Adaptive Asynchronous Control Using Meta-learned Neural Ordinary Differential Equations
This addresses challenges in real-world robotics control, but it appears incremental as it builds on existing meta-learning and neural ODE methods.
The paper tackled the problems of irregular/asynchronous observations and actions and dramatic changes in environment dynamics in robotics by proposing a meta-learning framework for adaptive dynamics models, achieving successful evaluations in simulations and on a real industrial robot.
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.