Learning to Terminate in Object Navigation

Yuhang Song, Anh Nguyen, Chun-Yi Lee
Proceedings of the 15th Asian Conference on Machine Learning, PMLR 222:1247-1262, 2024.

Abstract

This paper tackles the critical challenge of object navigation in autonomous navigation systems, particularly focusing on the problem of target approach and episode termination in environments with long optimal episode length in Deep Reinforcement Learning (DRL) based methods. While effective in environment exploration and object localization, conventional DRL methods often struggle with optimal path planning and termination recognition due to a lack of depth information. To overcome these limitations, we propose a novel approach, namely the Depth-Inference Termination Agent (DITA), which incorporates a supervised model called the Judge Model to implicitly infer object-wise depth and decide termination jointly with reinforcement learning. We train our judge model along with reinforcement learning in parallel and supervise the former efficiently by reward signal. Our evaluation shows the method is demonstrating superior performance, we achieve a 9.3% gain on success rate than our baseline method across all room types and gain 51.2% improvements on long episodes environment while maintaining slightly better Success Weighted by Path Length (SPL). Code and resources, visualization are available at: \url{https://github.com/HuskyKingdom/DITA_acml2023}

Cite this Paper

BibTeX
@InProceedings{pmlr-v222-song24a, title = {Learning to Terminate in Object Navigation}, author = {Song, Yuhang and Nguyen, Anh and Lee, Chun-Yi}, booktitle = {Proceedings of the 15th Asian Conference on Machine Learning}, pages = {1247--1262}, year = {2024}, editor = {Yanıkoğlu, Berrin and Buntine, Wray}, volume = {222}, series = {Proceedings of Machine Learning Research}, month = {11--14 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v222/song24a/song24a.pdf}, url = {https://proceedings.mlr.press/v222/song24a.html}, abstract = {This paper tackles the critical challenge of object navigation in autonomous navigation systems, particularly focusing on the problem of target approach and episode termination in environments with long optimal episode length in Deep Reinforcement Learning (DRL) based methods. While effective in environment exploration and object localization, conventional DRL methods often struggle with optimal path planning and termination recognition due to a lack of depth information. To overcome these limitations, we propose a novel approach, namely the Depth-Inference Termination Agent (DITA), which incorporates a supervised model called the Judge Model to implicitly infer object-wise depth and decide termination jointly with reinforcement learning. We train our judge model along with reinforcement learning in parallel and supervise the former efficiently by reward signal. Our evaluation shows the method is demonstrating superior performance, we achieve a 9.3% gain on success rate than our baseline method across all room types and gain 51.2% improvements on long episodes environment while maintaining slightly better Success Weighted by Path Length (SPL). Code and resources, visualization are available at: \url{https://github.com/HuskyKingdom/DITA_acml2023}} }
Endnote
%0 Conference Paper %T Learning to Terminate in Object Navigation %A Yuhang Song %A Anh Nguyen %A Chun-Yi Lee %B Proceedings of the 15th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Berrin Yanıkoğlu %E Wray Buntine %F pmlr-v222-song24a %I PMLR %P 1247--1262 %U https://proceedings.mlr.press/v222/song24a.html %V 222 %X This paper tackles the critical challenge of object navigation in autonomous navigation systems, particularly focusing on the problem of target approach and episode termination in environments with long optimal episode length in Deep Reinforcement Learning (DRL) based methods. While effective in environment exploration and object localization, conventional DRL methods often struggle with optimal path planning and termination recognition due to a lack of depth information. To overcome these limitations, we propose a novel approach, namely the Depth-Inference Termination Agent (DITA), which incorporates a supervised model called the Judge Model to implicitly infer object-wise depth and decide termination jointly with reinforcement learning. We train our judge model along with reinforcement learning in parallel and supervise the former efficiently by reward signal. Our evaluation shows the method is demonstrating superior performance, we achieve a 9.3% gain on success rate than our baseline method across all room types and gain 51.2% improvements on long episodes environment while maintaining slightly better Success Weighted by Path Length (SPL). Code and resources, visualization are available at: \url{https://github.com/HuskyKingdom/DITA_acml2023}
APA
Song, Y., Nguyen, A. & Lee, C.. (2024). Learning to Terminate in Object Navigation. Proceedings of the 15th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 222:1247-1262 Available from https://proceedings.mlr.press/v222/song24a.html.

Related Material