When Your Robot Breaks: Active Learning During Plant Failure

TL;DR

This paper introduces a probabilistically-safe, real-time active learning framework combining model predictive control and neural networks to quickly adapt to robotic failures, demonstrated on damaged aircraft in simulation.

Contribution

It presents a novel online learning method that safely and efficiently infers altered robot dynamics during failures using neural networks and chance-constrained optimization.

Findings

Regains control of damaged aircraft within seconds

Finds safe, information-rich trajectories in 0.1 seconds

Outperforms state-of-the-art approaches in simulation

Abstract

Detecting and adapting to catastrophic failures in robotic systems requires a robot to learn its new dynamics quickly and safely to best accomplish its goals. To address this challenging problem, we propose probabilistically-safe, online learning techniques to infer the altered dynamics of a robot at the moment a failure (e.g., physical damage) occurs. We combine model predictive control and active learning within a chance-constrained optimization framework to safely and efficiently learn the new plant model of the robot. We leverage a neural network for function approximation in learning the latent dynamics of the robot under failure conditions. Our framework generalizes to various damage conditions while being computationally light-weight to advance real-time deployment. We empirically validate within a virtual environment that we can regain control of a severely damaged aircraft in seconds and require only 0.1 seconds to find safe, information-rich trajectories, outperforming state-of-the-art approaches.