Search papers, labs, and topics across Lattice.
This paper introduces MAVEN, a meta-RL framework designed to train a single policy capable of robust quadrotor navigation across a wide range of dynamic variations. MAVEN employs a predictive context encoder to infer a latent representation of system dynamics from interaction history, enabling adaptation to varying quadrotor mass and rotor failure. Experiments demonstrate MAVEN's superior adaptation and agility in simulation and real-world scenarios, achieving zero-shot sim-to-real transfer with significant mass variations and thrust losses.
A single meta-RL policy can now handle 66% mass variations and 70% rotor thrust losses in quadrotors, achieving zero-shot sim-to-real transfer for agile maneuvers.
Reinforcement learning (RL) has emerged as a powerful paradigm for achieving online agile navigation with quadrotors. Despite this success, policies trained via standard RL typically fail to generalize across significant dynamic variations, exhibiting a critical lack of adaptability. This work introduces MAVEN, a meta-RL framework that enables a single policy to achieve robust end-to-end navigation across a wide range of quadrotor dynamics. Our approach features a novel predictive context encoder, which learns to infer a latent representation of the system dynamics from interaction history. We demonstrate our method in agile waypoint traversal tasks under two challenging scenarios: large variations in quadrotor mass and severe single-rotor thrust loss. We leverage a GPU-vectorized simulator to distribute tasks across thousands of parallel environments, overcoming the long training times of meta-RL to converge in less than an hour. Through extensive experiments in both simulation and the real world, we validate that MAVEN achieves superior adaptation and agility. The policy successfully executes zero-shot sim-to-real transfer, demonstrating robust online adaptation by performing high-speed maneuvers despite mass variations of up to 66.7% and single-rotor thrust losses as severe as 70%.
