Smart Chemical Sensing Payload for Emergency Response Uncrewed Autonomous Systems

A novel smart sensor payload for uncrewed autonomous systems and emergency responders with the ability to automatically detect, estimate, and localize chemical sources is presented. The smart-sensing device fuses Bayesian inference machine learning with information-theoretic motion planning for fast estimation and localization performance. More specifically, chemical concentration is measured by a recently developed microelectromechanical-system (MEMS)-based sensor, the location and the size of a chemical leak are estimated using a Bayesian inference machine learning process, and information-theoretic motion planning is used to optimally guide the user or an autonomous mobile robot during the search process to improve the speed and accuracy of localizing and quantifying a leaking gas source. Experiments are performed that compare the device's leak-source estimation and localization performance between two different motion planning methods: (1) moving the device as instructed by the device's information-based guided-motion planner and (2) randomly moving the device for search (baseline approach). By following the device's visual cues on where to take measurements (guided-motion method), on average, the smart chemical sensor locates a source over 170% faster than moving the sensor randomly (unguided motion method). Additionally, it was found that irregardless of the motion methods followed the leak localization error was less than 6.4% (0.325 m). Finally, live methane gas release experiments are performed to further demonstrate real-world application of the smart handheld chemical-sensing device.