paper-with-me

홈 › Papers

Scaling Single Human Demonstrations for Imitation Learning using Generative Foundational Models

2026-02-13 · Nick Heppert, Minh Quang Nguyen, Abhinav Valada arxiv

Imitation learning is a popular paradigm to teach robots new tasks, but collecting robot demonstrations through teleoperation or kinesthetic teaching is tedious and time-consuming. In contrast, directly demonstrating a task using our human embodiment is much easier and data is available in abundance, yet transfer to the robot can be non-trivial. In this work, we propose Real2Gen to train a manipulation policy from a single human demonstration. Real2Gen extracts required information from the demonstration and transfers it to a simulation environment, where a programmable expert agent can demonstrate the task arbitrarily many times, generating an unlimited amount of data to train a flow matching policy. We evaluate Real2Gen on human demonstrations from three different real-world tasks and compare it to a recent baseline. Real2Gen shows an average increase in the success rate of 26.6% and better generalization of the trained policy due to the abundance and diversity of training data. We further deploy our purely simulation-trained policy zero-shot in the real world. We make the data, code, and trained models publicly available at real2gen.cs.uni-freiburg.de.

📄 PDF Abstract BibTeX arXiv:2602.12734

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Multi-Camera View Scaling for Data-Efficient Robot Imitation Learning

2026-04-01 · Yichen Xie, Yixiao Wang, Shuqi Zhao, Cheng-En Wu 외 arxiv

The generalization ability of imitation learning policies for robotic manipulation is fundamentally constrained by the diversity of expert demonstrations, while collecting demonstrations across varied environments is cos…

Structured Imitation Learning of Interactive Policies through Inverse Games

2025-11-17 · Max M. Sun, Todd Murphey arxiv

Generative model-based imitation learning methods have recently achieved strong results in learning high-complexity motor skills from human demonstrations. However, imitation learning of interactive policies that coordin…

Generative adversarial imitation learning for robot swarms: Learning from human demonstrations and trained policies

2026-03-03 · Mattes Kraus, Jonas Kuckling arxiv

In imitation learning, robots are supposed to learn from demonstrations of the desired behavior. Most of the work in imitation learning for swarm robotics provides the demonstrations as rollouts of an existing policy. In…

Learning a Thousand Tasks in a Day

2025-11-13 · Kamil Dreczkowski, Pietro Vitiello, Vitalis Vosylius, Edward Johns arxiv

Humans are remarkably efficient at learning tasks from demonstrations, but today's imitation learning methods for robot manipulation often require hundreds or thousands of demonstrations per task. We investigate two fund…

Robot Manipulation

Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance

2024-01-21 · Zheng Fang, Tianhao Chen, Dong Jiang, Zheng Zhang 외

Multiple autonomous underwater vehicles (multi-AUV) can cooperatively accomplish tasks that a single AUV cannot complete. Recently, multi-agent reinforcement learning has been introduced to control of multi-AUV. However,…

Imitation LearningMulti-agent Reinforcement Learning