RoboTron-Nav: A Unified Framework for Embodied Navigation Integrating Perception, Planning, and Prediction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912526535491584 |
|---|---|
| author | Zhong, Yufeng Feng, Chengjian Yan, Feng Liu, Fanfan Zheng, Liming Ma, Lin |
| author_facet | Zhong, Yufeng Feng, Chengjian Yan, Feng Liu, Fanfan Zheng, Liming Ma, Lin |
| contents | In language-guided visual navigation, agents locate target objects in unseen environments using natural language instructions. For reliable navigation in unfamiliar scenes, agents should possess strong perception, planning, and prediction capabilities. Additionally, when agents revisit previously explored areas during long-term navigation, they may retain irrelevant and redundant historical perceptions, leading to suboptimal results. In this work, we propose RoboTron-Nav, a unified framework that integrates perception, planning, and prediction capabilities through multitask collaborations on navigation and embodied question answering tasks, thereby enhancing navigation performances. Furthermore, RoboTron-Nav employs an adaptive 3D-aware history sampling strategy to effectively and efficiently utilize historical observations. By leveraging large language model, RoboTron-Nav comprehends diverse commands and complex visual scenes, resulting in appropriate navigation actions. RoboTron-Nav achieves an 81.1% success rate in object goal navigation on the $\mathrm{CHORES}$-$\mathbb{S}$ benchmark, setting a new state-of-the-art performance. Project page: https://yvfengzhong.github.io/RoboTron-Nav |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18525 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RoboTron-Nav: A Unified Framework for Embodied Navigation Integrating Perception, Planning, and Prediction Zhong, Yufeng Feng, Chengjian Yan, Feng Liu, Fanfan Zheng, Liming Ma, Lin Robotics In language-guided visual navigation, agents locate target objects in unseen environments using natural language instructions. For reliable navigation in unfamiliar scenes, agents should possess strong perception, planning, and prediction capabilities. Additionally, when agents revisit previously explored areas during long-term navigation, they may retain irrelevant and redundant historical perceptions, leading to suboptimal results. In this work, we propose RoboTron-Nav, a unified framework that integrates perception, planning, and prediction capabilities through multitask collaborations on navigation and embodied question answering tasks, thereby enhancing navigation performances. Furthermore, RoboTron-Nav employs an adaptive 3D-aware history sampling strategy to effectively and efficiently utilize historical observations. By leveraging large language model, RoboTron-Nav comprehends diverse commands and complex visual scenes, resulting in appropriate navigation actions. RoboTron-Nav achieves an 81.1% success rate in object goal navigation on the $\mathrm{CHORES}$-$\mathbb{S}$ benchmark, setting a new state-of-the-art performance. Project page: https://yvfengzhong.github.io/RoboTron-Nav |
| title | RoboTron-Nav: A Unified Framework for Embodied Navigation Integrating Perception, Planning, and Prediction |
| topic | Robotics |
| url | https://arxiv.org/abs/2503.18525 |