Flowretrieval: Flow-guided data retrieval for few-shot imitation learning

[Free GPT-4]
[PDF] arxiv.org

SPOT: SE (3) Pose Trajectory Diffusion for Object-Centric Manipulation

CC Hsu, B Wen, J Xu, Y Narang, X Wang, Y Zhu… - arxiv preprint arxiv …, 2024 - arxiv.org
We introduce SPOT, an object-centric imitation learning framework. The key idea is to
capture each task by an object-centric representation, specifically the SE (3) object pose …
保存 引用 被引用次数：1 相关文章 HTML 版
[Free GPT-4]
[PDF] arxiv.org

Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning

J Ren, P Sundaresan, D Sadigh, S Choudhury… - arxiv preprint arxiv …, 2025 - arxiv.org
Teaching robots to autonomously complete everyday tasks remains a challenge. Imitation
Learning (IL) is a powerful approach that imbues robots with skills via demonstrations, but is …
保存 引用 相关文章 HTML 版
[Free GPT-4]
[PDF] arxiv.org

STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning

M Memmel, J Berg, B Chen, A Gupta… - arxiv preprint arxiv …, 2024 - arxiv.org
Robot learning is witnessing a significant increase in the size, diversity, and complexity of
pre-collected datasets, mirroring trends in domains such as natural language processing …
保存 引用 相关文章 所有 3 个版本 HTML 版
[Free GPT-4]
[PDF] arxiv.org

Skills Made to Order: Efficient Acquisition of Robot Cooking Skills Guided by Multiple Forms of Internet Data

M Verghese, C Atkeson - arxiv preprint arxiv:2409.15172, 2024 - arxiv.org
This study explores the utility of various internet data sources to select among a set of
template robot behaviors to perform skills. Learning contact-rich skills involving tool use from …
保存 引用 相关文章 HTML 版