A path planning method and system for autonomous driving of mining electric shovel

Abstract

The present invention relates to the technical field of path planning for mining electric shovels, and specifically to a path planning method and system for autonomous driving of mining electric shovels, the method comprising starting the operation of the mining electric shovel based on a task sent by a user, obtaining environmental information and current position information of a target area according to sensors on the mining electric shovel, and constructing an environmental map; based on the environmental map, starting point and target end point information, using an improved A* algorithm, performing global path planning to obtain a global optimal path sequence; selecting local target points from the global optimal path sequence; using an improved DWA algorithm to perform local path planning to obtain a local path that bypasses obstacles; and traversing each local target point in turn until the target end point is reached. The present invention solves the path planning problem of mining electric shovels in complex paths, can obtain a safe and efficient path, and can achieve safe obstacle avoidance for dynamic obstacles.

Description

Technical Field

[0001] The present invention belongs to the field of automation technology, and in particular relates to a path planning method and system for autonomous driving of a mining electric shovel. Background Art

[0002] In recent years, with the development of intelligent control technology, autonomous driving has also become a hot topic. In the field of industrial production, due to the particularity of the environment, the environment is often dangerous, which may seriously damage the health of workers. Autonomous driving can not only reduce the incidence of accidents, greatly improve productivity, but also reduce labor costs. Path planning, as an important part of autonomous driving, is the premise and foundation of unmanned autonomous driving.

[0003] For mining electric shovels, due to their complex working environment, there are roads with relatively large slopes and relatively deep depressions, and due to the large mass of the mining electric shovel itself and inconvenient steering, the existing path planning cannot meet the control of the mining electric shovel in complex paths. In path planning, it is not considered that the working environment of the mining electric shovel is relatively complex, there are many slopes, steps and depressions, which may cause the planned path to be unreachable or cause danger; and the existing path planning does not fully consider the adaptive adjustment of the weight of the path evaluation function, resulting in the problems of large search range, large amount of calculation and long planning time in the path planning process; and the movement of dynamic obstacles is not fully considered, resulting in the planned path colliding again, and the optimal path planning cannot be obtained. In order to solve the above problems, the present invention provides a path planning method and system for autonomous driving of mining electric shovels. Summary of the invention

[0004] The object of the present invention is to provide a path planning method and system for autonomous driving of a mining electric shovel.

[0005] The technical solution of the present invention is as follows: A path planning method for autonomous driving of a mining electric shovel comprises the following steps: Step 1: based on a task sent by a user, starting the operation of the mining electric shovel, obtaining environmental information and current position information of a target area according to sensors on the mining electric shovel, and constructing an environmental map;

[0006] Step 2: Based on the environment map, starting point and target end point information, the improved A* algorithm is used to perform global path planning to obtain the global optimal path sequence;

[0007] Step 3: Select a local target point from the global optimal path sequence; use the improved DWA algorithm to perform local path planning to obtain a local path that bypasses obstacles; traverse each local target point in turn until the target end point is reached.

[0008] Preferably, the evaluation function of the improved A* algorithm includes setting the actual cost function and the heuristic cost function of the current path point, and setting the weight of the heuristic cost function to improve the search efficiency of the path; the evaluation function of the improved A* algorithm is: f(n)=g(n)+α(h(n)-kcosβ); wherein g(n) is the actual cost function of the current path point; h(n) is the heuristic cost function; α is the weight of the heuristic cost function, s is the distance from the starting point to the target end point; d is the distance from the current path point to the target end point; k is the set weight, β is the angle between the line connecting the starting point and the current path point and the line connecting the current path point and the target end point; Z is the number of known obstacles.

[0009] Preferably, since the working environment of the mining electric shovel is relatively complex, with many slopes, steps and depressions, the improved A* algorithm improves the actual cost function and the heuristic cost function, and introduces the slope, energy consumption and obstacle span of the current path into the actual cost function and the heuristic cost function. The actual cost function is:

[0010]

[0011] The heuristic cost function is:

[0012]

[0013] Where: n is the current path point, N is the target end point, (x n ,y n ) is the coordinate of the current path point n; is the terrain height of path point n; is the additional energy consumption of the path point n; P n is the obstacle spanning degree of the path point; θ n is the path inclination angle of the path point.

