2018-10-23-karkus18a.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
Particle Filter Networks with Application to Visual Localization	Particle filtering is a powerful approach to sequential state estimation and finds application in many domains, including robot localization, object tracking, etc. To apply particle filtering in practice, a critical challenge is to construct probabilistic system models, especially for systems with complex dynamics or rich sensory inputs such as camera images. This paper introduces the Particle Filter Network (PFnet), which encodes both a system model and a particle filter algorithm in a single neural network. The PF-net is fully differentiable and trained end-to-end from data. Instead of learning a generic system model, it learns a model optimized for the particle filter algorithm. We apply the PF-net to a visual localization task, in which a robot must localize in a rich 3-D world, using only a schematic 2-D floor map. In simulation experiments, PF-net consistently outperforms alternative learning architectures, as well as a traditional model-based method, under a variety of sensor inputs. Further, PF-net generalizes well to new, unseen environments.	sequential state estimation, particle filtering, deep neural network, end-to-end learning, visual localization	inproceedings	Proceedings of Machine Learning Research	karkus18a	0	Particle Filter Networks with Application to Visual Localization	169	178	169-178	169	false	Karkus, Peter and Hsu, David and Lee, Wee Sun	given family Peter Karkus given family David Hsu given family Wee Sun Lee	2018-10-23		PMLR	Proceedings of The 2nd Conference on Robot Learning	87	inproceedings	date-parts 2018 10 23	http://proceedings.mlr.press/v87/karkus18a/karkus18a.pdf	label link Source code https://github.com/AdaCompNUS/pfnet