Augmented Action-Space Whole-Body Teleoperation of Mobile Manipulation Robots
Sophie Lueth and Georgia Chalvatzaki
Sophie Lueth and Georgia Chalvatzaki
TLDR: Novel teleoperation framework beyond end-effector control by enabling multi-contact, whole-body coordination for mobile manipulators. This augmented action-space allows to efficiently execute complex household tasks and collect high-quality demonstration data leveraging the synergy of different parts of the robot's body for future imitation learning.
Abstract
We present a novel approach for whole-body teleoperation of mobile manipulation robots, focusing on complex household tasks that require coordination of arms manipulation and robot-body posture while enabling multiple contact points along the robot’s kinematic chain. Current state-of-the-art methods often overlook the synergy between different parts of the robot’s body, particularly in humanoid robots, as they typically rely on end-effector actions alone. In contrast, we propose a teleoperation framework that supports multi-embodiment and multi-contact teleoperation, allowing for efficient whole-body control that enhances task execution in real-world scenarios and brings robots closer to human-like behaviors. Our augmented action-space compliant teleoperation interface enables users to control the robot and collect high-quality demonstrations for future imitation learning. Preliminary experiments demonstrate promising results, with high success rates in task completion, suggesting the potential of our approach for robust and efficient teleoperation.