Data-driven simulators promise high data-efficiency for driving policy learning. When used for modelling interactions, this data-efficiency becomes a bottleneck: Small underlying datasets often lack interesting and challenging edge cases for learning interactive driving. We address this challenge by proposing a simulation method that uses in-painted ado vehicles for learning robust driving policies. Thus, our approach can be used to learn policies that involve multi-agent interactions and allows for training via state-of-the-art policy learning methods. We evaluate the approach for learning standard interaction scenarios in driving. In extensive experiments, our work demonstrates that the resulting policies can be directly transferred to a full-scale autonomous vehicle without making use of any traditional sim-to-real transfer techniques such as domain randomization.
@article{arxiv.2111.12137,
title = {Learning Interactive Driving Policies via Data-driven Simulation},
author = {Tsun-Hsuan Wang and Alexander Amini and Wilko Schwarting and Igor Gilitschenski and Sertac Karaman and Daniela Rus},
journal= {arXiv preprint arXiv:2111.12137},
year = {2021}
}
Comments
The first two authors contributed equally to this this work. Code is available here: http://vista.csail.mit.edu/