Rao-combined artificial bee colony algorithm for minimum dose path planning in complex radioactive environments

Abstract

Nuclear power plant workers inevitably work in a radiation environment. Minimum dose path planning becomes an important issue in ensuring that they receive as little radiation as possible. However, a work environment with complex obstacles or narrow passages makes the problem of finding the path with the minimum dose more difficult. In this paper, we propose a meta-heuristic method to solve this problem. An algorithm called Rao-combined artificial bee colony (RABC) is proposed with a novel obstacle detour technique. The RABC algorithm combines the directional solution update method of the Rao algorithm with the traditional ABC algorithm to further improve performance. To evaluate the effectiveness of the proposed method, three hypothetical environments are simulated. In the first hypothetical environment where there are no obstacles and many radiation sources are scattered, the meta-heuristic algorithms, PSO, ABC and RABC are compared, and in the second hypothetical environment with narrow passages and obstacles, the grid-based A* algorithm and the sampling-based RRT* algorithm are used for comparison with RABC. The third hypothetical environment is a complex environment where many radiation sources and obstacles are distributed and there are narrow passages. In this case, the proposed algorithm is compared with the Dijkstra algorithm and the GB-RRT* algorithm, which is known as one of the best in obstacle avoidance. Experimental results show that the proposed method is superior in exploration and exploitation, convergence and robustness compared to other meta-heuristic algorithms as well as grid-based or sampling-based algorithms.