Improved artificial bee colony algorithm-based path planning of unmanned autonomous helicopter using multi-strategy evolutionary learning

Abstract

Aiming at producing a high-quality flight path for the unmanned autonomous helicopter with multi-constraints, a path planning method is proposed based on the multi-strategy evolutionary learning artificial bee colony algorithm in this paper. Firstly, an evolutionary learning framework is established for the artificial bee colony algorithm based on brain-like cognition. By integrating the swarm intelligence and human cognitive mechanism, this framework gives more autonomy and intelligence to the bee colony. In addition, a multi-strategy evolutionary database is built based on the evolutionary learning framework to replace the traditional evolutionary approach of the artificial bee colony algorithm. Different nectar sources adopt different evolutionary strategies according to the integrated feedback mechanism, and evolutionary behavioral selection probability is updated through the accumulation of experience and the exploration of new knowledge. The simulation results show that the trajectories produced by the multi-strategy evolutionary learning artificial bee colony algorithm have better fuel economy and higher safety than other comparison algorithms, and the number of optimization iterations can be reduced by at least 12%.