[0014] Preferably, the obstacle spanning degree of the path point is: θ max The maximum path inclination angle that the shovel can climb; Among them, F max is the maximum output power of the electric shovel; m is the mass of the vehicle; g is the gravity coefficient; δ is the rolling coefficient of the electric shovel; The maximum terrain height that the shovel can overcome; Where R is the wheel radius of the shovel; k is the path adhesion coefficient; L 1 is the distance between the center of gravity of the electric shovel and the front wheel of the electric shovel; L is the distance between the front and rear wheels of the electric shovel.

[0015] Preferably, the method comprises selecting a local target point from the global optimal path sequence; using an improved DWA algorithm to perform local path planning to obtain a local path that bypasses obstacles; traversing each local target point in turn until the target end point is reached, specifically comprising: S1 selecting a key turning point from the global optimal path sequence as a local target point; S2 establishing a speed constraint space and an objective function; S3 sampling the speed constraint space through a kinematic model of an electric shovel and generating a predicted path; S4 predicting the trajectory of a dynamic obstacle in real time; S5 evaluating the sampling speeds of multiple groups of predicted paths through an objective function based on the real-time predicted trajectory of the dynamic obstacle to obtain the optimal predicted path and the corresponding speed information; S6 judging whether the local target point is the target end point, and if so, outputting the optimal path; if not, jumping to step S3 and repeating the operation.

[0016] Preferably, a speed constraint space is established to reduce the speed search range; the speed constraint space is: V∈V max ∩V o ∩V r ; where V max is the speed and angular velocity limit of the electric shovel; v min , v max are the minimum and maximum speed respectively; ω min ,ω max is the minimum and maximum value of angular velocity; V o V is the achievable speed limit of the electric shovel; r It is the safe speed limit of the electric shovel;

[0017]

[0018] where v a and ω a are the real-time speed and angular velocity of the shovel; a and a ω is the acceleration and angular acceleration of the shovel; Δt is the sampling period; L min Predict the shortest distance from a waypoint to an obstacle for the current speed.

[0019] Preferably, the objective function is: score =β 1 f h +β 2 f d +β 3 f v +β 4 f o ;f h is the fit cost function between the local path and the global path; f h =180°-|θ t -θ f |, where θ tis the angle between the predicted path point of the shovel and the target end point, θ f The heading angle of the path point predicted by the shovel; this cost function is used to screen out the path points with small deviation between the target angle and the heading angle, so that the forward direction of the shovel points to the target end point; f d The distance cost function between the predicted path point and the target end point for the shovel is: x t and t is the coordinate of the predicted path point, x s and s is the coordinate of the target end point; f v =|v i | is the speed cost function, where v i is the predicted running speed; f o A distance cost from a path point to a dynamic obstacle predicted by the electric shovel, wherein the predicted trajectory of the dynamic obstacle is a Gaussian probability distribution; Where I is the number of dynamic obstacles, and are the standard deviations of the normal probability distribution of the predicted trajectory of the ith dynamic obstacle in the x and y directions, respectively; and are the means of the normal probability distribution of the predicted trajectory of the ith dynamic obstacle in the x and y directions; β 1 , β 2 , β 3 , β 4 They are fit cost coefficient, distance cost coefficient, speed cost coefficient and obstacle cost coefficient respectively.

[0020] Preferably, an adaptive distance cost coefficient is set, and the distance cost coefficient is adaptively adjusted according to the distance between the predicted path point and the target end point. When the electric shovel is far away from the target end point, a larger distance cost coefficient is set, and when the electric shovel is close to the target end point, a smaller distance cost coefficient is set; x c and c is the coordinate of the starting point of the electric shovel; set an adaptive speed cost coefficient, and adaptively adjust the speed cost coefficient by judging the distance between the electric shovel's predicted path point and the obstacle. When the electric shovel's predicted path point is close to the obstacle, set a smaller speed cost coefficient; when the electric shovel's predicted path point is far from the obstacle, set a larger speed cost coefficient to ensure the speed and safety of the obstacle;

[0021] where β min and β max is the minimum and maximum value of the preset speed cost coefficient; L min To predict the shortest distance between the path point and the obstacle, L sis the distance threshold.

