MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations
This addresses the scalability problem in robot learning for researchers and practitioners by providing an economical alternative to costly human data collection, though it is incremental as it builds on existing imitation learning paradigms.
The authors tackled the high cost of collecting human demonstrations for robot imitation learning by introducing MimicGen, a system that synthesizes over 50K demonstrations from just ~200 human ones, enabling strong performance in tasks like multi-part assembly and coffee preparation.
Imitation learning from a large set of human demonstrations has proved to be an effective paradigm for building capable robot agents. However, the demonstrations can be extremely costly and time-consuming to collect. We introduce MimicGen, a system for automatically synthesizing large-scale, rich datasets from only a small number of human demonstrations by adapting them to new contexts. We use MimicGen to generate over 50K demonstrations across 18 tasks with diverse scene configurations, object instances, and robot arms from just ~200 human demonstrations. We show that robot agents can be effectively trained on this generated dataset by imitation learning to achieve strong performance in long-horizon and high-precision tasks, such as multi-part assembly and coffee preparation, across broad initial state distributions. We further demonstrate that the effectiveness and utility of MimicGen data compare favorably to collecting additional human demonstrations, making it a powerful and economical approach towards scaling up robot learning. Datasets, simulation environments, videos, and more at https://mimicgen.github.io .