Robot grid sub-map amalgamation method based on immune self-adapted genetic algorithm

Abstract

The invention provides a robot grid sub-map fusion method based on immune adaptive genetic algorithm. A matrix corresponding to two grid sub-maps is regarded as an antigen. An antibody is plane transformation made by a second grid sub-map. An antibody colony generates a next antibody in operations of copying, crossing and mutation operator basing on affinity degree of the antigen and the antibody.A selection probability calculated according to similar vector distance guarantees multiformity of the antibody. On the base of an immune principle, a crossover probability and a mutation probabilityare adaptively adjusted according to sufficiency of the antibody to reduce a probability of local optimum. The invention has a high searching efficiency and can effectively search the best plane transformation randomly distributed in a searching space. The invention is especially fit for a multiple mobile robot grid sub-map fusion problem in complex environment. And the invention can realize information sharing among robots as soon as possible and effectively realize coordinating exploration among robots, and improve exploration efficiency.

Description

technical field [0001] The invention relates to a fusion method for each robot in a multi-mobile robot system to independently create a grid sub-map of a local environment. Background technique [0002] The prerequisite for a mobile robot to complete various intelligent tasks autonomously in an unknown environment is that the robot can continuously explore, perceive the environment and gradually create an environmental map autonomously. Multi-robot systems can accomplish complex tasks that a single robot cannot, such as search and rescue in hazardous areas, poisonous material handling, and military applications. [0003] The distributed system structure can give full play to the robustness of the multi-robot system. Each robot independently creates a sub-map of the local environment by fusing the perception information obtained by its own sensors. When appropriate, the robot fuses the sub-maps of the local environment created by other robots to realize Information sharing i...

AI Technical Summary

Problems solved by technology

The paper "Merging occupancy grid maps from multiple robots" published in "Proceedings of the IEEE" ("IEEE Proceedings") 94(7): 1384-1397 in 2006 does not consider the location It is estimated that if the cells of the grid map are free or occupied, they are represented by color, and the grid map is represented as a graph. The problem of map fusion is transformed into fixing one graph, and the other graph as a plane such as translation and rotation. Transform TR:(t x , t y , θ), until the same parts of the two images overlap, use a random walk search strategy to find the optimal translation and rotation parameters TR * :( x , t y , θ) * , but the convergence speed of the random walk search strategy is low, and the optimization efficiency is not high

However, the traditional genetic algorithm has the disadvantage of premature convergence due to the rapid decrease in the diversity of the population, and it is easy to fall into local optimum.

Images