2023-12-21

Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation

ABSTRACT

Generative pre-trained models have demonstrated remarkable effectiveness in language and vision domains by learning useful representations. In this paper, we extend the scope of this effectiveness by showing that visual robot manipulation can significantly benefit from large-scale video generative pre-training. We introduce GR-1, a straightforward GPT-style model designed for multi-task languageconditioned visual robot manipulation. GR-1 takes as inputs a language instruction, a sequence of observation images, and a sequence of robot states. It predicts robot actions as well as future images in an end-to-end manner. Thanks to a flexible design, GR-1 can be seamlessly finetuned on robot data after pre-trained on a large-scale video dataset. We perform extensive experiments on the challenging CALVIN benchmark and a real robot. On CALVIN benchmark, our method outperforms state-of-the-art baseline methods and improves the success rate from 88.9% to 94.9%. In the setting of zero-shot unseen scene generalization, GR-1 improves the success rate from 53.3% to 85.4%. In real robot experiments, GR-1 also outperforms baseline methods and shows strong potentials in generalization to unseen scenes and objects. We provide inaugural evidence that a unified GPTstyle transformer, augmented with large-scale video generative pre-training, exhibits remarkable generalization to multi-task visual robot manipulation. Project page: https://GR1-Manipulation.github.io

AUTHORS

Hongtao Wu,Ya Jing,Chilam Cheang,Guangzeng Chen,Jiafeng Xu,Xinghang Li,Minghuan Liu,Hang Li,Tao Kong

Featured Publications

View All
Computer Vision

SeedEdit: Align Image Re-Generation to Image Editing

Yichun Shi, Peng Wang, Weilin Huang

2024-11-11

System Research

ByteCheckpoint: A Unified Checkpointing System for LLM Development

Borui Wan, Mingji Han, Yiyao Sheng, Zhichao Lai, Mofan Zhang, Junda Zhang, Yanghua Peng, Haibin Lin, Xin Liu, Chuan Wu

2024-07-29

Speech&Audio

SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words

Junyi Ao, Yuancheng Wang, Xiaohai Tian, Dekun Chen, Jun Zhang, Lu Lu, Yuxuan Wang, Haizhou Li, Zhizheng Wu

2024-06-19