steps of step S2 are as follows:

[0017] Step S21: Based on the position information of the robot and the target point, the position coordinates of the robot and the target point are obtained; a plane rectangular coordinate system is constructed, and the position coordinates of the robot and the target point are marked in the plane rectangular coordinate system; the position coordinates of the robot are marked as the starting position, and the position coordinates of the target point are marked as the end position;

[0018] Step S22: Connect the starting position and the end position with a straight line, and use the line segment between the starting position and the end position as the initial route; the robot moves along the initial route, and when the robot contacts an obstacle, obtains the state information of the obstacle; and performs obstacle avoidance operations based on the robot's parameter information;

[0019] Step S23: Obtain the position after the obstacle avoidance operation is completed, record it as the node position, establish an updated route based on the node position and the end position, and the robot moves according to the updated route until it moves to the end position.

[0020] Furthermore, the specific steps of step S22 are as follows:

[0021] Step S221: measuring the obstacle conditions in the initial route to obtain the obstacle height zh, obstacle width zk, and obstacle length zc;

[0022] Through the robot's parameter information, the robot's crossing height jh and the robot's stride length jk are obtained;

[0023] Obstacles are judged based on their height, width, the robot's stride height, and the robot's stride length:

[0024] If the robot can pass through the obstacle directly, the robot moves according to the initial route;

[0025] If the robot cannot pass through the obstacle directly, it needs to move to a position without obstacles and proceed to step S222;

[0026] Step S222: Obtain the current position of the robot and the position of the obstacle; draw a perpendicular line from the current position of the robot to the obstacle, with the length of the perpendicular line recorded as cx; the point where the perpendicular line intersects the obstacle is the perpendicular point, and using the perpendicular point as the boundary, measure the lengths of both sides of the perpendicular point of the obstacle to obtain the upper margin sbj and the lower margin xbj;

[0027] Connect the robot's current position to the upper and lower nodes of the obstacle respectively; obtain the upper and lower displacements; and calculate the robot's upward deflection angle α based on the triangle formed by the vertical line, the upper margin, and the upper displacement.

[0028] The downward deflection angle β of the robot is calculated based on the triangle formed by the vertical line, the lower margin and the downward displacement;

[0029] The robot moves (cx 2 +cbj 2 ) 1 / 2 , avoid obstacles, the obstacle avoidance route is the upward movement distance; rotate β downward, move (cx 2 +xbj 2 ) 1 / 2 , avoid obstacles, and the obstacle avoidance route is the downward movement distance.

[0030] Furthermore, the specific steps of step S23 are as follows:

[0031] Step S231: Obtaining a node position and an end position; connecting the node position and the end position; obtaining a line segment between the node position and the end position as an updated route; and moving the robot toward the end position according to the updated route.

[0032] Step S232: When the robot encounters an obstacle while moving along the updated route, the obstacle avoidance operation of step S22 is processed, and the route is updated again. At the same time, the node position after obstacle avoidance is recorded until the robot moves to the end point.

[0033] Furthermore, the specific steps of step S3 are as follows:

[0034] Step S31: Obtain node positions and obstacle avoidance routes, and preliminarily establish a connected graph; the node positions constitute graph nodes of the connected graph, and the obstacle avoidance routes form edges of the connected graph;

[0035] Analyze the nodes in the connectivity graph; supplement the connectivity graph based on the analysis results of the nodes;

[0036] Step S32: planning the robot's route according to the connectivity graph; traversing the connectivity graph using a depth-first algorithm;

[0037] The robot's traversal route LXi is obtained according to the traversal results; the length of the traversal route is calculated through the robot's traversal route and the edge weight of the connected graph; the traversal route length CDi is obtained; the traversal route is optimized in combination with the robot's energy capacity to obtain the robot's feasible route.