[0022] The technical solution of the present invention also includes: a path planning system for autonomous driving of a mining electric shovel, including a cloud server and a mining electric shovel; the mining electric shovel includes a map construction module, a sensor module, a path planning module and a control module; the cloud server obtains a task sent by a user and starts the operation of the mining electric shovel; the sensor module is used to obtain environmental information and current position information of a target area; the map construction module obtains environmental information and current position information of a target area according to the sensor module on the mining electric shovel, and constructs an environmental map; the path planning module, based on the environmental map, starting point and target end point information, uses an improved A* algorithm to perform global path planning to obtain a global optimal path sequence; selects local target points from the global optimal path sequence; uses an improved DWA algorithm to perform local path planning to obtain a local path that bypasses obstacles; traverses each local target point in turn until the target end point is reached; the control module controls the mining electric shovel to travel based on the planned path.

[0023] Preferably, the evaluation function of the improved A* algorithm includes setting the actual cost function and the heuristic cost function of the current path point, and setting the weight of the heuristic cost function to improve the search efficiency of the path; the evaluation function of the improved A* algorithm is: f(n)=g(n)+α(h(n)-kcosβ); wherein g(n) is the actual cost function of the current path point; h(n) is the heuristic cost function; α is the weight of the heuristic cost function, s is the distance from the starting point to the target end point; d is the distance from the current path point to the target end point; k is the set weight, β is the angle between the line connecting the starting point and the current path point and the line connecting the current path point and the target end point; Z is the number of known obstacles.

[0024] Preferably, the improved A* algorithm improves the actual cost function and the heuristic cost function by introducing the slope, energy consumption and obstacle span of the current path into the actual cost function and the heuristic cost function. The actual cost function is:

[0025]

[0026] The heuristic cost function is:

[0027]

[0028] Where: n is the current path point, N is the target end point, (x n ,y n ) is the coordinate of the current path point n; is the terrain height of path point n; is the additional energy consumption of the path point n; P nis the obstacle spanning degree of the path point; θ n is the path inclination angle of the path point.

[0029] The present invention provides a path planning method and system for autonomous driving of a mining electric shovel, which has the following beneficial effects:

[0030] 1. The present invention adopts an improved A* algorithm for global path planning, sets the weight of the heuristic cost function, adaptively adjusts the weight of the heuristic cost function by the distance between the current node and the target end point and the number of obstacles, and considers the angle between the current path point and the line connecting the starting point and the end point in the evaluation function, which can improve the search efficiency, flexibility and safety of the path;

[0031] 2. Since the working environment of mining electric shovels is relatively complex, with many slopes, steps and depressions, the planned path may be inaccessible or dangerous. The algorithm of global path planning is improved, and the slope, energy consumption and obstacle crossing of the current path are introduced into the actual cost function and heuristic cost function. This can ensure that the path can be safely reached, the energy consumption of elastic loss is small, and the path can safely cross obstacles, thereby ensuring the safety of the electric shovel;

[0032] 3. Use the improved DWA algorithm for local path planning, establish a speed constraint space, and reduce the speed search range. In the process of local path planning, consider the motion trajectory of dynamic obstacles so that the planned path can avoid the motion direction of dynamic obstacles in advance, reduce the probability of conflict between the planned path and obstacles, and avoid secondary collisions. The objective function of the improved DWA algorithm includes fit cost, distance cost, speed cost, and obstacle cost. Set an adaptive distance cost coefficient. When the electric shovel is far away from the target path point, set a larger distance cost coefficient to make it reach the target point as soon as possible, thereby improving the efficiency of path planning. Set an adaptive speed cost coefficient. By judging the distance between the electric shovel and the obstacle, the speed cost coefficient is adaptively adjusted. When the electric shovel is close to the obstacle, a smaller speed cost coefficient is set. When the electric shovel is far away from the obstacle, a larger speed cost coefficient is set to ensure the speed and safety of the electric shovel, improve the robustness of the path, and achieve efficient and safe obstacle avoidance. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a flow chart of the path planning method for autonomous driving of a mining electric shovel according to the present invention;

