UACE2017 Proceedings: Autonomous Trajectory Design System for Mapping of Unknown Sea-floors using a team of AUVs



  • Session:
    Underwater vehicles and acoustic sensing
  • Paper:
    Autonomous Trajectory Design System for Mapping of Unknown Sea-floors using a team of AUVs
  • Author(s):
    Georgios Salavasidis, Athanasios Kapoutsis, Elias Kosmatopoulos
  • Abstract:
    This research aims to develop new on-line trajectory planning algorithms for a team of Autonomous Underwater Vehicles (AUVs). The mission goal is exploration and mapping of ocean sea-floors, where the AUVs have to cooperatively acquire environmental information in order to construct the terrain morphology. As the morphology of the seabed is unknown and complex, standard non- convex algorithms are not sufficient. To tackle this, a new simulation-based approach adapting the Parametrized Cognitive-based Adaptive Optimization (PCAO) algorithm is proposed and evaluated. This approach transforms the exploration problem to a parametrized decision-making mechanism whose real-time implementation is practically feasible. Upon that transformation, this scheme calculates off-line a set of decision making mechanism's parameters that approximate the - non-practically feasible - optimal solution. The advantages of the algorithm are significant computational simplicity, scalability, and the fact that it can straightforwardly embed any type of physical constraints and system limitations (e.g. obstacle avoidance, nonlinear sensor noise models, etc.). The algorithm is trained over a set of morphologically different maps. During this learning part, the PCAO algorithm outperforms an unrealistic optimal-one- step-ahead search algorithm. Furthermore, to generalize the results, we apply the best learnt controller to a new set of morphologically different sea-floors. The potential of the PCAO is demonstrated by outperforming several gradient-descent-like approaches.
  •   Download the full paper

Contact details

  • Contact person:
    Mr Athanasios Kapoutsis
  • e-mail:
  • Affiliation:
    Democritus University of Thrace
  • Country:
    Greece