[0038] Furthermore, the specific steps of step S31 are as follows:

[0039] Step S311: Obtain the starting point position and node position, and directly connect the starting point position and the node position as the robot's movement trajectory; the robot moves according to the movement trajectory. If no obstacles are encountered during the movement or the obstacles encountered can be directly crossed, the node can be directly connected to the starting point, forming an edge of the connected graph. The distance of the robot's movement trajectory is recorded, and the edge weight of the connected graph is obtained;

[0040] Step S312: According to the analysis process between the starting point position and the node position in step S311; similarly, the connectivity between the nodes is judged; the positions of the two nodes are obtained; the two nodes are directly connected, and the robot moves the line between the two nodes as the moving trajectory, and the moving distance is recorded at the same time; if the nodes are connected to each other; the nodes are directly connected to form the edge of the connected graph, the distance of the robot's moving trajectory is recorded, and the edge weight of the connected graph is obtained.

[0041] Furthermore, the specific steps of step S32 are as follows:

[0042] Step S321: Based on the robot's parameter information, the robot's energy capacity ny is obtained, the remaining energy capacity sy is monitored, and the completion value gli of the robot's traversal route is calculated based on the ratio between the remaining energy capacity sy and the energy capacity:

[0043] Step S322: Obtain the length yz of the route traveled by the robot, and calculate the completion value gli of the robot's traversal route based on the proportional relationship between the length yz of the route traveled and the length CDi of the traversed route and the proportional relationship between the remaining energy capacity sy and the energy capacity;

[0044] Step S323: Optimizing the traversal route according to the completion value gli of the robot's traversal route;

[0045] If the completion value of the traversed route gli≥1, it is determined that the route can be completed under the specified energy consumption and the route is retained;

[0046] If the completion value of the traversed route is less than 1, it is determined that the route cannot be completed under the specified energy consumption and the route is excluded;

[0047] The routes that can be completed under the specified energy consumption are counted to obtain the feasible path of the robot.

[0048] Furthermore, the specific steps of step S4 are as follows:

[0049] Step S41: Obtain the intersection of the robot's feasible paths and measure the distance the robot travels to the intersection, which is recorded as the intersection distance xj(j). Obtain the robot's movement speed sd based on the robot's parameter information. Calculate the intersection time pz based on the intersection distance xj(j) and the robot's movement speed sd.

[0050] ;

[0051] If pz=0, all robots passing through the intersection are analyzed to obtain the robot that has collided, and the robot is controlled to wait at the intersection for a waiting time of tt;

[0052] Step S42: Obtain the moving distance kyd of the robot's feasible path, obtain the robot's moving speed sd, calculate the robot's moving time ydt by dividing the moving distance of the robot's feasible path by the robot's moving speed; and calculate the completion time wct by adding the moving time ydt and the waiting time tt.

[0053] Step S43: Traverse the feasible paths of the robot and calculate the completion time wct; according to the calculation results, obtain the shortest completion time, extract the path corresponding to the shortest completion time, and plan the path for the robot.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] Considering multiple factors: the present invention traverses all paths and judges the path by energy capacity. If the energy capacity is insufficient to complete the path movement, the path is deleted; the energy capacity is associated with the path movement; and the movement time is judged at the same time, so that the path planning satisfies both energy usage and the total time to complete the movement.

[0056] Optimized obstacle handling: The present invention uses the robot to obtain obstacles in the moving route in real time, while taking into account the robot's crossing height and stride length, and crosses the obstacles, reducing the time the robot takes to avoid obstacles;

[0057] Unified planning for multiple robots: The present invention analyzes the path planning of multiple robots based on the path planning results of a single robot, determines the collision situation of the robots on the path, and performs waiting operations on the robots according to the collision situation; combines the waiting operation with the movement time to perform path planning for the overall movement time of the robots. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments with reference to the following drawings:

[0059] Figure 1 Schematic diagram of the method of the present invention;

[0060] Figure 2 This is a schematic diagram of the route planning of the present invention;

[0061] Figure 3 Schematic diagram of obstacle avoidance processing of the present invention;

[0062] Figure 4 This is a schematic diagram of node connectivity in the present invention;

