2023-12-02-kim23b.md

title	section	openreview	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Im2Contact: Vision-Based Contact Localization Without Touch or Force Sensing	Poster	h8halpbqB-	Contacts play a critical role in most manipulation tasks. Robots today mainly use proximal touch/force sensors to sense contacts, but the information they provide must be calibrated and is inherently local, with practical applications relying either on extensive surface coverage or restrictive assumptions to resolve ambiguities. We propose a vision-based extrinsic contact localization task: with only a single RGB-D camera view of a robot workspace, identify when and where an object held by the robot contacts the rest of the environment. We show that careful task-attuned design is critical for a neural network trained in simulation to discover solutions that transfer well to a real robot. Our final approach im2contact demonstrates the promise of versatile general-purpose contact perception from vision alone, performing well for localizing various contact types (point, line, or planar; sticking, sliding, or rolling; single or multiple), and even under occlusions in its camera view. Video results can be found at: https://sites.google.com/view/im2contact/home	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	kim23b	0	Im2Contact: Vision-Based Contact Localization Without Touch or Force Sensing	1533	1546	1533-1546	1533	false	Kim, Leon and Li, Yunshuang and Posa, Michael and Jayaraman, Dinesh	given family Leon Kim given family Yunshuang Li given family Michael Posa given family Dinesh Jayaraman	2023-12-02		Proceedings of The 7th Conference on Robot Learning	229	inproceedings	date-parts 2023 12 2	https://proceedings.mlr.press/v229/kim23b/kim23b.pdf