Robotic simulation today remains challenging to scale up due to the human efforts required to create diverse simulation tasks and scenes. Simulation-trained policies also face scalability issues as many sim-to-real methods focus on a single task. To address these challenges, this work proposes GenSim2, a scalable framework that leverages coding multi-modal LLMs for complex and realistic simulation task creation, including long-horizon tasks with articulated objects. To automatically generate demonstration data for these tasks at scale, we propose planning and RL solvers that generalize within object categories. The pipeline can generate data for up to 100 articulated tasks with 200 objects and reduce the required human efforts by over 50%. To utilize such data, we propose a simple yet effective multi-task language-conditioned policy architecture, dubbed proprioceptive point-cloud transformer (PPT), that learns from the generated demonstrations and exhibits strong sim-to-real zero-shot transfer.
Combining the proposed pipeline and the policy architecture, we show a promising usage of GenSim2 that the generated data can be used for zero-shot transfer or co-train with real-world collected data, which significantly enhances the policy performance by 20% compared with training exclusively on limited real data.
@inproceedings{hua2024gensim2,
author = {Pu Hua, Minghuan Liu, Annabella Macaluso, Yunfeng Lin, Weinan Zhang, Huazhe Xu, Lirui Wang},
title = {GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs},
booktitle = {Conference on Robot Learning},
year = {2024}}