Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloads
This addresses a critical safety and performance issue for autonomous drones in logistics or rescue operations, but it is incremental as it builds on existing meta-learning and adaptive control techniques.
The paper tackles the problem of autonomous aerial vehicles transporting suspended payloads with unknown properties, which cause unpredictable dynamic changes, by proposing a meta-learning approach that adapts models within seconds using post-connection flight data, and it outperforms non-adaptive methods in experiments.
Transporting suspended payloads is challenging for autonomous aerial vehicles because the payload can cause significant and unpredictable changes to the robot's dynamics. These changes can lead to suboptimal flight performance or even catastrophic failure. Although adaptive control and learning-based methods can in principle adapt to changes in these hybrid robot-payload systems, rapid mid-flight adaptation to payloads that have a priori unknown physical properties remains an open problem. We propose a meta-learning approach that "learns how to learn" models of altered dynamics within seconds of post-connection flight data. Our experiments demonstrate that our online adaptation approach outperforms non-adaptive methods on a series of challenging suspended payload transportation tasks. Videos and other supplemental material are available on our website: https://sites.google.com/view/meta-rl-for-flight