Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy
This addresses safety and performance trade-offs in interactive robot autonomy, representing a novel paradigm rather than an incremental improvement.
The paper tackles the challenge of ensuring safe interaction with humans in robotic systems like autonomous vehicles without compromising performance, by proposing a closed-loop paradigm that synthesizes safe control policies accounting for evolving uncertainty and adaptive learning, and demonstrates its framework using adversarial reinforcement learning with Bayesian belief propagation and neural trajectory predictors.
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.