Leveraging Symmetry to Accelerate Learning of Trajectory Tracking Controllers for Free-Flying Robotic Systems

Published: 23 Oct 2024, Last Modified: 24 Feb 2025NeurReps 2024 OralEveryoneRevisionsBibTeXCC BY 4.0
Keywords: MDP Homomorphisms, Lie Groups, Reinforcement Learning, Equivariance, Robotics, Trajectory Tracking
TL;DR: We leverage the natural Lie group symmetries of robotic systems to reduce the trajectory tracking problem to a reduced-order MDP via a continuous MDP homomorphism, leading to accelerated learning of tracking controllers via reinforcement learning.
Abstract: Tracking controllers enable robotic systems to accurately follow planned reference trajectories. In particular, reinforcement learning (RL) has shown promise in the synthesis of controllers for systems with complex dynamics and modest online compute budgets. However, the poor sample efficiency of RL and the challenges of reward design make training slow and sometimes unstable, especially for high-dimensional systems. In this work, we leverage the inherent Lie group symmetries of robotic systems with a floating base to mitigate these challenges when learning tracking controllers. We model a general tracking problem as a Markov decision process (MDP) that captures the evolution of both the physical and reference states. Next, we show that symmetry in the underlying dynamics and running costs leads to an MDP homomorphism, a mapping that allows a policy trained on a lower-dimensional “quotient” MDP to be lifted to an optimal tracking controller for the original system. We compare this symmetry-informed approach to an unstructured baseline, using Proximal Policy Optimization (PPO) to learn tracking controllers for three systems: the Particle (a forced point mass), the Astrobee (a fully-actuated space robot), and the Quadrotor (an underactuated system). Results show that a symmetry-aware approach accelerates training and reduces tracking error after the same training duration.
Submission Number: 71
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview