Unmanned aerial vehicle path planning faces multiple challenges in terms of effectiveness and safety. Traditional optimization methods are difficult to use to effectively find the best route. An enhanced artificial lemming optimization algorithm (ALAEN) is proposed here, which introduces stochastic differential mutation and Beta opposition-based learning into the artificial lemming algorithm (ALA). The comparison with other algorithms on the CEC2017 test set shows that it can effectively improve the optimization ability and convergence speed of the artificial lemming algorithm. Among all algorithms, ALA has an overall ranking of 5.45 and ALAEN has a ranking of 1.34. The ability of ALAEN to solve the actual problem of UAV trajectory planning is tested on two different maps, and it is found that it can effectively improve the path planning ability and ensure safety compared with the ALA. In the small map scene, the average cost function of ALA is 92.999, and the average cost function of ALAEN is 91.598, which is a significant improvement. Compared with other algorithms, ALAEN has the shortest trajectory route and trajectory cost function.
Liu et al. (Fri,) studied this question.