부산대학교 도서관

In marine robotics, data-collection operations often require an autonomous underwater vehicle (AUV) to collaborate with an unmanned surface vehicle (USV). The mission for the AUV is to reach many goal locations, avoid obstacles and unsafe areas, and maintain communication with the USV. The goals, however, are not known a priori, but are dynamically discovered by the USV as it moves along a predefined path. The USV communicates the discovered goals to the AUV along with rewards for reaching each goal to incentivize the AUV to increase the sum of the rewards when obstacles, time, and communication constraints make it impossible to reach all the goals. We develop a framework comprised of an execution module and a multi-layered planner to enable the AUV to avoid collisions, maintain communication with the USV, and increase the sum of the rewards by reaching many of the discovered goals. The execution module enables the AUV to follow the planned motions, invoking the planner when new goals are discovered. To facilitate navigation, the planner constructs a 3D roadmap that captures the connectivity of the environment by sampling and connecting waypoints in the free space. The high-level planning layer is based on informed discrete search to find roadmap paths that satisfy the communication constraints and increase the sum of the goal rewards. The low-level layer uses sampling-based motion planning to expand a tree of feasible motions along these roadmap paths. The layers interact to update the planned motions as new goals are discovered. Experiments using 3D environments and an increasing number of goals demonstrate the efficiency of the approach to solve dynamic multi-goal motion-planning problems with communication constraints. Note to Practitioners— This paper is motivated by the problem of at-sea data collection using unmanned vehicles where inter-vehicle communications constraints must be maintained. This is a challenging problem that has generally required significant human monitoring and intervention due to the communication constraints and planning challenges. In this paper, we leverage recent advances in underwater communications and focus on new problems that arise in the planning space, specifically, how we generate trajectories for an AUV that satisfies communication range constraints while still performing an underlying task. We show that it is possible to plan for an AUV in real-time while considering these constraints. This paper suggests that our approach can support these complex at-sea missions. Future research will focus on field deployments and introducing more uncertainty into the underlying sensor models during planning.