Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation
This addresses the challenge of real-world reinforcement learning for mobile manipulation, offering a fully autonomous solution that could reduce reliance on human supervision and instrumentation in robotics.
The authors tackled the problem of enabling robots to autonomously learn combined navigation and grasping skills in real-world settings without human intervention, achieving this through their ReLMM system, which learned a room cleanup task in about 40 hours of training.
We study how robots can autonomously learn skills that require a combination of navigation and grasping. While reinforcement learning in principle provides for automated robotic skill learning, in practice reinforcement learning in the real world is challenging and often requires extensive instrumentation and supervision. Our aim is to devise a robotic reinforcement learning system for learning navigation and manipulation together, in an autonomous way without human intervention, enabling continual learning under realistic assumptions. Our proposed system, ReLMM, can learn continuously on a real-world platform without any environment instrumentation, without human intervention, and without access to privileged information, such as maps, objects positions, or a global view of the environment. Our method employs a modularized policy with components for manipulation and navigation, where manipulation policy uncertainty drives exploration for the navigation controller, and the manipulation module provides rewards for navigation. We evaluate our method on a room cleanup task, where the robot must navigate to and pick up items scattered on the floor. After a grasp curriculum training phase, ReLMM can learn navigation and grasping together fully automatically, in around 40 hours of autonomous real-world training.