Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.10360 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918300907208704 |
|---|---|
| author | Wang, Liuyi He, Zongtao Li, Jinlong Xia, Ruihao Hu, Mengxian Yao, Chenpeng Liu, Chengju Tang, Yang Chen, Qijun |
| author_facet | Wang, Liuyi He, Zongtao Li, Jinlong Xia, Ruihao Hu, Mengxian Yao, Chenpeng Liu, Chengju Tang, Yang Chen, Qijun |
| contents | Vision-and-Language Navigation (VLN) requires robots to follow natural language instructions and navigate complex environments without prior maps. While recent vision-language large models demonstrate strong reasoning abilities, they often underperform task-specific panoramic small models in VLN tasks. To address this, we propose CLASH (Collaborative Large-Small Hierarchy), a VLN-CE framework that integrates a reactive small-model planner (RSMP) with a reflective large-model reasoner (RLMR). RSMP adopts a causal-learning-based dual-branch architecture to enhance generalization, while RLMR leverages panoramic visual prompting with chain-of-thought reasoning to support interpretable spatial understanding and navigation. We further introduce an uncertainty-aware collaboration mechanism (UCM) that adaptively fuses decisions from both models. For obstacle avoidance, in simulation, we replace the rule-based controller with a fully learnable point-goal policy, and in real-world deployment, we design a LiDAR-based clustering module for generating navigable waypoints and pair it with an online SLAM-based local controller. CLASH achieves state-of-the-art (SoTA) results (ranking 1-st) on the VLN-CE leaderboard, significantly improving SR and SPL on the test-unseen set over the previous SoTA methods. Real-world experiments demonstrate CLASH's strong robustness, validating its effectiveness in both simulation and deployment scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_10360 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CLASH: Collaborative Large-Small Hierarchical Framework for Continuous Vision-and-Language Navigation Wang, Liuyi He, Zongtao Li, Jinlong Xia, Ruihao Hu, Mengxian Yao, Chenpeng Liu, Chengju Tang, Yang Chen, Qijun Robotics Vision-and-Language Navigation (VLN) requires robots to follow natural language instructions and navigate complex environments without prior maps. While recent vision-language large models demonstrate strong reasoning abilities, they often underperform task-specific panoramic small models in VLN tasks. To address this, we propose CLASH (Collaborative Large-Small Hierarchy), a VLN-CE framework that integrates a reactive small-model planner (RSMP) with a reflective large-model reasoner (RLMR). RSMP adopts a causal-learning-based dual-branch architecture to enhance generalization, while RLMR leverages panoramic visual prompting with chain-of-thought reasoning to support interpretable spatial understanding and navigation. We further introduce an uncertainty-aware collaboration mechanism (UCM) that adaptively fuses decisions from both models. For obstacle avoidance, in simulation, we replace the rule-based controller with a fully learnable point-goal policy, and in real-world deployment, we design a LiDAR-based clustering module for generating navigable waypoints and pair it with an online SLAM-based local controller. CLASH achieves state-of-the-art (SoTA) results (ranking 1-st) on the VLN-CE leaderboard, significantly improving SR and SPL on the test-unseen set over the previous SoTA methods. Real-world experiments demonstrate CLASH's strong robustness, validating its effectiveness in both simulation and deployment scenarios. |
| title | CLASH: Collaborative Large-Small Hierarchical Framework for Continuous Vision-and-Language Navigation |
| topic | Robotics |
| url | https://arxiv.org/abs/2512.10360 |