Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation

Ronghao Dang, Lu Chen, Liuyi Wang, Zongtao He, Chengju Liu, Qijun Chen
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:6855-6872, 2023.

Abstract

We propose a meta-ability decoupling (MAD) paradigm, which brings together various object navigation methods in an architecture system, allowing them to mutually enhance each other and evolve together. Based on the MAD paradigm, we design a multiple thinking (MT) model that leverages distinct thinking to abstract various meta-abilities. Our method decouples meta-abilities from three aspects: input, encoding, and reward while employing the multiple thinking collaboration (MTC) module to promote mutual cooperation between thinking. MAD introduces a novel qualitative and quantitative interpretability system for object navigation. Through extensive experiments on AI2-Thor and RoboTHOR, we demonstrate that our method outperforms state-of-the-art (SOTA) methods on both typical and zero-shot object navigation tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-dang23a, title = {Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation}, author = {Dang, Ronghao and Chen, Lu and Wang, Liuyi and He, Zongtao and Liu, Chengju and Chen, Qijun}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {6855--6872}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/dang23a/dang23a.pdf}, url = {https://proceedings.mlr.press/v202/dang23a.html}, abstract = {We propose a meta-ability decoupling (MAD) paradigm, which brings together various object navigation methods in an architecture system, allowing them to mutually enhance each other and evolve together. Based on the MAD paradigm, we design a multiple thinking (MT) model that leverages distinct thinking to abstract various meta-abilities. Our method decouples meta-abilities from three aspects: input, encoding, and reward while employing the multiple thinking collaboration (MTC) module to promote mutual cooperation between thinking. MAD introduces a novel qualitative and quantitative interpretability system for object navigation. Through extensive experiments on AI2-Thor and RoboTHOR, we demonstrate that our method outperforms state-of-the-art (SOTA) methods on both typical and zero-shot object navigation tasks.} }
Endnote
%0 Conference Paper %T Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation %A Ronghao Dang %A Lu Chen %A Liuyi Wang %A Zongtao He %A Chengju Liu %A Qijun Chen %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-dang23a %I PMLR %P 6855--6872 %U https://proceedings.mlr.press/v202/dang23a.html %V 202 %X We propose a meta-ability decoupling (MAD) paradigm, which brings together various object navigation methods in an architecture system, allowing them to mutually enhance each other and evolve together. Based on the MAD paradigm, we design a multiple thinking (MT) model that leverages distinct thinking to abstract various meta-abilities. Our method decouples meta-abilities from three aspects: input, encoding, and reward while employing the multiple thinking collaboration (MTC) module to promote mutual cooperation between thinking. MAD introduces a novel qualitative and quantitative interpretability system for object navigation. Through extensive experiments on AI2-Thor and RoboTHOR, we demonstrate that our method outperforms state-of-the-art (SOTA) methods on both typical and zero-shot object navigation tasks.
APA
Dang, R., Chen, L., Wang, L., He, Z., Liu, C. & Chen, Q.. (2023). Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:6855-6872 Available from https://proceedings.mlr.press/v202/dang23a.html.

Related Material