To the Noise and Back: Diffusion for Shared Autonomy

About To the Noise and Back: Diffusion for Shared Autonomy

Shared autonomy is an operational concept in which a user and an autonomous agent collaboratively control a robotic system. It provides a number of advantages over the extremes of full-teleoperation and full-autonomy in many settings. Traditional approaches to shared autonomy rely on knowledge of the environment dynamics, a discrete space of user goals that is known a priori, or knowledge of the user's policy---assumptions that are unrealistic in many domains. Recent works relax these assumptions by formulating shared autonomy with model-free deep reinforcement learning (RL), and train the agent's policy that produces an action close to that of the user while satisfying value function constraints. These formula

Key Topics

Details