[0034] Figure 2 This is a structural block diagram of the path planning system for autonomous driving of a mining electric shovel according to the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0036] First embodiment: Figure 1 This embodiment provides a path planning method for autonomous driving of a mining electric shovel, comprising the following steps:

[0037] Step 1: Based on the task sent by the user, the mining shovel is started, and the environmental information and current location information of the target area are obtained according to the sensors on the mining shovel to build an environmental map;

[0038] Step 2: Based on the environment map, starting point and target end point information, the improved A* algorithm is used to perform global path planning to obtain the global optimal path sequence;

[0039] Step 3: Select a local target point from the global optimal path sequence; use the improved DWA algorithm to perform local path planning to obtain a local path that bypasses obstacles; traverse each local target point in turn until the target end point is reached.

[0040] Furthermore, the evaluation function of the improved A* algorithm includes setting the actual cost function and the heuristic cost function of the current path point, and setting the weight of the heuristic cost function to improve the search efficiency of the path; the evaluation function of the improved A* algorithm is: f(n)=g(n)+α(h(n)-kcosβ); wherein g(n) is the actual cost function of the current path point; h(n) is the heuristic cost function; α is the weight of the heuristic cost function, s is the distance from the starting point to the target end point; d is the distance from the current path point to the target end point; k is the set weight, β is the angle between the line connecting the starting point and the current path point and the line connecting the current path point and the target end point; Z is the number of known obstacles.

[0041] Furthermore, since the working environment of the mining electric shovel is relatively complex, with many slopes, steps and depressions, the improved A* algorithm improves the actual cost function and the heuristic cost function, and introduces the slope, energy consumption and obstacle span of the current path into the actual cost function and the heuristic cost function. The actual cost function is:

[0042]

[0043] The heuristic cost function is:

[0044]

[0045] Where: n is the current path point, N is the target end point, (x n ,y n ) is the coordinate of the current path point n; is the terrain height of path point n; is the additional energy consumption of the path point n; P n is the obstacle spanning degree of the path point; θ n is the path inclination angle of the path point.

[0046] Furthermore, the obstacle span of the path point is: θ max The maximum path inclination angle that the shovel can climb; Among them, F max is the maximum output power of the electric shovel; m is the mass of the vehicle; g is the gravity coefficient; δ is the rolling coefficient of the electric shovel; The maximum terrain height that the shovel can overcome; Where R is the wheel radius of the shovel; k is the path adhesion coefficient; L 1 is the distance between the center of gravity of the electric shovel and the front wheel of the electric shovel; L is the distance between the front and rear wheels of the electric shovel.

[0047] Furthermore, the method selects a local target point from the global optimal path sequence; adopts an improved DWA algorithm to perform local path planning to obtain a local path that bypasses obstacles; and traverses each local target point in turn until the target end point is reached, specifically including: S1 selecting a key turning point from the global optimal path sequence as a local target point; S2 establishing a speed constraint space and an objective function; S3 sampling the speed constraint space through a kinematic model of an electric shovel and generating a predicted path; S4 predicting the trajectory of a dynamic obstacle in real time; S5 evaluating the sampling speeds of multiple groups of predicted paths through an objective function based on the real-time predicted trajectory of the dynamic obstacle to obtain the optimal predicted path and corresponding speed information; S6 judging whether the local target point is the target end point, and if so, outputting the optimal path; if not, jumping to step S3 and repeating the operation.

