HITL-D: Human In The Loop Diffusion Assisted Shared Control

TL;DR

HITL-D introduces a shared control framework combining diffusion-based policies with human input, significantly improving task efficiency and user experience in robotic manipulation tasks.

Contribution

The paper presents HITL-D, a novel human-in-the-loop diffusion-assisted control method that reduces workload and enhances performance in robotic manipulation.

Findings

Reduced task completion time by 40%

Lowered perceived workload by 37%

Improved user ratings for independence, intuitiveness, and confidence

Abstract

Autonomous manipulation systems have achieved remarkable capabilities, yet the integration of human expertise with diffusion-based policies in shared control remains relatively unexplored. In this paper, we propose Human-In-The-Loop Diffusion (HITL-D), a shared control framework that enhances user performance in multi-step, insertion, and fine manipulation tasks. HITL-D leverages a novel combination of diffusion-based policies and human control to provide autonomous end effector orientation updates conditioned on a scene point cloud and the Cartesian position of the end effector. This approach reduces the number of joystick control axes required, thereby lowering mental workload. In a multi-task user study with 12 participants, HITL-D reduced average task completion times by 40%, decreased perceived workload by 37%, and improved Likert-scale ratings for independence, intuitiveness, and confidence compared to traditional teleoperation methods. These results demonstrate that HITL-D effectively integrates human expertise with autonomous assistance, improving both objective and subjective aspects of teleoperation.