OdorSpaces：3D 环境中的视觉-嗅觉具身导航基准发布（CoRL 2026）
OdorSpaces: Visual-Olfactory Embodied Navigation in 3D Environments
AI 导读
研究者推出 OdorSpaces，一个基于物理仿真的视觉-嗅觉具身导航平台与基准。该平台在 Habitat-Sim 基础上接入 Fire Dynamics Simulator（FDS）模拟 3D 气味传输与扩散，设置隐蔽气体泄漏定位和早期火源定位两类源搜索任务，并提出融合视觉与嗅觉观测的多模态强化学习策略，实验表明其优于多种基线。论文已被 CoRL 2026 接收。
正文 · 原文
Abstract:Olfaction provides critical information about airborne chemical cues, yet it remains largely underexplored in embodied AI, with limited prior machine olfaction work focusing primarily on semantic odor perception. We introduce OdorSpaces, a physics-based simulation platform and benchmark for visual-olfactory embodied navigation. OdorSpaces augments Habitat-Sim with 3D odor transport and dispersion simulated by Fire Dynamics Simulator (FDS), enabling agents to navigate photorealistic indoor environments using both visual and olfactory observations. The benchmark includes two representative source-seeking scenarios: invisible gas-leak localization and early-stage fire localization. We develop an initial multimodal reinforcement learning policy that integrates visual observations and olfactory measurements over time. Experiments show that the policy outperforms a diverse set of baselines, establishing a strong reference for future research on visual-olfactory embodied navigation.
| Comments: | Accepted at the 10th Conference on Robot Learning (CoRL 2026). 20 pages, 4 figures, 6 tables |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.05738 [cs.RO] |
| (or arXiv:2611.05738v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05738 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Changyeon Lee [view email]
[v1]
Tue, 3 Nov 2026 23:21:27 UTC (4,051 KB)
来源：arXiv cs.AI · arxiv.org