Learning Speed Adaptation for Flight in Clutter
This work addresses the challenge of balancing aggressiveness and safety for mobile robots in cluttered environments, representing an incremental advance by combining model-based methods with trial-and-error learning.
The paper tackles the problem of enabling flight vehicles to adapt their speed in unknown, cluttered environments by proposing a hierarchical learning and planning framework that uses online reinforcement learning to learn a policy for dynamic speed configuration. The results show advantages over constant-speed baselines in simulation and real-world deployment, with improvements in flight efficiency and safety, though specific numbers are not provided.
Animals learn to adapt speed of their movements to their capabilities and the environment they observe. Mobile robots should also demonstrate this ability to trade-off aggressiveness and safety for efficiently accomplishing tasks. The aim of this work is to endow flight vehicles with the ability of speed adaptation in prior unknown and partially observable cluttered environments. We propose a hierarchical learning and planning framework where we utilize both well-established methods of model-based trajectory generation and trial-and-error that comprehensively learns a policy to dynamically configure the speed constraint. Technically, we use online reinforcement learning to obtain the deployable policy. The statistical results in simulation demonstrate the advantages of our method over the constant speed constraint baselines and an alternative method in terms of flight efficiency and safety. In particular, the policy behaves perception awareness, which distinguish it from alternative approaches. By deploying the policy to hardware, we verify that these advantages can be brought to the real world.