Multicriterion Offline Path Planning of a Biomimetic Underwater Vehicle Using NSGA II

In this paper an optimal 3-D path is generated offline for a Biomimetic Underwater Vehicle (BUV). The BUV swims forward by oscillating its body, turns by curving its body and dives by bending its head. The BUV is intended to systematically plan its path having only the initial and final points and the positions and dimensions of the obstacles. The four widely-accepted criteria of the optimal path planning of the BUV are “overall path length”, “margin of safety”, “smoothness of planar motion” and “gradient of dive”. In this study the multi-objective GA algorithm NSGA-II is employed to find a set of Pareto-optimal solutions where each solution represents a path that cannot be outrun by any other path considering all four criteria. The solution set, also called the Pareto front, gives the designer the freedom of choice when it comes to prioritizing various criteria.