[0063] Figure 5 Schematic diagram of the robot route intersection of the present invention. DETAILED DESCRIPTION

[0064] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0065] Example 1

[0066] See also Figure 1 , an artificial intelligence robot path planning method includes:

[0067] Step S1: Obtain robot parameter information and obtain the position information of the robot and the target point;

[0068] Step S11: Using a high-precision testing instrument, the robot's battery capacity is tested multiple times, and the average of the test results is calculated as the robot's energy capacity; the robot's leg flexion and extension movements are tested to obtain the robot's leaping height; and the robot's stride is tested to obtain the robot's stride length.

[0069] Step S12: Perform m tests on n related robots to test their moving time t at a distance of jl meters; eliminate outliers in the time t according to the isolation forest algorithm; calculate the mean of the test results to obtain the robot's moving speed sd;

[0070] ;

[0071] Step S13: The energy capacity of the robot, the leaping height of the robot, the stride length of the robot, and the moving speed of the robot constitute the parameter information of the robot.

[0072] Step S2: Based on the position information of the robot and the target point, an initial route is constructed; obstacles encountered by the robot during its movement along the initial route are acquired, and obstacle avoidance operations are performed based on the robot's parameter information; the position after obstacle avoidance is acquired to obtain the node position;

[0073] Step S21: Based on the position information of the robot and the target point, the position coordinates of the robot and the target point are obtained; a plane rectangular coordinate system is constructed, and the position coordinates of the robot and the target point are marked in the plane rectangular coordinate system; the position coordinates of the robot are marked as the starting position, and the position coordinates of the target point are marked as the end position;

[0074] It should be noted that marking in a rectangular coordinate system means displaying the positional relationship between the robot's position coordinates and the target point's position coordinates in the coordinate system, making the robot's movement route more intuitive.

[0075] See also Figure 2 ; Step S22: Connect the starting position and the end position with a straight line, and use the line segment between the starting position and the end position as the initial route;

[0076] It should be noted that if there are no obstacles between the preset starting position and the end position, the distance moved along the initial route is the shortest. If there are obstacles, the route change is mainly an additional route generated by avoiding the obstacles.

[0077] The robot moves along the initial route. When the robot contacts an obstacle, it obtains the obstacle's status information and performs obstacle avoidance operations based on the robot's parameter information. The details are as follows:

[0078] Step S221: Measure the obstacle conditions in the initial route using the visual sensor to obtain the obstacle height zh, obstacle width zk, and obstacle length zc;

[0079] Through the robot's parameter information, the robot's crossing height jh and the robot's stride length jk are obtained;

[0080] Obstacles are judged based on their height, width, the robot's stride height, and the robot's stride length:

[0081] If the robot can pass through the obstacle directly, the robot moves according to the initial route;

[0082] If the robot cannot pass through the obstacle directly, it needs to move to a location without obstacles;

[0083] See also Figure 3 Step S222: Get the robot's current position and the obstacle's position; draw a perpendicular line from the robot's current position to the obstacle, with the length of the perpendicular line denoted as cx; the point where the perpendicular line intersects the obstacle is the perpendicular point, and using the perpendicular point as the boundary, measure the lengths of both sides of the perpendicular point of the obstacle to obtain the upper margin sbj and the lower margin xbj;

[0084] Connect the robot's current position to the upper and lower nodes of the obstacle respectively; obtain the upper and lower displacements; and calculate the robot's upward deflection angle α based on the triangle formed by the vertical line, the upper margin, and the upper displacement.

[0085] ;

[0086] Similarly, the downward deflection angle β of the robot is calculated based on the triangle formed by the vertical line, the lower margin, and the lower displacement.

