aiqbench analysis
OdorSpaces introduces a novel benchmark integrating visual and olfactory data within Habitat-Sim to solve embodied navigation tasks like gas-leak localization using reinforcement learning. By simulating 3D odor dispersion via Fire Dynamics Simulator, this work addresses a significant gap in machine olfaction research where chemical cues are currently underexplored. The study establishes a foundational reference for future multimodal AI systems that leverage non-visual sensory inputs for environmental awareness and safety.
OdorSpaces: Visual-Olfactory Embodied Navigation in 3D Environments
arXiv:2611.05738v1 Announce Type: cross 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.
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.
Accepted at the 10th Conference on Robot Learning (CoRL 2026). 20 pages, 4 figures, 6 tables
Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2611.05738 [cs.RO]
(or arXiv:2611.05738v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2611.05738 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 243 words