Engineering machinery automatic driving system based on complex environment

Abstract

The invention relates to an engineering machinery automatic driving system based on a complex environment, and belongs to the technical field of automatic driving. The method comprises a terrain map construction module, a global path planning module, a key point extraction module and a local path planning module. The topographic map construction module collects original topographic data and obstacle area data through an unmanned aerial vehicle, and obtains a curved surface topographic map model through an environment construction model according to the original topographic data and the obstacle area data; the global path planning module obtains a global static planning path through a global path planning model according to the curved surface terrain map model; the key point extraction module obtains a quadratic programming path through a quadratic programming model according to the global static programming path; and the local path planning module obtains a global dynamic planning path through a local path planning model according to the secondary planning path. The engineering machinery automatic driving based on the complex environment is realized, and the safety and the accuracy of the automatic driving are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of automatic driving, and in particular relates to an automatic driving system for engineering machinery based on a complex environment. Background Art

[0002] In engineering construction, the scale of infrastructure projects such as water conservancy facilities, roads, bridges and tunnels continues to expand. At the same time, modern infrastructure construction has gradually spread to high-altitude areas and remote mountainous areas. Natural barriers increase the difficulty of construction and put forward higher requirements for construction accuracy and quality stability, which cannot be met by manual construction. In view of the characteristics of some operations in engineering construction, such as harsh environments, high repeatability and high quality stability requirements, it is of great practical significance for engineering machinery to achieve automatic driving. However, how to achieve the accuracy, stability and safety of automatic driving of engineering machinery in complex environments is still a key problem in current research.

[0003] Path planning is the selection of driving routes for automatic driving of construction machinery. It realizes the optimal path selection for unmanned driving under the premise of ensuring vehicle safety, complying with vehicle motion constraints and traffic rules. It is an important research direction for achieving the accuracy, stability and safety of automatic driving of construction machinery. Traditional static path planning algorithms based on Dijkstra algorithm, Floyd algorithm, A* algorithm and meta-heuristic optimization algorithm have limitations in dynamic environments. Dynamic path planning algorithms based on D* algorithm, artificial potential field algorithm and dynamic window algorithm can achieve the avoidance of dynamic obstacles, but are only suitable for local dynamic path planning. Therefore, the above algorithms are not satisfied with the path planning of global dynamic obstacle avoidance. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides an automatic driving system for engineering machinery based on complex environments. The purpose of the present invention can be achieved through the following technical solutions: An automatic driving system for construction machinery based on complex environments, comprising a terrain map building module, a global path planning module, a key point extraction module, and a local path planning module; The terrain map construction module is used to collect original terrain data and obstacle area data through a drone, and obtain a curved terrain map model through an environment construction model based on the original terrain data and the obstacle area data; The global path planning module is used to obtain a global static planning path through a global path planning model according to the curved terrain map model; The key point extraction module is used to obtain a quadratic planning path through a quadratic planning model according to the global static planning path; The local path planning module is used to obtain a global dynamic planning path through a local path planning model according to the secondary planning path.

[0005] Preferably, the curved terrain map model includes a reference terrain model and an obstacle terrain model.

[0006] Preferably, the obtaining of the curved terrain map model by building a model through the environment according to the original terrain data and the obstacle area data comprises: The reference terrain model is obtained by describing the original terrain data through the reference terrain trigonometric function; The obstacle terrain model is obtained by describing the obstacle area data through an obstacle index function.

[0007] Preferably, obtaining a global static planning path through a global path planning model according to the curved terrain map model comprises: S201: using the curved terrain map model as a particle optimization space, initializing particle positions and particle velocities in the particle optimization space, wherein the particle optimization space particle positions carry a particle optimization space particle position update times label; S202: Acquire a current path, where the current path is an individual optimal solution, and obtain a group optimal solution through shortest path calculation based on the current path; S203: obtaining an updated particle speed in the particle optimization space through a speed update function according to the particle speed in the particle optimization space, the particle position in the particle optimization space, the individual optimal solution, and the group optimal solution; S204: obtaining an updated particle optimization space particle position according to the updated particle optimization space particle velocity and the particle optimization space particle position through a position update function; S205: generating a new path according to the particle position in the updated particle optimization space, and obtaining an updated individual optimal solution and an updated group optimal solution through optimal solution update judgment according to the new path; S206: Preset a loop number threshold, and obtain the global static planning path by judging the number of loops according to the particle optimization space particle position update number label and the loop number threshold.

