A Robust Reactive Static Obstacle Avoidance System for Surface Marine Vehicles

Abstract

This paper is centered on the guidance systems used to increase the autonomy of unmanned surface vehicles (USVs). The new Robust Reactive Static Obstacle Avoidance System (RRSOAS) has been specifically designed for USVs. This algorithm is easily applicable, since previous knowledge of the USV mathematical model and its controllers is not needed. Instead, a new estimated closed-loop model (ECLM) is proposed and used to estimate possible future trajectories. Furthermore, the prediction errors (due to the uncertainty present in the ECLM) are taken into account by modeling the USV’s shape as a time-varying ellipse. Additionally, in order to decrease the computation time, we propose to use a variable prediction horizon and an exponential resolution to discretize the decision space. As environmental model an occupancy probability grid is used, which is updated with the measurements generated by a LIDAR sensor model. Finally, the new RRSOAS is compared with other SOA (static obstacle avoidance) methods. In addition, a robustness study was carried out over a set of random scenarios. The results obtained through numerical simulations indicate that RRSOAS is robust to unknown and congested scenarios in the presence of disturbances, while offering competitive performance with respect to other SOA methods.

A Review of Artificial Intelligence-Based Optimization Applications in Traditional Active Maritime Collision Avoidance

“…Rather, it uses an estimated closed-loop model (ECLM) to estimate the likely future trajectory of the USV and accounts for prediction errors caused by uncertainty by modeling the shape of the USV as a time-varying ellipse. Using an occupancy probability grid as the environment model updated by the LiDAR sensor model, the algorithm utilizes a variable prediction horizon and exponential resolution to discretize the decision space [103].…”