Unmanned road roller cluster minor radius curve path planning method based on artificial potential field technology

Abstract

The invention relates to the technical field of unmanned road rollers, in particular to an unmanned road roller cluster minor radius curve path planning method based on an artificial potential field technology, which comprises the following steps: S1, collecting road environment information, and establishing an environment model; s2, setting an artificial potential field function in the environment model, and defining potential fields of an obstacle and a target point; s3, calculating control parameters of path planning according to the kinetic model of the unmanned road roller; s4, generating an optimal path by adopting a model predictive control algorithm in combination with an artificial potential field function; s5, adjusting the parameters of the artificial potential field function in real time according to the change of the surrounding environment of the road roller by using a fuzzy inference system; in the invention, aiming at the defects of the traditional path planning method, the adaptability and the practicability of the algorithm are improved through multiple technical improvements.

Description

Technical Field

[0001] The present invention relates to the technical field of driverless rollers, and particularly to a method for planning a small-radius curved path for a cluster of driverless rollers using the artificial potential field technique. Background Art

[0002] With the development of autonomous driving technology, the demand for driverless vehicles in various application scenarios has gradually increased. In the fields of construction and road maintenance, driverless rollers, as an efficient and precise construction tool, have gradually received extensive attention and application;

[0003] The artificial potential field technique is an algorithm commonly used for path planning. It avoids obstacles and finds the optimal path by simulating the potential field. The main advantage of this method is high computational efficiency and the ability to generate paths in real time in complex environments;

[0004] The existing technology has the following problems in the path planning of driverless rollers: insufficient adaptability in path planning for dynamic environments and multi-obstacle scenarios, and it is easy to fall into local optimal solutions; in the planning of small-radius curved paths, it is difficult to ensure path smoothness and feasibility; when multiple rollers work together, there is a lack of an effective cooperative control mechanism, which easily leads to path conflicts and reduced construction efficiency. Therefore, in view of the above problems, a method for planning a small-radius curved path for a cluster of driverless rollers using the artificial potential field technique is proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for planning a small-radius curved path for a cluster of driverless rollers using the artificial potential field technique to solve the following problems existing in the path planning of driverless rollers in the existing technology: insufficient adaptability in path planning for dynamic environments and multi-obstacle scenarios, and it is easy to fall into local optimal solutions; in the planning of small-radius curved paths, it is difficult to ensure path smoothness and feasibility; when multiple rollers work together, there is a lack of an effective cooperative control mechanism, which easily leads to path conflicts and reduced construction efficiency.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] A method for planning a small-radius curved path for a cluster of driverless rollers using the artificial potential field technique, including the following steps: S1: Collect road environment information and establish an environmental model; S2: Set an artificial potential field function in the environmental model and define the potential fields of obstacles and target points; S3: Calculate the control parameters for path planning according to the dynamic model of the driverless roller; S4: Use a model predictive control algorithm and combine it with the artificial potential field function to generate an optimal path; S5: Use a fuzzy inference system to adjust the parameters of the artificial potential field function in real time according to the changes in the environment around the roller.

[0008] As a further optimization content of the present invention, wherein: the environment model is established by using multi-sensor fusion technology, including a lidar, a camera and an ultrasonic sensor for real-time updating of environmental information to ensure the accuracy and real-time nature of path planning.

[0009] As a further optimization content of the present invention, wherein: the artificial potential field function includes a repulsive potential field and an attractive potential field. The repulsive potential field is used to avoid obstacles, and the attractive potential field is used to guide the roller towards the target point. The influence range of the repulsive potential field is dynamically adjusted according to the driving speed of the roller.

[0010] As a further optimization content of the present invention, wherein: the calculation formula of the repulsive potential field function is:

[0011]

[0012] In the formula, η is the repulsive potential field gain coefficient, ρ(x, y) is the distance between the roller and the obstacle, ρ0 is the influence range of the repulsive potential field, and the repulsive potential field gain coefficient η is dynamically adjusted according to the danger level of the obstacle to achieve a more precise obstacle avoidance effect.

