2018-10-23-mueller18a.md

title	abstract	keywords	layout	series	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	publisher	container-title	volume	genre	issued	pdf	extras
Driving Policy Transfer via Modularity and Abstraction	End-to-end approaches to autonomous driving have high sample complexity and are difficult to scale to realistic urban driving. Simulation can help end-to-end driving systems by providing a cheap, safe, and diverse training environment. Yet training driving policies in simulation brings up the problem of transferring such policies to the real world. We present an approach to transferring driving policies from simulation to reality via modularity and abstraction. Our approach is inspired by classic driving systems and aims to combine the benefits of modular architectures and end-to-end deep learning approaches. The key idea is to encapsulate the driving policy such that it is not directly exposed to raw perceptual input or low-level vehicle dynamics. We evaluate the presented approach in simulated urban environments and in the real world. In particular, we transfer a driving policy trained in simulation to a 1/5-scale robotic truck that is deployed in a variety of conditions, with no finetuning, on two continents.	Autonomous Driving, Transfer Learning, Sim-to-Real	inproceedings	Proceedings of Machine Learning Research	mueller18a	0	Driving Policy Transfer via Modularity and Abstraction	1	15	1-15	1	false	Mueller, Matthias and Dosovitskiy, Alexey and Ghanem, Bernard and Koltun, Vladlen	given family Matthias Mueller given family Alexey Dosovitskiy given family Bernard Ghanem given family Vladlen Koltun	2018-10-23		PMLR	Proceedings of The 2nd Conference on Robot Learning	87	inproceedings	date-parts 2018 10 23	http://proceedings.mlr.press/v87/mueller18a/mueller18a.pdf	label link Supplementary video https://www.youtube.com/watch?v=BrMDJqI6H5U