How to Train Your Robots? The Impact of Demonstration Modality on Imitation Learning
Authors:
- 19 May 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1113-1120
Abstract
Imitation learning is a promising approach for learning robot policies with user-provided data. The way demonstrations are provided, i.e., demonstration modality, influences the quality of the data. While existing research shows that kinesthetic teaching (physically guiding the robot) is preferred by users for the intuitiveness and ease of use, the majority of existing manipulation datasets were collected through teleoperation via a VR controller or spacemouse. In this work, we investigate how different demonstration modalities impact downstream learning performance as well as user experience. Specifically, we compare low-cost demonstration modalities including kinesthetic teaching, teleoperation with a VR controller, and teleoperation with a spacemouse controller. We experiment with three table-top manipulation tasks with different motion constraints. We evaluate and compare imitation learning performance using data from different demonstration modalities, and collected subjective feedback on user experience. Our results show that kinesthetic teaching is rated the most intuitive for controlling the robot and provides cleanest data for best downstream learning performance. However, it is not preferred as the way for large-scale data collection due to the physical load. Based on such insight, we propose a simple data collection scheme that relies on a small number of kinesthetic demonstrations mixed with data collected through teleoperation to achieve the best overall learning performance while maintaining low data-collection effort.Keywords
All Related Versions
Funding Information
- NSF (2132847,2218760,ONR N00014-21-1-2298,AFOSR YIP)
- DARPA (W911NF2210214)
This publication has 20 references indexed in Scilit:
- Bottom-Up Skill Discovery From Unsegmented Demonstrations for Long-Horizon Robot ManipulationIEEE Robotics and Automation Letters, 2022
- Training Human Teacher to Improve Robot Learning from Demonstration: A Pilot Study on Kinesthetic Teaching2020
- A review of haptic feedback in tele-operated robotic surgeryJournal of Medical Engineering & Technology, 2020
- A VR System for Immersive Teleoperation and Live Exploration with a Mobile Robot2019
- An Autonomous Dynamic Camera Method for Effective Remote Teleoperation2018
- Deep Residual Learning for Image Recognition2016
- On handing down our tools to robots: Single-phase kinesthetic teaching for dynamic in-contact tasks2015
- Trajectories and keyframes for kinesthetic teaching2012
- A survey of robot learning from demonstrationRobotics and Autonomous Systems, 2009
- Robot Programming by Demonstration2008