[0013] As a further optimization content of the present invention, wherein: the calculation formula of the attractive potential field function is:

[0014]

[0015] In the formula, k att is the attractive potential field gain coefficient, (x g , y g ) is the target point coordinate, and the attractive potential field gain coefficient k att is dynamically adjusted according to the urgency of the task and the complexity of the road to ensure that the roller can reach the target point smoothly and efficiently.

[0016] As a further optimization content of the present invention, wherein: the objective function of the model predictive control algorithm is:

[0017]

[0018] In the formula, N is the prediction horizon length, x k is the state variable, u k is the control input, and Q, R and P are weight matrices; the weight matrices are adjusted in real time according to the working state of the roller and environmental changes to optimize the adaptability and robustness of path planning.

[0019] As a further optimization content of the present invention, wherein: during the path planning process, a fuzzy inference system is used to adjust the parameters of the artificial potential field function in real time according to the changes in the environment around the roller. The inputs of the fuzzy inference system include environmental complexity, obstacle density and road curvature;

[0020] As a further optimized content of the present invention, wherein: through a real-time simulation platform, the path planning effect of the driverless roller compactor cluster is verified and optimized. The simulation platform can simulate various complex road conditions and emergency situations to ensure the reliability and applicability of the path planning method.

[0021] As a further optimized content of the present invention, wherein: after the path planning is completed, the construction process of the roller compactor cluster is monitored and managed through a central control system. The central control system can adjust the path planning and driving speed of each roller compactor in real time to adapt to the dynamically changing construction environment.

[0022] As a further optimized content of the present invention, wherein: the path planning method is applicable to different types of driverless roller compactors, including single-drum and double-drum roller compactors, and can dynamically adjust the driving speed of the roller compactor to adapt to different construction requirements and safety requirements.

[0023] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0024] 1. In the present invention, aiming at the deficiencies of the traditional path planning method, through multiple technical improvements, the adaptability and practicability of the algorithm are improved; specifically including: by introducing a dynamic potential field function, the adaptability of the algorithm in a dynamic environment is improved, enabling it to effectively avoid moving obstacles, and by adopting a distributed cooperative control algorithm, the path planning coordination among multiple roller compactors is realized, avoiding mutual interference and improving the overall construction efficiency;

[0025] 2. In the present invention, in combination with the dynamic model of the roller compactor, the generated path is smoothed and optimized to ensure the feasibility of the path and the construction quality. Aiming at the requirement of small-radius curved path planning, a specific path generation and tracking algorithm is designed to ensure that the roller compactor can accurately drive in a narrow area. By improving the efficiency and accuracy of path planning, the application effect of the driverless roller compactor in construction can be significantly improved, reducing construction time and cost. The realization of multi-machine cooperative planning further improves the automation level of the construction process, reduces manual intervention, and improves construction safety and construction quality. Specific embodiments

[0026] Embodiment 1:

[0027] The present invention provides a technical solution:

[0028] A method for planning a small-radius curved path of a driverless roller compactor cluster using an artificial potential field technology, comprising the following steps:

[0029] S1: Collect road environment information and establish an environmental model: Deploy various sensors at the construction site, including lidar, cameras, and ultrasonic sensors. The sensors collect construction environment data in real-time, such as road shape, obstacle position and size, etc. The data is wirelessly transmitted to the central control system, and an accurate environmental model is generated using multi-sensor fusion technology;

[0030] S2: Set an artificial potential field function in the environmental model and define the potential fields of obstacles and target points: Define an artificial potential field function in the environmental model, including a repulsive potential field and an attractive potential field. The repulsive potential field is used to avoid obstacles, and the attractive potential field is used to guide the roller towards the target point. Dynamically adjust the influence range of the repulsive potential field according to the driving speed of the roller;

[0031] S3: Calculate the control parameters for path planning according to the dynamic model of the driverless roller: Calculate the control parameters for path planning according to the dynamic model of the roller. The dynamic model takes into account parameters such as the mass, acceleration, and steering angle of the roller to ensure the feasibility and stability of path planning;

