MetaTune: Adjoint-based Meta-tuning via Robotic Differentiable Dynamics

TL;DR

MetaTune introduces an adjoint-based meta-learning framework for joint auto-tuning of controllers and disturbance observers in robotic systems, improving robustness and efficiency across diverse tasks.

Contribution

It presents a novel adjoint method for efficient gradient computation in differentiable system dynamics, enabling adaptive gain tuning with reduced computational complexity.

Findings

Achieves over 50% reduction in gradient computation time.

Improves tracking error by 15-20% in high-speed quadrotor flights.

Demonstrates zero-shot transfer in hardware-in-the-loop simulations.

Abstract

Disturbance observer-based control has shown promise in robustifying robotic systems against uncertainties. However, tuning such systems remains challenging due to the strong coupling between controller gains and observer parameters. In this work, we propose MetaTune, a unified framework for joint auto-tuning of feedback controllers and disturbance observers through differentiable closed-loop meta-learning. MetaTune integrates a portable neural policy with physics-informed gradients derived from differentiable system dynamics, enabling adaptive gain across tasks and operating conditions. We develop an adjoint method that efficiently computes the meta-gradients with respect to adaptive gains backward in time to directly minimize the cost-to-go. Compared to existing forward methods, our approach reduces the computational complexity to be linear in the data horizon. Experimental results on quadrotor control show that MetaTune achieves consistent improvements over state-of-the-art differentiable tuning methods while reducing gradient computation time by more than 50 percent. In high-fidelity PX4-Gazebo hardware-in-the-loop simulation, the learned adaptive policy yields 15-20 percent average tracking error reduction at aggressive flight speeds and up to 40 percent improvement under strong disturbances, while demonstrating zero-shot sim-to-sim transfer without fine-tuning.