Planning Paths Through Unknown Space by Imagining What Lies Therein

Yutao Han, Jacopo Banfi, Mark Campbell
Proceedings of the 2020 Conference on Robot Learning, PMLR 155:905-914, 2021.

Abstract

This paper presents a novel framework for planning paths in maps containing unknown spaces, such as from occlusions. Our approach takes as input a semantically-annotated point cloud, and leverages an image inpainting neural network to generate a reasonable model of unknown space as free or occupied. Our validation campaign shows that it is possible to greatly increase the performance of standard pathfinding algorithms which adopt the general optimistic assumption of treating unknown space as free.

Cite this Paper

BibTeX
@InProceedings{pmlr-v155-han21a, title = {Planning Paths Through Unknown Space by Imagining What Lies Therein}, author = {Han, Yutao and Banfi, Jacopo and Campbell, Mark}, booktitle = {Proceedings of the 2020 Conference on Robot Learning}, pages = {905--914}, year = {2021}, editor = {Kober, Jens and Ramos, Fabio and Tomlin, Claire}, volume = {155}, series = {Proceedings of Machine Learning Research}, month = {16--18 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v155/han21a/han21a.pdf}, url = {https://proceedings.mlr.press/v155/han21a.html}, abstract = {This paper presents a novel framework for planning paths in maps containing unknown spaces, such as from occlusions. Our approach takes as input a semantically-annotated point cloud, and leverages an image inpainting neural network to generate a reasonable model of unknown space as free or occupied. Our validation campaign shows that it is possible to greatly increase the performance of standard pathfinding algorithms which adopt the general optimistic assumption of treating unknown space as free.} }
Endnote
%0 Conference Paper %T Planning Paths Through Unknown Space by Imagining What Lies Therein %A Yutao Han %A Jacopo Banfi %A Mark Campbell %B Proceedings of the 2020 Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2021 %E Jens Kober %E Fabio Ramos %E Claire Tomlin %F pmlr-v155-han21a %I PMLR %P 905--914 %U https://proceedings.mlr.press/v155/han21a.html %V 155 %X This paper presents a novel framework for planning paths in maps containing unknown spaces, such as from occlusions. Our approach takes as input a semantically-annotated point cloud, and leverages an image inpainting neural network to generate a reasonable model of unknown space as free or occupied. Our validation campaign shows that it is possible to greatly increase the performance of standard pathfinding algorithms which adopt the general optimistic assumption of treating unknown space as free.
APA
Han, Y., Banfi, J. & Campbell, M.. (2021). Planning Paths Through Unknown Space by Imagining What Lies Therein. Proceedings of the 2020 Conference on Robot Learning, in Proceedings of Machine Learning Research 155:905-914 Available from https://proceedings.mlr.press/v155/han21a.html.

Related Material