[0032] S4: Adopt a model predictive control algorithm and combine it with the artificial potential field function to generate an optimal path:

[0033] The objective function is:

[0034]

[0035] In the formula, N is the prediction horizon length, x k is the state variable, u k is the control input, and Q, R, and P are weight matrices; The weight matrices are adjusted in real-time according to the working state of the roller and environmental changes to optimize the adaptability and robustness of path planning;

[0036] S5: Use a fuzzy inference system to adjust the parameters of the artificial potential field function in real-time according to changes in the environment around the roller. The inputs of the fuzzy inference system include environmental complexity, obstacle density, and road curvature;

[0037] Path execution and monitoring: Through the central control system, send the path planning instructions generated by the calculation to each roller, monitor the driving state of the roller and the construction process in real-time, and adjust the path according to the actual situation;

[0038] Through the above steps, the roller can drive efficiently and accurately on a small-radius curved path, avoid obstacles and successfully complete the construction task. By using multi-sensor fusion technology and an adaptive artificial potential field model, the accuracy and flexibility of path planning are improved.

[0039] Example 2:

[0040] A method for small-radius curve path planning of an unmanned roller group using the artificial potential field technique, comprising the following steps:

[0041] Environmental information collection and modeling:

[0042] A variety of sensors are set up at the construction site, including lidar, cameras, and ultrasonic sensors. The sensors collect road environment data in real time, such as road shape, obstacle position and size, etc. The data is wirelessly transmitted to the central control system, and an accurate environmental model is generated using multi-sensor fusion technology;

[0043] Artificial potential field function setting: Define the artificial potential field function in the environmental model, including the repulsive potential field and the gravitational potential field. The repulsive potential field is used to avoid obstacles, and the gravitational potential field is used to guide the roller towards the target point. The calculation formula of the repulsive potential field function is:

[0044]

[0045] In the formula, η is the repulsive potential field gain coefficient, ρ(x,y) is the distance between the roller and the obstacle, ρ0 is the influence range of the repulsive potential field, and the repulsive potential field gain coefficient η is dynamically adjusted according to the danger level of the obstacle to achieve a more precise obstacle avoidance effect;

[0046] Calculation of path planning control parameters: According to the dynamic model of the roller, calculate the control parameters of path planning. The dynamic model takes into account parameters such as the mass, acceleration, and steering angle of the roller to ensure the feasibility and stability of path planning;

[0047] Application of model predictive control algorithm: Use the model predictive control algorithm to generate the optimal path. The objective function is:

[0048]

[0049] In the formula, N is the prediction horizon length, x k is the state variable, u k is the control input, and Q, R, and P are weight matrices; the weight matrices are adjusted in real time according to the working state of the roller and environmental changes to optimize the adaptability and robustness of path planning;

[0050] Path planning and adjustment: Use a fuzzy inference system to adjust the parameters of the artificial potential field function in real time according to the changes in the environment around the roller. The inputs of the fuzzy inference system include environmental complexity, obstacle density, and road curvature;

[0051] Path execution and monitoring: Through the central control system, send the calculated path planning instructions to each roller, monitor the driving state and construction process of the roller in real time, and adjust the path according to the actual situation;

[0052] Through the above implementation steps, the road roller can effectively avoid obstacles and accurately travel along the planned path, improving the construction efficiency and safety. The model predictive control algorithm and fuzzy inference system are adopted to make the path planning have higher adaptability and robustness, ensuring that the road roller can also operate stably in complex road environments.

[0053] In this article, specific examples are used to elaborate on the principles and implementation methods of the present invention. The description of the above examples is only used to help understand the method of the present invention and its core idea. The above is only the preferred implementation method of the present invention. It should be noted that due to the limited nature of written expression and the objectively infinite specific structures, for those of ordinary skill in the art, without departing from the principles of the present invention, several improvements, refinements or changes can be made, or the above technical features can be combined in an appropriate manner; these improvements, refinements, changes or combinations, or directly applying the concept and technical solution of the invention to other occasions without improvement, should all be regarded as the protection scope of the present invention.

