Evaluation Simulator Platform for Extended Collision Risk of Autonomous Surface Vehicles

Abstract

Autonomous surface vehicles need to be at least as safe as conventional vessels, if not safer, when navigating on waters. With a great deal of navigation algorithms for surface vessels out there, the safety of their produced paths is questionable, and, in most cases, complicated to assess and compare. Hence, this paper proposes a method for extended collision risk assessment for paths generated by autonomous navigation algorithms as follows: (1) static, dynamic, and historic risk factors are calculated; (2) individual risk value is determined using a fuzzy inference system; (3) the extended collision risk assessment (ECRA) score is acquired using a root-mean-square method. Finally, a comparison of the ECRA score of each path determines the path with the lowest risk. The validation results show that the proposed method is able to detect lower/higher risk scenarios and assign an adequate risk value in most cases. Risk reduction for cautious paths varies up to 8.43%, while risk increases for incautious paths—up to 57.98%. The results indicate that the method could be used for navigation algorithm evaluation and comparison with some improvements. This research also reveals several promising future directions and applications of the method.

Collision Avoidance for ASVs in Archipelagos―A COLREGs-Aware Optimization-Based Method

“…The first four directions are the expansion of a box centered at q exp (or q SO,exp ), with an expansion limit of l max , and the fifth direction is along the nominal path, toward q max . For each expansion j ∈ [1,5], expand a step d j along the corresponding direction, if it is not possible decrease the step size d j in the next iteration. Stop expansion j if d j is smaller than a defined value, here 5 m was used.…”

“…The results presented here are in selected scenarios for demonstration of the method. There are numerous scenarios that can be created, and methods to evaluate the overall performance of such an algorithm and this is research of its own as discussed in, e.g., [4] and [5]. In order to execute the plan, the initial course and speed provided by the planner is, for simplicity, used as set points for course and speed until the next planning iteration.…”

“…This stage setting also poses uncertainty in how to evaluate an action in terms of safety and efficiency. Research on algorithm metrics and evaluation can be found in, e.g., Stankiewicz et al [4] and Vagale et al [5].…”