[论文解读] Chasing Ghosts: A Simulation-to-Real Olfactory Navigation Stack with Optional Vision Augmentation

Kordel K. France, Ovidiu Daescu+2 more|arXiv (Cornell University)|Feb 23, 2026

Insect Pheromone Research and Control被引用 0

一句话总结

本论文提出一个开源无人机系统，利用最少的嗅觉传感器实现对气味源的定位，可选的视觉模块在仿真训练后部署在真实四旋翼上。

ABSTRACT

Autonomous odor source localization remains a challenging problem for aerial robots due to turbulent airflow, sparse and delayed sensory signals, and strict payload and compute constraints. While prior unmanned aerial vehicle (UAV)-based olfaction systems have demonstrated gas distribution mapping or reactive plume tracing, they rely on predefined coverage patterns, external infrastructure, or extensive sensing and coordination. In this work, we present a complete, open-source UAV system for online odor source localization using a minimal sensor suite. The system integrates custom olfaction hardware, onboard sensing, and a learning-based navigation policy trained in simulation and deployed on a real quadrotor. Through our minimal framework, the UAV is able to navigate directly toward an odor source without constructing an explicit gas distribution map or relying on external positioning systems. Vision is incorporated as an optional complementary modality to accelerate navigation under certain conditions. We validate the proposed system through real-world flight experiments in a large indoor environment using an ethanol source, demonstrating consistent source-finding behavior under realistic airflow conditions. The primary contribution of this work is a reproducible system and methodological framework for UAV-based olfactory navigation and source finding under minimal sensing assumptions. We elaborate on our hardware design and open source our UAV firmware, simulation code, olfaction-vision dataset, and circuit board to the community. Code, data, and designs will be made available at https://github.com/KordelFranceTech/ChasingGhosts.

研究动机与目标

• 在不进行显式气体分布映射或外部定位的前提下，证明在轻量级无人机上实现在线气味源定位。
• 开发一个适用于嗅觉传感模式的最小传感器导航框架。
• 通过在仿真中训练导航策略并部署到硬件上，实现仿真到现实的转移。
• 在特定条件下引入可选的视觉模态以加速气味引导导航。
• 提供可重复的硬件、软件与数据集，促进未来嗅觉机器人研究。

提出的方法

• 在改装的 DJI Tello 平台上整合自定义嗅觉硬件（MOX 和电化学传感器）与红外感知。
• 在仿真中训练导航策略（基于 Gymnasium 的羽流环境和卡尔曼滤波控制）并以最小传感器组在硬件上部署。
• 使用双时延尺度的气味处理（短期/长期 EMA 差）来检测羽流并计算羽流角度以进行偏航控制。
• 开发 COLIP（对比嗅觉-视觉预训练），结合基于 CLIP 的视觉编码器与一个 12 层嗅觉编码器，通过 InfoNCE 损失对齐嗅觉与视觉嵌入。
• 实现一个两部件视觉系统：慢速的高层 OVM 和快速的 YOLOv11 基于反应模块，以在泛化和边缘速度推理之间取得平衡。
• 将羽流定向决策转化为离散动作集合（向前推进、铰向方向、暂停、着陆），通过嗅觉惯性测距与羽流动力学实现。

Figure 1: The UAV equipped with the olfactory processing unit (OPU) and sensor harnesses for scent-based navigation. The metal-oxide sensor configuration is shown in panel A with the electrochemical sensor configuration shown in panel B.

实验结果

研究问题

• RQ1 无人机是否能仅使用最小嗅觉传感器而没有事先气体分布地图或外部定位辅助，在线定位气味源？
• RQ2 可选的视觉增强是否提高气味源定位的性能和速度，以及它如何与嗅觉驱动控制相互作用？
• RQ3 在真实气流条件下，仿真到现实的传输对于真实 UAV 的嗅觉导航策略有多好？
• RQ4 所提议的最小传感框架是否可跨不同传感介质（MOX vs 电化学）和环境进行泛化？

主要发现

Method	Sensor Type	Nav. Algorithm	Average Time μ_t (s)	Sigma Time σ_t (s)	Best Time β_t (s)
Olfaction	MOX	OIO	98.38	14.84	71.59
Olfaction	EC	OIO	112.22	16.70	97.65
Olfaction	MOX	E.SARSA(λ)	103.99	14.89	82.73
Olfaction	EC	E.SARSA(λ)	121.85	16.77	97.10
Olfaction + Vision	MOX	OIO	94.03	14.68	66.12
Olfaction + Vision	EC	OIO	107.71	17.07	80.50

• 仅嗅觉导航在使用 MOX 和 EC 传感器的多次试验中均能成功定位气味源。
• 与仅嗅觉导航相比，增加视觉模块在不同传感器类型下一致地缩短导航时间。
• 视觉增强带来性能提升，与仅嗅觉基线相比，任务平均完成时间更短。
• 在真实 UAV 上对一个 200 平方米的航段实现了仿真到现实的部署，实时处理嗅觉数据。
• 该方法可跨传感介质泛化，并通过开源的硬件、软件与数据集展示了可重复性。

Figure 2: The UAV equipped with the olfactory processing unit (OPU) and sensor harnesses. The figure shows a top-down view of the aircraft: (1) the 2 ballast points needed to balance the aircraft; (2) the battery to power the motherboard required for the olfactory sensors; (3) the wire harnessing le