Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy

TL;DR

This paper introduces a closed-loop safety framework for interactive robots that integrates learning and adaptation at runtime, enhancing safety without overly conservative behavior.

Contribution

It presents a novel paradigm combining physical dynamics and learning algorithms for safe control policy synthesis in robots.

Findings

Effective safety analysis using adversarial reinforcement learning.

Framework works with Bayesian belief propagation and neural trajectory predictors.

Demonstrated improved safety and adaptability in robotic systems.

Abstract

An outstanding challenge for the widespread deployment of robotic systems like autonomous vehicles is ensuring safe interaction with humans without sacrificing performance. Existing safety methods often neglect the robot's ability to learn and adapt at runtime, leading to overly conservative behavior. This paper proposes a new closed-loop paradigm for synthesizing safe control policies that explicitly account for the robot's evolving uncertainty and its ability to quickly respond to future scenarios as they arise, by jointly considering the physical dynamics and the robot's learning algorithm. We leverage adversarial reinforcement learning for tractable safety analysis under high-dimensional learning dynamics and demonstrate our framework's ability to work with both Bayesian belief propagation and implicit learning through large pre-trained neural trajectory predictors.