Influence of Gripper Design on Human Demonstration Quality for Robot Learning
Gina Georgadarellis, Natalija Beslic, Seonhun Lee, Frank Sup IV, Meghan Huber
AI summary
Problem
Handheld gripper tools for robot learning from demonstration often lack the mechanical design needed for complex healthcare manipulation, leading to poor demonstration quality and high user burden.
Approach
Eight participants performed a bimanual bandage-opening task using two modified handheld gripper designs and bare hands, with performance metrics and perceived workload measured to compare the impact of finger load distribution.
Key results
- 100% success rate with concentrated load grippers versus 65.8% with distributed load grippers
- 4× faster task completion with concentrated load grippers
- Significantly higher mental and physical workload with distributed load grippers
- Both gripper designs remained substantially slower than bare hands
Why it matters
Robotics researchers and healthcare automation developers must prioritize ergonomic gripper mechanics to ensure efficient, high-quality human demonstrations for training assistive robots.
Abstract
Opening sterile medical packaging is routine for healthcare workers but remains challenging for robots. Learn- ing from demonstration enables robots to acquire manipulation skills directly from humans, and handheld gripper tools such as the Universal Manipulation Interface (UMI) offer a pathway for efficient data collection. However, the effectiveness of these tools depends heavily on their usability. We evaluated UMI in demon- strating a bandage opening task, a common manipulation task in hospital settings, by testing three conditions: distributed load grippers, concentrated load grippers, and bare hands. Eight participants performed timed trials, with task performance assessed by success rate, completion time, and damage, along- side perceived workload using the NASA-TLX questionnaire. Concentrated load grippers improved performance relative to distributed load grippers but remained substantially slower and less effective than hands. These results underscore the impor- tance of ergonomic and mechanical refinements in handheld grippers to reduce user burden and improve demonstration quality, especially for applications in healthcare robotics.