Neuromorphic circuit for temporal odor encoding in turbulent environments

2024-12-28

AI Summary

Real-time odor identification and tracking in turbulent environments remains challenging due to rapid, unpredictable concentration fluctuations. Method: This work proposes a bioinspired spiking neuromorphic electronic nose front-end architecture. It first identifies turbulence-invariant, concentration-agnostic temporal odor features; then, inspired by the mammalian olfactory bulb’s dual-pathway processing, it designs a brain-inspired analog-to-spiking encoding mechanism that maps odor concentration inversely to inter-spike intervals. Leveraging MOx gas sensors and custom analog circuitry, the system performs end-to-end hardware-level feature extraction and spike encoding. Contribution/Results: Under controlled artificial turbulent airflow, the system achieves high-accuracy gas classification and concentration estimation (error <8%) using only a single spike per odor exposure, enabling real-time robotic source localization and navigation. This work establishes a novel paradigm for olfactory perception in dynamic, unstructured environments.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Bio-inspired Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Natural odor environments present turbulent and dynamic conditions, causing chemical signals to fluctuate in space, time, and intensity. While many species have evolved highly adaptive behavioral responses to such variability, the emerging field of neuromorphic olfaction continues to grapple with the challenge of efficiently sampling and identifying odors in real-time. In this work, we investigate Metal-Oxide (MOx) gas sensor recordings of constant airflow-embedded artificial odor plumes. We discover a data feature that is representative of the presented odor stimulus at a certain concentration - irrespective of temporal variations caused by the plume dynamics. Further, we design a neuromorphic electronic nose front-end circuit for extracting and encoding this feature into analog spikes for gas detection and concentration estimation. The design is inspired by the spiking output of parallel neural pathways in the mammalian olfactory bulb. We test the circuit for gas recognition and concentration estimation in artificial environments, where either single gas pulses or pre-recorded odor plumes were deployed in a constant flow of air. For both environments, our results indicate that the gas concentration is encoded in -- and inversely proportional to the time difference of analog spikes emerging out of two parallel pathways, similar to the spiking output of a mammalian olfactory bulb. The resulting neuromorphic nose could enable data-efficient, real-time robotic plume navigation systems, advancing the capabilities of odor source localization in applications such as environmental monitoring and search-and-rescue.

Problem

• Turbulent Environment
• Odor Tracking
• Robot Adaptability

Innovation

• Bionic Electronic Nose
• Turbulent Environment Scent Identification
• Animal Olfactory Mechanism Replication