[0008] Preferably, the optimal solution update judgment includes judging whether the new path is smaller than the current path. If yes, the new path is used as the updated individual optimal solution, and the updated group optimal solution is obtained by replacing the current path with the new path; if no, no operation is performed.

[0009] Preferably, the number of loops judgment includes judging whether the number of updates of the particle position in the particle optimization space is equal to the number of loops threshold, if yes, the swarm optimal solution is the global static planning path; if no, repeat steps S203 to S205 until the number of updates of the particle position in the particle optimization space is equal to the number of loops threshold.

[0010] Preferably, obtaining a quadratic planning path through a quadratic planning model according to the global static planning path comprises: Obtaining path nodes through depth-first traversal according to the global static planning path; Obtaining path node key points through the Floyd algorithm according to the path nodes; The secondary planning path is obtained by connecting the key points of the path nodes.

[0011] Preferably, obtaining a global dynamic planning path through a local path planning model according to the secondary planning path includes: Obtain the local path, preset the linear speed and angular speed of the engineering machinery; Obtaining an optimal trajectory through objective function evaluation according to the local path, the linear velocity of the engineering machinery, and the angular velocity of the engineering machinery; The global dynamic planning path is obtained by splicing the optimal trajectories.

[0012] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned complex environment-based automatic driving system for engineering machinery is implemented.

[0013] A storage medium containing computer executable instructions, which are used to execute the above-mentioned engineering machinery automatic driving system based on complex environment when executed by a computer processor.

[0014] The beneficial effects of the present invention are: (1) By combining the original terrain data and obstacle area data and using the environment construction model to generate a surface terrain map model, the system can fully adapt to complex terrain environments, improve its adaptability to high-altitude and remote mountain environments, and enhance the adaptability and planning efficiency of engineering machinery in autonomous driving in complex environments.

[0015] (2) Path planning is performed through global static planning and local dynamic planning. From an overall perspective, it provides macro-guidance for path planning, limits the planning scope, and improves computational efficiency. At the same time, local dynamic planning is used to solve the limitations of global planning in dealing with dynamic obstacles, and path planning can be adjusted in real time, thereby improving the accuracy and safety of autonomous driving of construction machinery.

[0016] (3) Through depth-first traversal and Floyd algorithm, key points of the path are extracted, redundant path nodes are reduced, the path structure is optimized, and the computational complexity is reduced. Then, combined with the dynamic window algorithm, the optimal trajectory is evaluated in real time through the objective function to obtain the global dynamic planning path, so that the automatic driving of construction machinery can better adapt to complex environments and ensure the safety and stability of automatic driving in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0018] Figure 1 The present invention is a flowchart of an automatic driving system for engineering machinery based on a complex environment. DETAILED DESCRIPTION

[0019] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0020] See also Figure 1 , an automatic driving system for construction machinery based on complex environment, including a terrain map construction module, a global path planning module, a key point extraction module, and a local path planning module; The terrain map construction module is used to collect original terrain data and obstacle area data through a drone, and obtain a curved terrain map model through an environment construction model based on the original terrain data and the obstacle area data; The global path planning module is used to obtain a global static planning path through a global path planning model according to the curved terrain map model; The key point extraction module is used to obtain a quadratic planning path through a quadratic planning model according to the global static planning path; The local path planning module is used to obtain a global dynamic planning path through a local path planning model according to the secondary planning path.

[0021] Specifically, the environment construction model includes: S101: The curved terrain map model includes a reference terrain model and an obstacle terrain model; S102: obtaining the reference terrain model by describing the original terrain data through a reference terrain trigonometric function; The trigonometric function expression of the reference terrain is: , in, Z1 (x,y) is the elevation value corresponding to the horizontal point, sin is a sine function, cos is the cosine function, a、b、c、 d、e、f、g is a constant coefficient that controls the reference terrain relief in the digital map. x is the horizontal coordinate of the point projected on the horizontal plane by the reference terrain model, y The ordinate coordinate of the point projected on the horizontal plane by the reference terrain model; S103: Obtaining the obstacle terrain model by describing the obstacle area data through an obstacle index function; The barrier index function expression is: , in, Z 2 (x,y) is the elevation value corresponding to the horizontal point, i represents the i-th obstacle, n Indicates the number of obstacles. h i is the obstacle elevation parameter, which controls the height. exp is an exponential function, x is the horizontal coordinate of the point projected on the horizontal plane by the obstacle terrain model, y is the vertical coordinate of the point projected on the horizontal plane by the obstacle terrain model, x i represents the horizontal coordinate of the center of the ith obstacle, y i The ordinate of the center of the i-th obstacle, x si represents the attenuation of the terrain uplift caused by the ith obstacle in the x-axis direction, y si It represents the attenuation of the terrain uplift caused by the i-th obstacle in the y-axis direction, and the attenuation controls the slope.