[0048] Further: establish a speed constraint space to reduce the speed search range; the speed constraint space is: V∈V max ∩V o ∩V r ; where V max is the speed and angular velocity limit of the electric shovel; v min , v max are the minimum and maximum speed respectively; ω min ,ω max is the minimum and maximum value of angular velocity; V o V is the achievable speed limit of the electric shovel; r It is the safe speed limit of the electric shovel;

[0049]

[0050] where v a and ω a are the real-time speed and angular velocity of the shovel; a and a ω is the acceleration and angular acceleration of the shovel; Δt is the sampling period; L min Predict the shortest distance from a waypoint to an obstacle for the current speed.

[0051] Furthermore, the objective function is: score =β 1 f h +β 2 f d +β 3 f v +β 4 f o ;f h is the fit cost function between the local path and the global path; f h =180°-|θ t -θ f |, where θ t is the angle between the predicted path point of the shovel and the target end point, θ f The heading angle of the path point predicted by the shovel; this cost function is used to screen out the path points with small deviation between the target angle and the heading angle, so that the forward direction of the shovel points to the target end point; f d The distance cost function between the predicted path point and the target end point for the shovel is: x t and t is the coordinate of the predicted path point, x s and s is the coordinate of the target end point; f v =|v i | is the speed cost function, where v i is the predicted running speed; f o A distance cost from a path point to a dynamic obstacle predicted by the electric shovel, wherein the predicted trajectory of the dynamic obstacle is a Gaussian probability distribution; Where I is the number of dynamic obstacles, and are the standard deviations of the normal probability distribution of the predicted trajectory of the ith dynamic obstacle in the x and y directions, respectively; and are the means of the normal probability distribution of the predicted trajectory of the ith dynamic obstacle in the x and y directions; β 1 , β 2 , β 3 , β 4They are fit cost coefficient, distance cost coefficient, speed cost coefficient and obstacle cost coefficient respectively.

[0052] Furthermore, an adaptive distance cost coefficient is set, and the distance cost coefficient is adaptively adjusted according to the distance between the predicted path point and the target end point. When the electric shovel is far away from the target end point, a larger distance cost coefficient is set, and when the electric shovel is close to the target end point, a smaller distance cost coefficient is set; x c and c is the coordinate of the starting point of the electric shovel; set an adaptive speed cost coefficient, and adaptively adjust the speed cost coefficient by judging the distance between the electric shovel's predicted path point and the obstacle. When the electric shovel's predicted path point is close to the obstacle, set a smaller speed cost coefficient; when the electric shovel's predicted path point is far from the obstacle, set a larger speed cost coefficient to ensure the speed and safety of the obstacle;

[0053] where β min and β max is the minimum and maximum value of the preset speed cost coefficient; L min To predict the shortest distance between the path point and the obstacle, L s is the distance threshold.

[0054] Second embodiment: Figure 2 As shown, an embodiment of the present invention provides a path planning system for autonomous driving of a mining electric shovel, including a cloud server and a mining electric shovel; the mining electric shovel includes a map construction module, a sensor module, a path planning module and a control module; the cloud server obtains a task sent by a user and starts the operation of the mining electric shovel; the sensor module is used to obtain environmental information and current position information of a target area; the map construction module obtains environmental information and current position information of a target area according to the sensor module on the mining electric shovel, and constructs an environmental map; the path planning module, based on the environmental map, the starting point and the target end point information, adopts an improved A* algorithm to perform global path planning to obtain a global optimal path sequence; selects local target points from the global optimal path sequence; adopts an improved DWA algorithm to perform local path planning to obtain a local path that bypasses obstacles; traverses each local target point in turn until the target end point is reached; the control module controls the mining electric shovel to travel based on the planned path.

[0055] Furthermore, the evaluation function of the improved A* algorithm includes setting the actual cost function and the heuristic cost function of the current path point, and setting the weight of the heuristic cost function to improve the search efficiency of the path; the evaluation function of the improved A* algorithm is: f(n)=g(n)+α(h(n)-kcosβ); wherein g(n) is the actual cost function of the current path point; h(n) is the heuristic cost function; α is the weight of the heuristic cost function, s is the distance from the starting point to the target end point; d is the distance from the current path point to the target end point; k is the set weight, β is the angle between the line connecting the starting point and the current path point and the line connecting the current path point and the target end point; Z is the number of known obstacles.

