Developing Autonomy for Unmanned Surface Vehicles by Using Virtual Environments

摘要

We address the problem of automated synthesis of an action selection policy for an unmanned vehicle operating in an environment with a deceptive adversary. We introduce a new synthesis approach using which an initial version of the policy is automatically generated and then gradually refined by detecting and fixing its shortcomings. Our focus is specifically on automated synthesis of a policy used for blocking the advancement of an intruder boat toward a valuable target. The USV must generate specific maneuvers for blocking. The intruder is human competitive and exhibits a deceptive behavior so that the USV cannot exploit regularity in its attacking behavior. We compared the performance of a hand coded USVs blocking policy to the performance of a policy that was automatically synthesized. Our results show that the performance of the automatically generated USVs policy exceed the performance of the hand coded policy and thus demonstrates the feasibility of the proposed approach.