[0087] ;

[0088] The robot moves (cx 2 +cbj 2 ) 1 / 2 , avoid obstacles, the obstacle avoidance route is the upward movement distance; rotate β downward, move (cx 2 +xbj 2 ) 1 / 2 , avoid obstacles, and the obstacle avoidance route is the downward movement distance;

[0089] Step S23: Obtain the position after the obstacle avoidance operation is completed, record it as the node position, establish an updated route based on the node position and the end position, and the robot moves along the updated route until it reaches the end position;

[0090] Step S231: Obtaining a node position and an end position; connecting the node position and the end position; obtaining a line segment between the node position and the end position as an updated route; and moving the robot toward the end position according to the updated route.

[0091] Step S232: When the robot encounters an obstacle while moving along the updated route, the robot is processed according to the obstacle avoidance operation in step S22, and the route is updated again. The node position after the obstacle avoidance is recorded until the robot reaches the end point.

[0092] See also Figure 4 Step S3: construct a connectivity graph based on the node positions, perform route planning on the connectivity graph, and obtain a traversal route; obtain the robot's energy capacity based on the robot's parameter information, and obtain a feasible path for the robot based on the traversal route;

[0093] Step S31: Obtain node positions and obstacle avoidance routes, and preliminarily establish a connected graph; the node positions constitute graph nodes of the connected graph, and the obstacle avoidance routes form edges of the connected graph;

[0094] It should be noted that the edges of the connected graph formed by the obstacle avoidance route are directed edges, that is, the subsequent nodes of the connected graph nodes are consistent with the movement direction of the robot;

[0095] Analyze the nodes in the connected graph; the details are as follows:

[0096] Step S311: Obtain the starting point position and node position, and directly connect the starting point position and the node position as the robot's movement trajectory; the robot moves according to the movement trajectory. If no obstacles are encountered during the movement or the obstacles encountered can be directly crossed, the node can be directly connected to the starting point, forming an edge of the connected graph. The distance of the robot's movement trajectory is recorded, and the edge weight of the connected graph is obtained;

[0097] Step S312: Based on the analysis process between the starting point position and the node position in step S311, the connectivity between the nodes is determined in the same way; the positions of the two nodes are obtained; the two nodes are directly connected, and the robot moves along the line between the two nodes as the movement trajectory, while recording the movement distance; if the nodes are connected, the connectivity graph is improved;

[0098] According to the analysis results of the nodes, the connectivity graph is supplemented;

[0099] Step S32: Plan the robot's route based on the connectivity graph; traverse the connectivity graph using a depth-first algorithm; details are as follows:

[0100] def dfs(graph, node, visited):

[0101] visited[node] = True # Mark the current node as visited

[0102] print(node) # Process the current node (e.g. print)

[0103] for neighbor in graph[node]: # traverse all adjacent nodes

[0104] if not visited[neighbor]: # If the adjacent node is not visited

[0105] dfs(graph, neighbor, visited)

[0106] # Initialize access status

[0107] visited = {node: False for node in graph}

[0108] dfs(graph, 'A', visited) #'A' represents the starting point

[0109] It should be noted that DFS is a recursive algorithm or an algorithm that uses an explicit stack. It explores each node as much as possible along the depth direction of the graph until it can no longer proceed, and then backtracks to the previous node to continue exploring other branches.

[0110] According to the traversal results, the robot's traversal route LXi[bl1, bl2, bl3...bli] is obtained; the length of the traversal route is calculated based on the robot's traversal route and the edge weights of the connected graph; the traversal route length CDi[bc1, bc2, bc3...bci] is obtained; according to the robot's parameter information, the robot's energy capacity ny is obtained, the remaining energy capacity sy is monitored, and the completion value gli of the robot's traversal route is calculated based on the proportional relationship between the remaining energy capacity sy and the energy capacity, as follows:

[0111] Obtain the length yz of the robot's route, and calculate the completion value gli of the robot's traversal route based on the proportional relationship between the length yz of the route and the length of the traversed route CDi and the proportional relationship between the remaining energy capacity sy and the energy capacity;

[0112] ;

[0113] It should be noted that: based on the proportional relationship between the length of the route traveled yz and the length of the traversed route CDi, the energy consumption of part of the route is calculated, and the energy consumption of that part of the route is obtained by subtracting the remaining energy capacity sy from the energy capacity; the energy consumption of that part of the route is determined by dividing it by the proportional relationship between energy consumption and energy capacity. For example, if the route length yz is half of the route length, and the energy consumption is less than half of the energy capacity, then the remaining energy capacity can support the robot to reach the end position.

