Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy
Preprint
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.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Contingency Games for Multi-Agent InteractionIEEE Robotics and Automation Letters, 2024
- Multi-Agent Reachability Calibration with Conformal Prediction2023
- GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving2023
- Safe Planning in Dynamic Environments Using Conformal PredictionIEEE Robotics and Automation Letters, 2023
- Parameter-Conditioned Reachable Sets for Updating Safety Assurances Online2023
- Online Update of Safety Assurances Using Confidence-Based Predictions2023
- Safety Assurances for Human-Robot Interaction via Confidence-aware Game-theoretic Human Models2022
- A Robust Control Framework for Human Motion PredictionIEEE Robotics and Automation Letters, 2020
- Guaranteed Obstacle Avoidance for Multi-Robot Operations With Limited Actuation: A Control Barrier Function ApproachIEEE Control Systems Letters, 2020
- Stochastic model predictive control with active uncertainty learning: A Survey on dual controlAnnual Reviews in Control, 2018