Multi-vehicle Dynamic Water Surface Monitoring

Repeated exploration of a water surface to detect objects interest and their subsequent monitoring is important in search-and-rescue or ocean clean-up operations. Since the location any detected object dynamic, we propose address combined by modeling spatio-temporal reward states coordinating team vehicles collect rewards. The model characterizes dynamics enables planner predict future system states. state value relevant particular cell increases over time nullified being sensor range vehicle. Thus, proposed multi-vehicle planning approach minimize collective dynamic purpose vehicles' motion constraints using predictive control on receding horizon fully exploiting utilized capabilities. Based evaluation results, indicates improvement solution kinematic orienteering problem task compared existing solutions. has been experimentally verified, supporting its feasibility real-world tasks.