[0114] Optimize the traversal route according to the completion value gli of the robot's traversal route;

[0115] If the completion value of the traversed route gli≥1, it is determined that the route can be completed under the specified energy consumption and the route is retained;

[0116] If the completion value of the traversed route is less than 1, it is determined that the route cannot be completed under the specified energy consumption and the route is excluded;

[0117] The routes that can be completed under the specified energy consumption are counted to obtain the feasible path of the robot.

[0118] Step S4: Analyze whether a collision occurs on the robot's feasible path, perform a waiting operation on the robot based on the analysis results, and record the waiting time; calculate the robot's movement time; obtain the completion time based on the waiting time and movement time, calculate the feasible routes based on the completion time, extract the feasible route with the shortest completion time, and plan the path for the robot.

[0119] Step S41: Please refer to Figure 5 , obtain the intersection point of the robot's feasible path, measure the distance the robot moves to the intersection position, and record it as the intersection distance xj(j); according to the robot's parameter information, obtain the robot's moving speed sd; calculate the intersection time pz based on the intersection distance xj(j) and the robot's moving speed sd;

[0120] ;

[0121] It should be noted that: xj(j) refers to the distance between the starting position and the intersection position of the jth robot passing through the intersection;

[0122] It should be noted that the time it takes for the robot to pass through the intersection is calculated by dividing the intersection distance xj(j) by the robot's moving speed sd. The difference between the times it takes for different robots to pass through the intersection is calculated, and all the differences are multiplied. If the calculated result is equal to 0, it is determined that there is a collision at the intersection.

[0123] If pz=0, all robots passing through the intersection are analyzed to obtain the robot that has collided, and the robot is controlled to wait at the intersection for a waiting time of tt;

[0124] It should be noted that the waiting time is when no robot passes the current intersection, which is equivalent to judging whether there is an obstacle at the current intersection. If there is an obstacle, the robot waits, and moves when there is no obstacle.

[0125] Step S42: Obtain the moving distance kyd of the robot's feasible path, obtain the robot's moving speed sd, calculate the robot's moving time ydt by dividing the moving distance kyd of the robot's feasible path by the robot's moving speed sd; and calculate the completion time wct by adding the moving time ydt to the waiting time tt.

[0126] Step S43: Traverse the feasible paths of the robots and calculate the completion time wct in the same way as steps S41 and S42. For example, when the first robot moves along the first feasible path, its corresponding completion time wct(1,1) is obtained, and when the second robot moves along the first feasible path, its corresponding completion time wct(2,1) is obtained. If wct(2,1) is greater than wct(1,1), the total time taken by the two robots to complete the movement is wct(2,1). The time taken by multiple paths of multiple robots is obtained, and the shortest time to complete the movement is finally obtained.

[0127] According to the calculation results, the shortest completion time is obtained, the path corresponding to the shortest completion time is extracted, and the path planning of the robot is performed.

[0128] The above formulas are all dimensionless and calculated by taking their numerical values. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions. For example, if there are weight coefficients and proportional coefficients, the size of the settings is to quantify each parameter to obtain a specific value, which is convenient for subsequent comparison. Regarding the size of the weight coefficient and the proportional coefficient, as long as it does not affect the proportional relationship between the parameter and the quantized value, it is fine.

