Enhao Zhang’s research while affiliated with Chongqing University of Technology and other places

In this paper, an improved sparrow search algorithm (SSA) for local path planning problem of mobile robot in an unknown environment is presented. The problems of premature convergence and decline of population diversity of basic SSA are solved by the inspiration of fitness-distance balance (FDB) selection and Harris Hawks Algorithm. A hybrid fitness function is formulated considering both path length and path safety, which enables the mobile robot to move to the target location safely. The effectiveness and superiority of the proposed improved SSA (ISSA) is verified in CEC 2017 suite for comparison experiments with multiple intelligent optimization algorithms. Local path planning simulation experiments are implemented using the proposed algorithm in the unknown environment and compared with other algorithms, and the results show that our algorithm is effective and robust in solving local path planning problem of mobile robots.

In this paper, an improved intelligence algorithm is proposed for path planning problem. The algorithm is based on Sparrow Search Algorithm and is combined with Random Opposition-based Learning and linear decreasing strategy, named ROSSA. The mobile robot path planning problem can be mathematically transformed into an optimization problem, which can be solved by intelligent optimization algorithms. With this consideration, an SSA-based optimization algorithm is proposed. Random opposition-based learning increases the diversity of the population and enhances the exploration ability of the algorithm; the linear decreasing strategy balances the ability of the algorithm to explore globally and exploit locally by adjusting the algorithm parameters. Meanwhile, the Bezier curve satisfies the requirement of path smoothness for the robot path planning problem. The superiority of the proposed algorithm is verified by conducting experiments with three standard algorithms for 11 benchmark test functions, and some comparison experiments on the path planning problem with PSO and SSA to confirm that the proposed algorithm can find a safe and optimal path in the mobile robot path planning problem.