2023-12-02-karnan23a.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
STERLING: Self-Supervised Terrain Representation Learning from Unconstrained Robot Experience	Poster	VLihM67Wdi6	Terrain awareness, i.e., the ability to identify and distinguish different types of terrain, is a critical ability that robots must have to succeed at autonomous off-road navigation. Current approaches that provide robots with this awareness either rely on labeled data which is expensive to collect, engineered features and cost functions that may not generalize, or expert human demonstrations which may not be available. Towards endowing robots with terrain awareness without these limitations, we introduce Self-supervised TErrain Representation LearnING (STERLING), a novel approach for learning terrain representations that relies solely on easy-to-collect, unconstrained (e.g., non-expert), and unlabelled robot experience, with no additional constraints on data collection. STERLING employs a novel multi-modal self-supervision objective through non-contrastive representation learning to learn relevant terrain representations for terrain-aware navigation. Through physical robot experiments in off-road environments, we evaluate STERLING features on the task of preference-aligned visual navigation and find that STERLING features perform on par with fully-supervised approaches and outperform other state-of-the-art methods with respect to preference alignment. Additionally, we perform a large-scale experiment of autonomously hiking a 3-mile long trail which STERLING completes successfully with only two manual interventions, demonstrating its robustness to real-world off-road conditions.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	karnan23a	0	STERLING: Self-Supervised Terrain Representation Learning from Unconstrained Robot Experience	2393	2413	2393-2413	2393	false	Karnan, Haresh and Yang, Elvin and Farkash, Daniel and Warnell, Garrett and Biswas, Joydeep and Stone, Peter	given family Haresh Karnan given family Elvin Yang given family Daniel Farkash given family Garrett Warnell given family Joydeep Biswas given family Peter Stone	2023-12-02		Proceedings of The 7th Conference on Robot Learning	229	inproceedings	date-parts 2023 12 2	https://proceedings.mlr.press/v229/karnan23a/karnan23a.pdf