[0129] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A path planning method for an artificial intelligence robot, characterized in that: The planning method includes: Step S1: Obtain robot parameter information and obtain the position information of the robot and the target point; Step S2: Based on the position information of the robot and the target point, an initial route is constructed; obstacles encountered by the robot during its movement along the initial route are acquired, and obstacle avoidance operations are performed based on the robot's parameter information; the position after obstacle avoidance is acquired to obtain the node position; Step S3: Based on the node positions, a connectivity graph is constructed, and a route is planned for the connectivity graph to obtain a traversal route; based on the robot's parameter information, the robot's energy capacity is obtained, and combined with the traversal route, a feasible path for the robot is obtained; Step S4: Analyze whether there is a collision on the robot's feasible path, perform a waiting operation on the robot based on the analysis result, and record the waiting time; calculate the robot's movement time; obtain the completion time based on the waiting time and the movement time, calculate the feasible routes based on the completion time, extract the feasible route with the shortest completion time, and perform path planning for the robot; The specific steps of step S1 are as follows: Step S11: Test the battery capacity of the robot multiple times, calculate the average of the test results, and obtain the energy capacity of the robot; obtain the robot's stride height and stride length; Step S12: Perform m tests on n related robots to test their moving time t at a distance of jl meters; eliminate outliers in the time t according to the isolation forest algorithm; calculate the mean of the test results to obtain the robot's moving speed sd; Step S13: The robot's parameter information is composed of the robot's energy capacity, the robot's leaping height, the robot's stride length, and the robot's moving speed.

2. The artificial intelligence robot path planning method according to claim 1, characterized in that: The specific steps of step S2 are as follows: Step S21: Based on the position information of the robot and the target point, the position coordinates of the robot and the target point are obtained; a plane rectangular coordinate system is constructed, and the position coordinates of the robot and the target point are marked in the plane rectangular coordinate system; the position coordinates of the robot are marked as the starting position, and the position coordinates of the target point are marked as the end position; Step S22: Connect the starting position and the end position with a straight line, and use the line segment between the starting position and the end position as the initial route; the robot moves along the initial route, and when the robot contacts an obstacle, obtains the state information of the obstacle; and performs obstacle avoidance operations based on the robot's parameter information; Step S23: Obtain the position after the obstacle avoidance operation is completed, record it as the node position, establish an updated route based on the node position and the end position, and the robot moves according to the updated route until it moves to the end position.

3. The artificial intelligence robot path planning method according to claim 2, characterized in that: The specific steps of step S22 are as follows: Step S221: measuring the obstacle conditions in the initial route to obtain the obstacle height zh, obstacle width zk, and obstacle length zc; Through the robot's parameter information, the robot's crossing height jh and the robot's stride length jk are obtained; Obstacles are judged based on their height, width, the robot's stride height, and the robot's stride length: If the robot can pass through the obstacle directly, the robot moves according to the initial route; If the robot cannot pass through the obstacle directly, it needs to move to a position without obstacles and proceed to step S222; Step S222: Obtain the robot's current position and the obstacle's position; Draw a perpendicular line from the robot's current position to the obstacle, and record the length of the perpendicular line as cx; the point where the perpendicular line intersects the obstacle is the perpendicular point. Using the perpendicular point as the boundary, measure the lengths of both sides of the perpendicular point of the obstacle to obtain the upper margin sbj and the lower margin xbj; Connect the robot's current position to the upper and lower nodes of the obstacle respectively; obtain the upper and lower displacements; and calculate the robot's upward deflection angle α based on the triangle formed by the vertical line, the upper margin, and the upper displacement. The downward deflection angle β of the robot is calculated based on the triangle formed by the vertical line, the lower margin and the downward displacement; The robot moves (cx 2 +sbj 2 ) 1 / 2 , avoid obstacles, the obstacle avoidance route is the upward movement distance; rotate β downward, move (cx 2 +xbj 2 ) 1 / 2 , avoid obstacles, and the obstacle avoidance route is the downward movement distance.

4. The artificial intelligence robot path planning method according to claim 2, characterized in that: The specific steps of step S23 are as follows: Step S231: Obtaining a node position and an end position; connecting the node position and the end position; obtaining a line segment between the node position and the end position as an updated route; and moving the robot toward the end position according to the updated route. Step S232: When the robot encounters an obstacle while moving along the updated route, the robot is processed according to the obstacle avoidance operation of step S22; And update the route again; at the same time, record the node position after obstacle avoidance; until the robot moves to the end point.

