Scalable Underwater Assembly with Reconfigurable Visual Fiducials

We present a scalable combined localization in- frastructure deployment and task planning algorithm for un- derwater assembly. Infrastructure is autonomously modified to suit the needs of manipulation tasks based on an uncertainty model on the infrastructure’s positional accuracy. Our uncer- tainty model can be combined with the noise characteristics from multiple sensors. For the task planning problem, we propose a layer-based clustering approach that completes the manipulation tasks one cluster at a time. We employ movable visual fiducial markers as infrastructure and an autonomous underwater vehicle (AUV) for manipulation tasks. The pro- posed task planning algorithm is computationally simple, and we implement it on AUV without any offline computation re- quirements. Combined hardware experiments and simulations over large datasets show that the proposed technique is scalable to large areas.