Generalized Robot Dynamics Learning and Gen2Real Transfer
Dengpeng Xing, Yiming Yang, Zechang Wang, Jiale Li, Bo Xu
Abstract
Acquiring dynamics is critical for robot learning and is fundamental to planning and control. This paper concerns two fundamental questions: How can we learn a model that covers massive, diverse robot dynamics? Can we construct a model that lifts the data-collection pain and domain expertise required for building specific robot models? We learn the dynamics involved in a dataset containing a large number of serial articulated robots and propose a new concept, “Gen2Real”, to transfer simulated, generalized models to physical, specific robots. We generate a large-scale dataset by randomizing dynamics parameters, topology configurations, and model dimensions, which, in sequence, correspond to different properties, connections, and numbers of robot links. A structure modified from the generative pre-trained transformer is applied to approximate the dynamics of massive heterogeneous robots. In Gen2Real, we transfer the pre-trained model to a target robot using distillation, for the sake of real-time computation. The results demonstrate the superiority of the proposed method in terms of its accuracy in learning a tremendous amount of robot dynamics and its generality to transfer to different robots.
BibTeX
@inproceedings{iros2023_generalizedrobot,
title = {Generalized Robot Dynamics Learning and Gen2Real Transfer},
author = {Dengpeng Xing and Yiming Yang and Zechang Wang and Jiale Li and Bo Xu},
booktitle = {IROS 2023},
year = {2023}
}