[0022] Specifically, the global path planning model is based on a particle swarm optimization algorithm, and specifically includes: S201: using the curved terrain map model as a particle optimization space, initializing particle positions and particle velocities in the particle optimization space, wherein the particle optimization space particle positions carry a particle optimization space particle position update times label; S202: Acquire a current path, where the current path is an individual optimal solution, and obtain a group optimal solution through shortest path calculation based on the current path; The shortest path calculation expression is: , in, f(P) represents the path length, v i represents the i-th path, n Represents the total number of paths, d(v i ,v i+1 ) Represents Euclidean distance calculation; S203: obtaining an updated particle speed in the particle optimization space through a speed update function according to the particle speed in the particle optimization space, the particle position in the particle optimization space, the individual optimal solution, and the group optimal solution; The speed update function is expressed as: , in, represents the particle speed of the updating particle optimization space, represents the particle speed in the particle optimization space, represents the particle position in the particle optimization space, oh is the motion inertia weight, c 1 、c 2 is the acceleration constant, used to adjust the acceleration step length, r 1 、r 2 is a random number ranging from 0 to 1. pBest t represents the individual optimal solution, gBest represents the optimal solution of the group; S204: obtaining an updated particle optimization space particle position according to the updated particle optimization space particle velocity and the particle optimization space particle position through a position update function; The position update function is expressed as: , in, represents the particle speed of the updating particle optimization space, represents the particle position in the particle optimization space, represents the particle position in the updating particle optimization space; S205: generating a new path according to the particle position in the updated particle optimization space, and obtaining an updated individual optimal solution and an updated group optimal solution through optimal solution update judgment according to the new path; The optimal solution update judgment includes: Determine whether the new path is smaller than the current path. If yes, use the new path as the updated individual optimal solution, and obtain the updated group optimal solution by replacing the current path with the new path; if no, do nothing; S206: Preset a loop number threshold, and obtain the global static planning path by loop number judgment according to the particle optimization space particle position update number label and the loop number threshold; The number of loops judgment includes judging whether the number of updates of the particle position in the particle optimization space is equal to the number of loops threshold. If yes, the swarm optimal solution is the global static planning path; if no, repeating steps S203 to S205 until the number of updates of the particle position in the particle optimization space is equal to the number of loops threshold.

[0023] In this embodiment, particles represent paths, and the optimization objective function is the shortest path. The movement of particles is combined under the dual influence of individual optimality and group optimality to obtain the current movement direction, and continues to move until the complete cycle is completed, obtaining the optimal global path planning, that is, the global static planning path.

[0024] Specifically, the quadratic programming model includes: S301: Obtaining path nodes through depth-first traversal according to the global static planning path; S302: Obtaining path node key points according to the path nodes by using the Floyd algorithm; S303: Obtain the secondary planning path by connecting the key points of the path nodes.

[0025] In this embodiment, all path nodes in the global static planning path are traversed and searched through deep search, the starting point and the end point are retained, the inflection points therein are selected, and the redundant nodes in the path are deleted. Starting from the starting point, the Floyd algorithm principle is applied to connect the starting point with the inflection point, and under the premise of not passing through obstacles, the inflection point corresponding to the longest Euclidean distance is found as the path node key point. The path node key points are connected in sequence from the starting point to the end point to obtain the secondary planning path.

[0026] Specifically, the local path planning model is based on a dynamic window algorithm, and specifically includes: S401: Acquire a local path, preset the linear velocity and angular velocity of the engineering machinery, the local path is a path in the secondary planning path, and the path is a path formed by taking the key point of the path node as the starting point and taking the next key point of the path node as the target point; S402: Obtaining an optimal trajectory through objective function evaluation according to the local path, the linear velocity of the engineering machine, and the angular velocity of the engineering machine; The objective function evaluation expression is: , in, V represents the linear speed of the engineering machinery, oh represents the angular velocity of the engineering machinery, a、b、c is the weighting coefficient, Cost(V,ω) represents the objective function, Head(V,ω) is a construction machinery direction angle evaluation function, wherein the construction machinery direction angle evaluation function represents the angle between the line between the current position of the construction machinery and the target point and the direction of the current position, Vel(V,ω) is a construction machinery speed evaluation function, wherein the construction machinery speed evaluation function represents the construction machinery linear speed evaluation value, Obs(V,ω) is a distance evaluation function between the construction machinery and the obstacle, wherein the distance evaluation function between the construction machinery and the obstacle represents the shortest distance between the construction machinery and the obstacle; S403: Obtain the global dynamic planning path by splicing the optimal trajectories.