[0056] Furthermore, the improved A* algorithm improves the actual cost function and the heuristic cost function by introducing the slope, energy consumption and obstacle span of the current path into the actual cost function and the heuristic cost function. The actual cost function is:

[0057]

[0058] The heuristic cost function is:

[0059]

[0060] Where: n is the current path point, N is the target end point, (x n ,y n ) is the coordinate of the current path point n; is the terrain height of path point n; is the additional energy consumption of the path point n; P n is the obstacle spanning degree of the path point; θ n is the path inclination angle of the path point.

[0061] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A path planning method for autonomous driving of a mining electric shovel, characterized in that: The steps include: Step 1: Based on the task sent by the user, the mining shovel is started, and the environmental information and current location information of the target area are obtained according to the sensors on the mining shovel to build an environmental map; Step 2: Based on the environment map, starting point and target end point information, the improved A* algorithm is used to perform global path planning to obtain the global optimal path sequence; Step 3: Select a local target point from the global optimal path sequence; use the improved DWA algorithm to perform local path planning to obtain a local path that bypasses obstacles; traverse each local target point in turn until the target end point is reached; The evaluation function of the improved A* algorithm includes setting the actual cost function and the heuristic cost function of the current path point, and setting the weight of the heuristic cost function; the evaluation function of the improved A* algorithm is: f(n)=g(n)+α(h(n)-kcosβ); wherein g(n) is the actual cost function of the current path point; h(n) is the heuristic cost function; α is the weight of the heuristic cost function, s is the distance from the starting point to the target end point; d is the distance from the current path point to the target end point; k is the set weight, β is the angle between the line connecting the starting point and the current path point and the line connecting the current path point and the target end point; Z is the number of known obstacles; The actual cost function is: The heuristic cost function is: Where: n is the current path point, N is the target end point, (x n ,y n ) is the coordinate of the current path point n; is the terrain height of the current path point n; is the additional energy consumption of the current path point n; P n is the obstacle spanning degree of the current path point; θ n is the path inclination of the current path point.

2. A path planning method for autonomous driving of a mining electric shovel according to claim 1, characterized in that: The method comprises the following steps: selecting a local target point from the global optimal path sequence; using an improved DWA algorithm to perform local path planning to obtain a local path that bypasses obstacles; and traversing each local target point in turn until the target end point is reached. Specifically, the method comprises the following steps: S1 selecting a key turning point from the global optimal path sequence as a local target point; S2 establishing a speed constraint space and an objective function; S3 sampling the speed constraint space through a kinematic model of an electric shovel and generating a predicted path; S4 predicting the trajectory of a dynamic obstacle in real time; S5 evaluating the sampling speeds of multiple groups of predicted paths through an objective function based on the real-time predicted trajectory of the dynamic obstacle to obtain the optimal predicted path and the corresponding speed information; S6 judging whether the local target point is the target end point, and outputting the optimal path if so; if not, jumping to step S3 and repeating the operation.

3. A path planning method for autonomous driving of a mining electric shovel according to claim 2, characterized in that: Establish a speed constraint space to reduce the speed search range; the speed constraint space is: V∈V max ∩V o ∩V r ; where V max is the speed and angular velocity limit of the electric shovel; v min , v max are the minimum and maximum speed respectively; ω min ,ω max is the minimum and maximum value of angular velocity; V o V is the achievable speed limit of the electric shovel; r It is the safe speed limit of the electric shovel; where v a and ω a are the real-time speed and angular velocity of the shovel; a and a ω is the acceleration and angular acceleration of the shovel; Δt is the sampling period; L min Predict the shortest distance from a waypoint to an obstacle for the current speed.

