Stable path planning algorithm for avoidance of dynamic obstacles

Previous research of path planning has focused mainly on finding shortest paths or smallest movements. These methods, however, have poor stability characteristics when dynamic obstacles are considered on real-life or in-body map's environments. In this paper, we suggest a stable path planning algorithm for avoidance of dynamic obstacles. The proposed method makes the movement of a mobile robot more stable in a dynamic environment. Our focus is based on finding optimal movements for stability rather than finding shortest paths or smallest movements. The algorithm is based on Genetic Algorithm (GA) and uses k-means clustering to recognize the distribution of dynamics obstacles in various mobile space. Simulation results confirm this method can determine stable paths through environments involving dynamic obstacles. In order to validate our results, we compared the dynamic k values used in k-means clustering and grid-based dynamic cell sizes from several test sets.