[0027] Specifically, the engineering machinery includes excavators, bulldozers, graders, loaders, tower cranes, concrete pump trucks, and crawler cranes.

[0028] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0029] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0030] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0031] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An automatic driving system for construction machinery based on complex environments, characterized in that: It includes terrain map construction module, global path planning module, key point extraction module and local path planning module; The terrain map construction module is used to collect original terrain data and obstacle area data through a drone, and obtain a curved terrain map model through an environment construction model based on the original terrain data and the obstacle area data; The global path planning module is used to obtain a global static planning path through a global path planning model according to the curved terrain map model; The key point extraction module is used to obtain a quadratic planning path through a quadratic planning model according to the global static planning path; The local path planning module is used to obtain a global dynamic planning path through a local path planning model according to the secondary planning path.

2. The complex environment-based automatic driving system for construction machinery according to claim 1, characterized in that: The curved terrain map model includes a reference terrain model and an obstacle terrain model.

3. The complex environment-based automatic driving system for construction machinery according to claim 2, characterized in that: The obtaining of the curved terrain map model by building a model through the environment according to the original terrain data and the obstacle area data comprises: The reference terrain model is obtained by describing the original terrain data through the reference terrain trigonometric function; The obstacle terrain model is obtained by describing the obstacle area data through an obstacle index function.

4. The complex environment-based automatic driving system for construction machinery according to claim 1, characterized in that: The obtaining of a global static planning path through a global path planning model according to the curved terrain map model comprises: S201: using the curved terrain map model as a particle optimization space, initializing particle positions and particle velocities in the particle optimization space, wherein the particle optimization space particle positions carry a particle optimization space particle position update times label; S202: Acquire a current path, where the current path is an individual optimal solution, and obtain a group optimal solution through shortest path calculation based on the current path; S203: obtaining an updated particle speed in the particle optimization space through a speed update function according to the particle speed in the particle optimization space, the particle position in the particle optimization space, the individual optimal solution, and the group optimal solution; S204: obtaining an updated particle optimization space particle position according to the updated particle optimization space particle velocity and the particle optimization space particle position through a position update function; S205: generating a new path according to the particle position in the updated particle optimization space, and obtaining an updated individual optimal solution and an updated group optimal solution through optimal solution update judgment according to the new path; S206: Preset a loop number threshold, and obtain the global static planning path by loop number judgment according to the particle optimization space particle position update number label and the loop number threshold.

5. The complex environment-based automatic driving system for construction machinery according to claim 4, characterized in that: The optimal solution update judgment includes judging whether the new path is smaller than the current path, if yes, taking the new path as the updated individual optimal solution, and obtaining the updated group optimal solution by replacing the current path with the new path; If no, no action is taken.

6. The complex environment-based automatic driving system for construction machinery according to claim 4, characterized in that: The number of loops judgment includes judging whether the number of updates of the particle position in the particle optimization space is equal to the number of loops threshold. If yes, the swarm optimal solution is the global static planning path; if no, repeating steps S203 to S205 until the number of updates of the particle position in the particle optimization space is equal to the number of loops threshold.

7. The complex environment-based automatic driving system for construction machinery according to claim 1, characterized in that: The obtaining of a secondary planning path through a secondary planning model according to the global static planning path comprises: Obtaining path nodes through depth-first traversal according to the global static planning path; Obtaining path node key points through the Floyd algorithm according to the path nodes; The secondary planning path is obtained by connecting the key points of the path nodes.

8. The complex environment-based automatic driving system for construction machinery according to claim 1, characterized in that: The obtaining of a global dynamic planning path through a local path planning model according to the secondary planning path comprises: Obtain the local path, preset the linear speed and angular speed of the engineering machinery; Obtaining an optimal trajectory through objective function evaluation according to the local path, the linear velocity of the engineering machinery, and the angular velocity of the engineering machinery; The global dynamic planning path is obtained by splicing the optimal trajectories.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, it implements the engineering machinery automatic driving system based on a complex environment as described in any one of claims 1-8.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the complex environment-based automatic driving system for engineering machinery as described in any one of claims 1-8.

Images