A Collision Avoidance Planning Method for Usv Cluster Based on Improved Particle Swarm Optimization Algorithm
A technology for improving particle swarms and optimization algorithms. It is used in calculations, calculation models, and two-dimensional position/channel control. It can solve the problems of small calculation speed, oscillation, and long planning time, so as to improve real-time performance and improve smoothness effect
Active Publication Date: 2022-02-22
HARBIN ENG UNIV
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Most collision-avoidance planning algorithms cannot plan a non-collision-avoidance optimal path for the USV in a short period of time. Although traditional methods such as artificial potential field methods have simple principles, a small amount of calculation, and a fast calculation speed, they cannot It is easy to find the global optimal solution, and even shocks occur during the collision avoidance process. Although swarm intelligence algorithms such as genetic algorithms can avoid falling into local extremum points, the principle is complex, the amount of calculation is large, and the planning time is long. Therefore, It is crucial to design a simple, fast, real-time online collision avoidance planning algorithm for USV
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0057] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0058] According to the parameter characteristics of navigation radar and photoelectric sensor, the USV comprehensive view model is established;
[0059] The parameter characteristics of navigation radar and photoelectric sensor are shown in Table 1:
[0060] Table 1 USV common sensor performance parameter table
[0061]
[0062]
[0063] Build a global coordinate system and a local coordinate system
[0064] Such as figure 2 As shown, the local coordinate system X of USV U o U Y U The origin of is located at the center of gravity of the USV, the current forward direction of the USV is the positive direction of the X-axis, and the direction perpendicular to the X-axis and pointing to the starboard side of the USV is the positive direction of the Y-axis. The navigation radar and photoelectric sensors are installed at a distance from the center of ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention belongs to the field of obstacle avoidance of unmanned surface vehicles, and in particular relates to a USV cluster collision avoidance planning method based on an improved particle swarm optimization algorithm. The present invention mainly includes the following steps: establishing a USV comprehensive view model according to the parameter characteristics of the navigation radar and the photoelectric sensor; constructing a coordinate system; constructing an environment model; designing a rolling optimization strategy and an improved particle swarm optimization algorithm for USV cluster collision avoidance planning; The information detected by the comprehensive sensor and the information of the target point are input into the improved particle swarm optimization algorithm to obtain the navigation and speed adjustment instructions of the USV at the next moment. The invention not only overcomes the shortcoming that the standard particle swarm optimization algorithm is easy to fall into a local optimum, but also combines the current environment information of the USV to improve the real-time performance of USV collision avoidance planning, and adds the corner optimization of the USV to the fitness function. While optimizing the path, it also improves the smoothness of the path.
Description
technical field [0001] The invention belongs to the field of obstacle avoidance of unmanned surface vehicles, and in particular relates to a USV cluster collision avoidance planning method based on an improved particle swarm optimization algorithm. Background technique [0002] In recent years, more and more countries have paid attention to the development of sea power, and unmanned surface vehicles have become a research hotspot due to their advantages of small size, high flexibility and strong combat capability. Unmanned surface vehicles can not only navigate and plan independently, but also complete tasks such as target tracking and harbor patrol. Therefore, both in the military and civilian fields, unmanned surface vehicles are playing an increasingly important role. However, in the face of an unknown working environment and diverse missions, a single USV appears to be weak and unable to complete tasks efficiently, while a cluster system composed of multiple USVs is robu...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & AuthorityPatents(China)
IPC IPC(8): G05D1/02G06N3/00
CPCG05D1/0206G06N3/006
Inventor王宏健练青坡李成凤周佳加贺巨义
OwnerHARBIN ENG UNIV