Real-time gas recognition and gas unmixing in a robot application

Robot olfaction takes inspiration from animals for locating an object in the environment. This object can be a gas leak to fix or an explosive to neutralise. In these cases, the objects will emit Volatile Organic Compounds (VOCs) which can be measured with an electronic nose. This instrument has the great advantage of being able to detect a broad variety of VOCs, so the same device can then be used for a lot of different applications. In a realistic environment, several VOCs of interest can be present at the same time and mix. This creates difficulties for gas recognition, and in the literature, the problem is often ignored. In this article, we deal both with gas recognition of a large number of VOCs and gas unmixing. For that, we use a recently developed optoelectronic nose which uses peptides as sensing materials and Surface Plasmon Resonance imaging as transduction method. We present two different setups. The first setup studies the recognition of 24 gas sources of 12 VOCs disseminated in the environment. The second setup studies various realistic scenarios in which mixtures occur, due to gas sources being spatially close. We propose a real-time dictionary-based algorithm for dealing both with gas recognition and gas unmixing. We succeed in obtaining a score of 73% for the gas recognition task. For the unmixing issue, we reach at least 72% but we also show that this performance is strongly related to the VOCs used in the dictionary