Claims

1. A small radius curve path planning method for unmanned road roller clusters based on artificial potential field technology, characterized in that: The following steps are involved: S1: Collect road environment information and establish an environment model; S2: Setting an artificial potential field function in the environment model to define the potential field of obstacles and target points; S3: Calculating control parameters of path planning according to the dynamic model of the unmanned roller; S4: Use the model predictive control algorithm combined with the artificial potential field function to generate the optimal path; S5: Use the fuzzy inference system to adjust the parameters of the artificial potential field function in real time according to the changes in the environment around the roller.

2. According to the method of artificial potential field technology for small radius curve path planning of unmanned road roller clusters according to claim 1, it is characterized by: The environmental model is established using multi-sensor fusion technology, including laser radar, cameras and ultrasonic sensors for real-time updating of environmental information to ensure the accuracy and real-time performance of path planning.

3. According to the method of artificial potential field technology for small radius curve path planning of unmanned road roller clusters according to claim 1, it is characterized by: The artificial potential field function includes a repulsive potential field and a gravitational potential field. The repulsive potential field is used to avoid obstacles, and the gravitational potential field is used to guide the roller to move toward a target point. The influence range of the repulsive potential field is dynamically adjusted according to the driving speed of the roller.

4. According to the method of artificial potential field technology for small radius curve path planning of unmanned road roller clusters according to claim 1, it is characterized by: The calculation formula of the repulsive potential field function is: Where η is the repulsive potential field gain coefficient, ρ(x, y) is the distance between the roller and the obstacle, and ρ0 is the influence range of the repulsive potential field. The repulsive potential field gain coefficient η is dynamically adjusted according to the danger level of the obstacle to achieve a more accurate obstacle avoidance effect.

5. The method for planning a small radius curve path for a cluster of unmanned road rollers using artificial potential field technology according to claim 1 is characterized in that: The calculation formula of the gravitational potential field function is: In the formula, k att is the gravitational potential field gain coefficient, (x g ,y g ) is the target point coordinate, and the gravitational potential field gain coefficient k att Dynamically adjust according to the urgency of the task and the complexity of the road to ensure that the roller can reach the target point smoothly and efficiently.

6. The method for planning a small radius curve path for a cluster of unmanned road rollers using artificial potential field technology according to claim 1, characterized in that: The objective function of the model predictive control algorithm is: Where N is the prediction time domain length, x k is the state variable, u k is the control input, Q, R and P are the weight matrices; the weight matrix is ​​adjusted in real time according to the working state of the roller and environmental changes to optimize the adaptability and robustness of the path planning.

7. The method for planning a small radius curve path for a cluster of unmanned road rollers using artificial potential field technology according to claim 1 is characterized in that: During the path planning process, a fuzzy inference system is used to adjust the parameters of the artificial potential field function in real time according to the changes in the environment around the roller. The input of the fuzzy inference system includes environmental complexity, obstacle density and road curvature.

8. The method for planning a small radius curve path for a cluster of unmanned road rollers using artificial potential field technology according to claim 1 is characterized by: The path planning effect of the unmanned road roller cluster is verified and optimized through the real-time simulation platform. The simulation platform can simulate various complex road conditions and emergency situations to ensure the reliability and applicability of the path planning method.

9. The method for planning a small radius curve path for a cluster of unmanned road rollers using artificial potential field technology according to claim 1, characterized in that: After the path planning is completed, the construction process of the roller cluster is monitored and managed through the central control system. The central control system can adjust the path planning and driving speed of each roller in real time to adapt to the dynamically changing construction environment.

10. The method for planning a small radius curve path for a cluster of unmanned road rollers using artificial potential field technology according to claim 1, characterized in that: The path planning method is applicable to different types of unmanned rollers, including single-drum and double-drum rollers, and can dynamically adjust the travel speed of the roller to adapt to different construction needs and safety requirements.

Images