Topological Semantic Graph Memory for Image-Goal Navigation

Nuri Kim, Obin Kwon, Hwiyeon Yoo, Yunho Choi, Jeongho Park, Songhwai Oh
Proceedings of The 6th Conference on Robot Learning, PMLR 205:393-402, 2023.

Abstract

A novel framework is proposed to incrementally collect landmark-based graph memory and use the collected memory for image goal navigation. Given a target image to search, an embodied robot utilizes semantic memory to find the target in an unknown environment. In this paper, we present a topological semantic graph memory (TSGM), which consists of (1) a graph builder that takes the observed RGB-D image to construct a topological semantic graph, (2) a cross graph mixer module that takes the collected nodes to get contextual information, and (3) a memory decoder that takes the contextual memory as an input to find an action to the target. On the task of an image goal navigation, TSGM significantly outperforms competitive baselines by +5.0-9.0% on the success rate and +7.0-23.5% on SPL, which means that the TSGM finds efficient paths. Additionally, we demonstrate our method on a mobile robot in real-world image goal scenarios.

Cite this Paper

BibTeX
@InProceedings{pmlr-v205-kim23a, title = {Topological Semantic Graph Memory for Image-Goal Navigation}, author = {Kim, Nuri and Kwon, Obin and Yoo, Hwiyeon and Choi, Yunho and Park, Jeongho and Oh, Songhwai}, booktitle = {Proceedings of The 6th Conference on Robot Learning}, pages = {393--402}, year = {2023}, editor = {Liu, Karen and Kulic, Dana and Ichnowski, Jeff}, volume = {205}, series = {Proceedings of Machine Learning Research}, month = {14--18 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v205/kim23a/kim23a.pdf}, url = {https://proceedings.mlr.press/v205/kim23a.html}, abstract = {A novel framework is proposed to incrementally collect landmark-based graph memory and use the collected memory for image goal navigation. Given a target image to search, an embodied robot utilizes semantic memory to find the target in an unknown environment. In this paper, we present a topological semantic graph memory (TSGM), which consists of (1) a graph builder that takes the observed RGB-D image to construct a topological semantic graph, (2) a cross graph mixer module that takes the collected nodes to get contextual information, and (3) a memory decoder that takes the contextual memory as an input to find an action to the target. On the task of an image goal navigation, TSGM significantly outperforms competitive baselines by +5.0-9.0% on the success rate and +7.0-23.5% on SPL, which means that the TSGM finds efficient paths. Additionally, we demonstrate our method on a mobile robot in real-world image goal scenarios.} }
Endnote
%0 Conference Paper %T Topological Semantic Graph Memory for Image-Goal Navigation %A Nuri Kim %A Obin Kwon %A Hwiyeon Yoo %A Yunho Choi %A Jeongho Park %A Songhwai Oh %B Proceedings of The 6th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Karen Liu %E Dana Kulic %E Jeff Ichnowski %F pmlr-v205-kim23a %I PMLR %P 393--402 %U https://proceedings.mlr.press/v205/kim23a.html %V 205 %X A novel framework is proposed to incrementally collect landmark-based graph memory and use the collected memory for image goal navigation. Given a target image to search, an embodied robot utilizes semantic memory to find the target in an unknown environment. In this paper, we present a topological semantic graph memory (TSGM), which consists of (1) a graph builder that takes the observed RGB-D image to construct a topological semantic graph, (2) a cross graph mixer module that takes the collected nodes to get contextual information, and (3) a memory decoder that takes the contextual memory as an input to find an action to the target. On the task of an image goal navigation, TSGM significantly outperforms competitive baselines by +5.0-9.0% on the success rate and +7.0-23.5% on SPL, which means that the TSGM finds efficient paths. Additionally, we demonstrate our method on a mobile robot in real-world image goal scenarios.
APA
Kim, N., Kwon, O., Yoo, H., Choi, Y., Park, J. & Oh, S.. (2023). Topological Semantic Graph Memory for Image-Goal Navigation. Proceedings of The 6th Conference on Robot Learning, in Proceedings of Machine Learning Research 205:393-402 Available from https://proceedings.mlr.press/v205/kim23a.html.

Related Material