Neuromorphic circuit for temporal odor encoding in turbulent environments
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Q-learning with temporal memory to navigate turbulence
We consider the problem of olfactory searches in a turbulent environment. We focus on agents that respond solely to odor stimuli, with no access to spatial perception nor prior information about the odor. We ask whether …
Decision MakingNavigateQ-LearningSequential Decision MakingBifurcation enhances temporal information encoding in the olfactory periphery
Living systems continually respond to signals from the surrounding environment. Survival requires that their responses adapt quickly and robustly to the changes in the environment. One particularly challenging example is…
Neural Circuits for Fast Poisson Compressed Sensing in the Olfactory Bulb
Within a single sniff, the mammalian olfactory system can decode the identity and concentration of odorants wafted on turbulent plumes of air. Yet, it must do so given access only to the noisy, dimensionally-reduced repr…
Rapid online learning and robust recall in a neuromorphic olfactory circuit
We present a neural algorithm for the rapid online learning and identification of odorant samples under noise, based on the architecture of the mammalian olfactory bulb and implemented on the Intel Loihi neuromorphic sys…
Lifelong learningLimitations in odour recognition and generalisation in a neuromorphic olfactory circuit
Neuromorphic computing is one of the few current approaches that have the potential to significantly reduce power consumption in Machine Learning and Artificial Intelligence. Imam & Cleland presented an odour-learning al…