Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
Robot control is formulated as conditional denoising of action sequences, linking diffusion models to visuomotor learning.
THE RESEARCH ATLAS
π0: A Vision-Language-Action Flow Model for General Robot Control
A pretrained vision-language backbone is combined with flow-based action generation for diverse robot tasks.
Institution and location sources
Location refers to credited institutions or the listed organization, not author citizenship or an exhaustive collaboration list.
Why read this
Compare continuous action generation with discrete action-token prediction.
Citation
@misc{black2024vision,
title = {π0: A Vision-Language-Action Flow Model for General Robot Control},
author = {Kevin Black and Noah Brown and Danny Driess and Adnan Esmail and Michael Equi and Chelsea Finn and Niccolo Fusai and Lachy Groom and Karol Hausman and Brian Ichter and Szymon Jakubczak and Tim Jones and Liyiming Ke and Sergey Levine and Adrian Li-Bell and Mohith Mothukuri and Suraj Nair and Karl Pertsch and Lucy Xiaoyang Shi and James Tanner and Quan Vuong and Anna Walling and Haohuan Wang and Ury Zhilinsky},
year = {2024},
eprint = {2410.24164},
archivePrefix = {arXiv},
primaryClass = {cs.LG},
url = {https://arxiv.org/abs/2410.24164}
}Rights remain with the original authors. Refer to the original source for citations and licensing.
Related research
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
Vision-language models are trained to produce robot actions, exploring transfer from web-scale learning to robotic control.
OpenVLA: An Open-Source Vision-Language-Action Model
An open vision-language-action model and adaptation framework make generalist robot policy research more accessible.