Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloads

Abstract

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

References in corpus (8)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Playing Atari with Deep Reinforcement Learning
• Trust Region Policy Optimization
• QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
• Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control
• Meta Reinforcement Learning with Latent Variable Gaussian Processes
• Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions
• Efficient transfer learning and online adaptation with latent variable models for continuous control

Cited by in corpus (12)

• Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds
• Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control
• A Tutorial on Meta-Reinforcement Learning
• Neural Moving Horizon Estimation for Robust Flight Control
• RotorTM: A Flexible Simulator for Aerial Transportation and Manipulation
• A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques
• Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments
• Differentiable Moving Horizon Estimation for Robust Flight Control
• Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning
• Adaptive Asynchronous Control Using Meta-learned Neural Ordinary Differential Equations
• Intercepting Unauthorized Aerial Robots in Controlled Airspace Using Reinforcement Learning
• Improved Robustness and Safety for Pre-Adaptation of Meta Reinforcement Learning with Prior Regularization