Adaptive Asynchronous Control Using Meta-learned Neural Ordinary Differential Equations

TL;DR

This paper introduces a meta-learning framework for adaptive control in robotics that handles asynchronous observations and dynamic environment changes, enabling more flexible and robust real-world applications.

Contribution

It proposes a novel meta-learning approach for neural ODE-based models that adapt to irregular data and changing dynamics in continuous-time control tasks.

Findings

Effective in robot simulations and real industrial robot

Handles asynchronous observations and environment changes

Improves adaptability in real-world robotics

Abstract

Model-based Reinforcement Learning and Control have demonstrated great potential in various sequential decision making problem domains, including in robotics settings. However, real-world robotics systems often present challenges that limit the applicability of those methods. In particular, we note two problems that jointly happen in many industrial systems: 1) Irregular/asynchronous observations and actions and 2) Dramatic changes in environment dynamics from an episode to another (e.g. varying payload inertial properties). We propose a general framework that overcomes those difficulties by meta-learning adaptive dynamics models for continuous-time prediction and control. The proposed approach is task-agnostic and can be adapted to new tasks in a straight-forward manner. We present evaluations in two different robot simulations and on a real industrial robot.