4. A path planning method for autonomous driving of a mining electric shovel according to claim 3, characterized in that: The objective function is: score =β1f h +β2f d +β3f v +β4f o ;f h is the fit cost function between the local path and the global path; f h =180°-|θ t -θ f |, where θ t is the angle between the predicted path point of the shovel and the target end point, θ f The heading angle of the predicted path point for the shovel; f d The distance cost function between the predicted path point and the target end point for the shovel is: x t and t is the coordinate of the predicted path point, x s and s is the coordinate of the target end point; f v =|v i | is the speed cost function, where v i is the predicted running speed; f o A distance cost from a path point to a dynamic obstacle predicted by the electric shovel, wherein the predicted trajectory of the dynamic obstacle is a Gaussian probability distribution; Where I is the number of dynamic obstacles, and are the standard deviations of the Gaussian probability distribution of the predicted trajectory of the i-th dynamic obstacle in the x and y directions, respectively; and are the means of the Gaussian probability distribution of the predicted trajectory of the ith dynamic obstacle in the x and y directions respectively; β1, β2, β3, and β4 are the fit cost coefficient, distance cost coefficient, speed cost coefficient, and obstacle cost coefficient respectively.

5. A path planning method for autonomous driving of a mining electric shovel according to claim 4, characterized in that: The adaptive distance cost coefficient is set, and the distance cost coefficient is adaptively adjusted according to the distance between the predicted path point and the target end point; Adaptive distance cost coefficient x c and c are the coordinates of the shovel's starting point.

6. A path planning method for autonomous driving of a mining electric shovel according to claim 5, characterized in that: Set the adaptive speed cost coefficient. According to the distance between the predicted path point and the obstacle, the speed cost coefficient is adaptively adjusted. where β min and β max is the minimum and maximum value of the preset speed cost coefficient; L min To predict the shortest distance between the path point and the obstacle, L s is the distance threshold.

7. A path planning system for autonomous driving of a mining electric shovel, adopting a path planning method for autonomous driving of a mining electric shovel as claimed in any one of claims 1 to 6, characterized in that: It includes a cloud server and a mining electric shovel; the mining electric shovel includes a map building module, a sensor module, a path planning module and a control module; The cloud server obtains the task sent by the user and starts the operation of the mining electric shovel; The sensor module is used to obtain environmental information and current location information of the target area; The map construction module obtains environmental information and current position information of the target area according to the sensor module on the mining electric shovel, and constructs an environmental map; The path planning module uses an improved A* algorithm to perform global path planning based on the environment map, the starting point and the target end point information to obtain a global optimal path sequence; selects a local target point from the global optimal path sequence; uses an improved DWA algorithm to perform local path planning to obtain a local path that bypasses obstacles; and traverses each local target point in turn until the target end point is reached; The control module controls the mining electric shovel to travel based on the planned path.

8. A path planning system for autonomous driving of a mining electric shovel according to claim 7, characterized in that: The evaluation function of the improved A* algorithm includes setting the actual cost function and the heuristic cost function of the current path point, and setting the weight of the heuristic cost function; the evaluation function of the improved A* algorithm is: f(n)=g(n)+α(h(n)-kcosβ); wherein g(n) is the actual cost function of the current path point; h(n) is the heuristic cost function; α is the weight of the heuristic cost function, s is the distance from the starting point to the target end point; d is the distance from the current path point to the target end point; k is the set weight, β is the angle between the line connecting the starting point and the current path point and the line connecting the current path point and the target end point; Z is the number of known obstacles.

9. A path planning system for autonomous driving of a mining electric shovel according to claim 8, characterized in that: The improved A* algorithm improves the actual cost function and the heuristic cost function, and introduces the slope, energy consumption and obstacle span of the current path into the actual cost function and the heuristic cost function. The actual cost function is: The heuristic cost function is: Where: n is the current path point, N is the target end point, (x n ,y n ) is the coordinate of the current path point n; is the terrain height of the current path point n; is the additional energy consumption of the current path point n; P n is the obstacle spanning degree of the current path point; θ n is the path inclination of the current path point.

Images