SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Shengjie, You, Jiacheng, Hu, Yihang, Li, Jiongye, Gao, Yang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911032831639552
author Wang, Shengjie
You, Jiacheng
Hu, Yihang
Li, Jiongye
Gao, Yang
author_facet Wang, Shengjie
You, Jiacheng
Hu, Yihang
Li, Jiongye
Gao, Yang
contents Real-world tasks such as garment manipulation and table rearrangement demand robots to perform generalizable, highly precise, and long-horizon actions. Although imitation learning has proven to be an effective approach for teaching robots new skills, large amounts of expert demonstration data are still indispensible for these complex tasks, resulting in high sample complexity and costly data collection. To address this, we propose Semantic Keypoint Imitation Learning (SKIL), a framework which automatically obtains semantic keypoints with the help of vision foundation models, and forms the descriptor of semantic keypoints that enables efficient imitation learning of complex robotic tasks with significantly lower sample complexity. In real-world experiments, SKIL doubles the performance of baseline methods in tasks such as picking a cup or mouse, while demonstrating exceptional robustness to variations in objects, environmental changes, and distractors. For long-horizon tasks like hanging a towel on a rack where previous methods fail completely, SKIL achieves a mean success rate of 70\% with as few as 30 demonstrations. Furthermore, SKIL naturally supports cross-embodiment learning due to its semantic keypoints abstraction. Our experiments demonstrate that even human videos bring considerable improvement to the learning performance. All these results demonstrate the great success of SKIL in achieving data-efficient generalizable robotic learning. Visualizations and code are available at: https://skil-robotics.github.io/SKIL-robotics/.
format Preprint
id arxiv_https___arxiv_org_abs_2501_14400
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulation
Wang, Shengjie
You, Jiacheng
Hu, Yihang
Li, Jiongye
Gao, Yang
Robotics
Artificial Intelligence
Real-world tasks such as garment manipulation and table rearrangement demand robots to perform generalizable, highly precise, and long-horizon actions. Although imitation learning has proven to be an effective approach for teaching robots new skills, large amounts of expert demonstration data are still indispensible for these complex tasks, resulting in high sample complexity and costly data collection. To address this, we propose Semantic Keypoint Imitation Learning (SKIL), a framework which automatically obtains semantic keypoints with the help of vision foundation models, and forms the descriptor of semantic keypoints that enables efficient imitation learning of complex robotic tasks with significantly lower sample complexity. In real-world experiments, SKIL doubles the performance of baseline methods in tasks such as picking a cup or mouse, while demonstrating exceptional robustness to variations in objects, environmental changes, and distractors. For long-horizon tasks like hanging a towel on a rack where previous methods fail completely, SKIL achieves a mean success rate of 70\% with as few as 30 demonstrations. Furthermore, SKIL naturally supports cross-embodiment learning due to its semantic keypoints abstraction. Our experiments demonstrate that even human videos bring considerable improvement to the learning performance. All these results demonstrate the great success of SKIL in achieving data-efficient generalizable robotic learning. Visualizations and code are available at: https://skil-robotics.github.io/SKIL-robotics/.
title SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulation
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2501.14400