5. The artificial intelligence robot path planning method according to claim 1, characterized in that: The specific steps of step S3 are as follows: Step S31: Obtain node positions and obstacle avoidance routes, and preliminarily establish a connected graph; the node positions constitute graph nodes of the connected graph, and the obstacle avoidance routes form edges of the connected graph; Analyze the nodes in the connectivity graph; supplement the connectivity graph based on the analysis results of the nodes; Step S32: planning the robot's route according to the connectivity graph; traversing the connectivity graph using a depth-first algorithm; The robot's traversal route LXi is obtained according to the traversal results; the length of the traversal route is calculated through the robot's traversal route and the edge weight of the connected graph; the traversal route length CDi is obtained; the traversal route is optimized in combination with the robot's energy capacity to obtain the robot's feasible route.

6. The artificial intelligence robot path planning method according to claim 5, characterized in that: The specific steps of step S31 are as follows: Step S311: Obtain the starting point position and node position, and directly connect the starting point position and the node position as the robot's movement trajectory; the robot moves according to the movement trajectory. If no obstacles are encountered during the movement or the obstacles encountered can be directly crossed, the node can be directly connected to the starting point, forming an edge of the connected graph. The distance of the robot's movement trajectory is recorded, and the edge weight of the connected graph is obtained; Step S312: According to the analysis process between the starting point position and the node position in step S311; similarly, the connectivity between the nodes is judged; the positions of the two nodes are obtained; the two nodes are directly connected, and the robot moves the line between the two nodes as the moving trajectory, and the moving distance is recorded at the same time; if the nodes are connected to each other; the nodes are directly connected to form the edge of the connected graph, the distance of the robot's moving trajectory is recorded, and the edge weight of the connected graph is obtained.

7. The artificial intelligence robot path planning method according to claim 5, characterized in that: The specific steps of step S32 are as follows: Step S321: Based on the robot's parameter information, the robot's energy capacity ny is obtained, the remaining energy capacity sy is monitored, and the completion value gli of the robot's traversal route is calculated based on the ratio between the remaining energy capacity sy and the energy capacity: Step S322: Obtain the length yz of the route traveled by the robot, and calculate the completion value gli of the robot's traversal route based on the proportional relationship between the length yz of the route traveled and the length CDi of the traversed route and the proportional relationship between the remaining energy capacity sy and the energy capacity; Step S323: Optimizing the traversal route according to the completion value gli of the robot's traversal route; If the completion value of the traversed route gli≥1, it is determined that the route can be completed under the specified energy consumption and the route is retained; If the completion value of the traversed route is less than 1, it is determined that the route cannot be completed under the specified energy consumption and the route is excluded; The routes that can be completed under the specified energy consumption are counted to obtain the feasible path of the robot.

8. The artificial intelligence robot path planning method according to claim 1, characterized in that: The specific steps of step S4 are as follows: Step S41: Obtain the intersection of the robot's feasible paths and measure the distance the robot travels to the intersection, which is recorded as the intersection distance xj(j). Obtain the robot's movement speed sd based on the robot's parameter information. Calculate the intersection time pz based on the intersection distance xj(j) and the robot's movement speed sd. ； If pz=0, all robots passing through the intersection are analyzed to obtain the robot that has collided, and the robot is controlled to wait at the intersection for a waiting time of tt; Step S42: Obtain the moving distance kyd of the robot's feasible path, obtain the robot's moving speed sd, calculate the robot's moving time ydt by dividing the moving distance of the robot's feasible path by the robot's moving speed; and calculate the completion time wct by adding the moving time ydt and the waiting time tt. Step S43: Traverse the feasible paths of the robot and calculate the completion time wct; according to the calculation results, obtain the shortest completion time, extract the path corresponding to the shortest completion time, and plan the path for the robot.

Images