Autonomous miniature blimp navigation with online motion planning and re-planning

In recent years, there has been an increasing interest in autonomous navigation for lightweight flying robots in indoor environments. Miniature airships, which are an instance of such robots, are especially challenging since they behave nonlinearly, typically are under-actuated, and also are subject to drift. These aspects, paired with their high-dimensional state space, demand efficient planning and control techniques. In this paper, we present a highly effective approach to autonomous navigation of miniature blimps in mapped environments which applies a multi-stage algorithm to accomplish strongly goal-directed tree-based kinodynamic planning. It performs path-guided sampling and optimally selects actions leading the robot towards sampled subgoals. Based on this, our approach can quickly provide a partial trajectory, which is extended and refined in the consecutive planning steps. The navigation system has been implemented and is able to reliably operate a robotic blimp in a real-world setting. Further experiments demonstrate that our approach outperforms a standard tree planner.