paper-with-me

Papers

How to Train Your Robots? The Impact of Demonstration Modality on Imitation Learning

2025-03-10 · Haozhuo Li, Yuchen Cui, Dorsa Sadigh

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.

📄 PDF Abstract BibTeX arXiv:2503.07017

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation Learning

Similar Papers 제목 키워드 기반

Chain-of-Modality: Learning Manipulation Programs from Multimodal Human Videos with Vision-Language-Models

2025-04-17 · Chen Wang, Fei Xia, Wenhao Yu, Tingnan Zhang 외

Learning to perform manipulation tasks from human videos is a promising approach for teaching robots. However, many manipulation tasks require changing control parameters during task execution, such as force, which visua…

Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks

2022-10-10 · Albert Yu, Raymond J. Mooney

Demonstrations and natural language instructions are two common ways to specify and teach robots novel tasks. However, for many complex tasks, a demonstration or language instruction alone contains ambiguities, preventin…

From Introspection to Best Practices: Principled Analysis of Demonstrations in Multimodal In-Context Learning

2024-07-01 · Nan Xu, Fei Wang, Sheng Zhang, Hoifung Poon 외

Motivated by in-context learning (ICL) capabilities of Large Language models (LLMs), multimodal LLMs with additional visual modality are also exhibited with similar ICL abilities when multiple image-text pairs are provid…

In-Context Learning

State Representation Learning from Demonstration

2019-09-15 · Astrid Merckling, Alexandre Coninx, Loic Cressot, Stéphane Doncieux 외

Robots could learn their own state and world representation from perception and experience without supervision. This desirable goal is the main focus of our field of interest, state representation learning (SRL). Indeed,…

Imitation LearningReinforcement LearningReinforcement Learning (RL)Representation Learning

TaskNPoint: How to Teach Your Humanoid to Hit a Backhand in Minutes

2026-06-24 · Blake Werner, Ilona Demler, Pietro Perona, Aaron D. Ames arxiv

How do we learn to hit a tennis backhand? Not from a thousand hours of tennis tournaments on TV - we work with a coach and practice. We argue this is also the right recipe for teaching dynamic skills to humanoid robots. …