Research map / Vision-language and multimodal / Robot action and navigation
AMCoNav: Asynchronous Multi-module Collaborative Framework for Embodied Visual Navigation
Jiaquan Yan, Fang Zhao, Yushi Chen, Long wang, Haiyong Luo, Dan Luo
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add global guidance (MSC + ZLMM) to MTU3D (ablation) | MTU3D · HM3D-OVON Val Unseen | SR (%): 40.8 -> 44.2 | Improved |
| add global guidance (MSC + ZLMM) to MTU3D (ablation) | MTU3D · HM3D-OVON Val Seen Synonyms | SR (%): 45.0 -> 53.3 | Improved |
| add BPDFM on top of global guidance (ablation) | AMCoNav · HM3D-OVON Val Unseen | SR (%): 44.2 -> 53.3 | Improved |
| add BPDFM on top of global guidance (ablation) | AMCoNav · HM3D-OVON Val Seen Synonyms | SPL (%): 17.5 -> 20.9 | Improved |
| add BPDFM on top of global guidance (ablation) | AMCoNav · HM3D-OVON Val Seen | SPL (%): 15.8 -> 15.6 | No clear effect |
| use AMCoNav vs MTU3D (dual verification) | AMCoNav · HM3D-OVON Val Seen | SPL (%): 23.6 -> 15.6 | Hurt |
| use AMCoNav vs MTU3D | AMCoNav · SG3D-Nav | SPL (%): 16.5 -> 11.3 | Hurt |
| use AMCoNav vs MTU3D | AMCoNav · GOAT-Bench Val Unseen | SR (%): 47.2 -> 47.2 | No clear effect |
| run large-model TDM asynchronously instead of synchronously (ablation) | AMCoNav · Runtime per episode (100 episodes) | seconds: 174.1 -> 142.5 | Improved |
| set verification step threshold c1 to 500 instead of 300 (ablation) | AMCoNav · HM3D-OVON Val Seen (50 episodes) | SR (%): 60.0 -> 52.0 | Hurt |
| set verification step threshold c1 to 200 instead of 300 (ablation) | AMCoNav · HM3D-OVON Val Seen (50 episodes) | SR (%): 60.0 -> 56.0 | Hurt |
| replace GPT-5 with GPT-4o as ZLMM (ablation) | AMCoNav · HM3D-OVON Val Seen (50 episodes) | SR (%): 60.0 -> 56.0 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- MSGNav — MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation (CVPR 2026) · better on 1 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-and-Language Navigation (CVPR 2026 · similarity 0.88)
- NavBench: Probing Multimodal Large Language Models for Embodied Navigation (NeurIPS 2025 · similarity 0.87)
- PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments (NeurIPS 2025 · similarity 0.87)
- Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation (NeurIPS 2025 · similarity 0.87)
- BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation (NeurIPS 2025 · similarity 0.86)
- Reasoning in Visual Navigation of End-to-end Trained Agents: A Dynamical Systems Approach (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
