Underwater vehicle obstacle avoidance and path planning using a multi-beamforward looking sonar

This paper describes a new framework for segmentation of sonar images, trac king of underwater objects and motion estimation. This framework is applied to the design of an obstacle avoidance and path planning system for underw ater vehicles based on a multi-beam forward looking sonar sensor The real-t ime data flow (acoustic images) at the input of the system is first segment ed and relevant features are extracted. We also take advantage of the real- time data stream to track the obstacles in following frames to obtain their dynamic characteristics. This allows us to optimize the preprocessing phas es in segmenting only the relevant part of the images. Once the static (siz e and shape) as well as dynamic characteristics (velocity, acceleration, .. .) of the obstacles have been computed, we create a representation of the v ehicle's workspace based on these features. This representation uses constr uctive solid geometry (CSG) to create a convex set of obstacles defining th e workspace. The tracking takes also into account obstacles which are no lo nger in the field of view of the sonar in the path planning phase. A well-p roven nonlinear search (sequential quadratic programming) is then employed, where obstacles are expressed as constraints in the search space. This app roach is less affected by local minima than classical methods using potenti al fields. The proposed system is not only capable of obstacle avoidance bu t also of path planning in complex environments which include fast moving o bstacles. Results obtained on real sonar data are shown and discussed. Poss ible applications to sonar servoing and real-time motion estimation are als o discussed.