Modified Continuous Ant Colony Optimisation with Local Search for Multiple Unmanned Aerial Vehicle Path Planning

This paper introduces a new algorithm named modified continuous ant colony optimisation with local search (MACO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</inf>-LS), designed to address the path planning problem for multiple unmanned aerial vehicles (UAVs) in an environment with various obstacles and threats. The goal of the algorithm is to optimise the flight paths of each UAV. The proposed algorithm incorporates a highly effective local search strategy, Broyden-Fletcher-Goldfarb-Shanno, building upon the foundation of a continuous ant colony optimisation with a probability-based random-walk strategy and an adaptive waypoints-repair method. By integrating the strategy of local search, the proposed algorithm reduces the cost associated with each UAV path planning. Experiments are conducted to compare MACO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</inf>-LS to three other advanced algorithms in six cases. Compared to the other algorithms, the experimental results show that MACO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</inf>-LS exhibits significantly better optimal path costs. This underscores its superiority in addressing multi-UAV path planning challenges.