Multiwindow-heuristic three-dimensional space path planning method based on magic cube model

Abstract

The invention discloses a multiwindow-heuristic three-dimensional space path planning method based on a magic cube model. The method includes: sensing environment information through a sensor, and filtering and integrating on this basis to convert into a three-dimensional space grid map; building 26 degree-of-freedom search space based on the magic cube model; using a multiwindow model to quicklydetermine accessibility of 26 degrees of freedom in batches according to a priority sequence; establishing a heuristic evaluation function, calculating a function value according to weight parameters,and utilizing the evaluation function for screening to acquire a local target; iterating step by step to finally acquire a globally unique optimal path. The method can be applied in quick path planning of unmanned aerial vehicles / unmanned underwater vehicles containing prior information in three-dimensional space, high degree of freedom in the three-dimensional space is fully taken into consideration, and a globally-optimal collisionless three-dimensional path can be acquired quickly.

Description

technical field [0001] The invention relates to three-dimensional space environment perception modeling and path planning technology, in particular to a multi-window heuristic three-dimensional space path planning method based on Rubik's Cube model. Background technique [0002] Path planning technology is a key technology necessary for unmanned systems such as robots and UAVs to be put into practical applications. With the continuous breakthrough of the current sensor technology, the speed and accuracy of environmental perception are also continuously improved. On this basis, the path planning of the unmanned system can be carried out more accurately and safely. [0003] The purpose of path planning is to find an optimal or suboptimal collision-free path from the start point to the end point according to some evaluation index in an environment with obstacles. Existing technologies can be roughly divided into two categories: global path planning and local path planning. Th...

AI Technical Summary

Problems solved by technology

However, the shortcomings of this method are also obvious. First of all, the original 26-dimensional freedom in three-dimensional space is constrained to six dimensions, resulting in constraints on the final planning results, which cannot be used in applications such as unmanned aerial vehicles and unmanned submersibles in three-dimensional space. Equipment flexibility

Secondly, the existing methods only pay attention to the occupancy of the grid point when exploring candidate grid points, and often ignore the situation around the candidate grid point. Therefore, in order to ensure safety, it is necessary to inflate the obstacles in the prior information one by one. , the steps are cumbersome, resulting in low efficiency and low practicability of the algorithm

Images