This Robotic Drone Can Smell Hazards and Protect You From Blasts!

This robotic drone has a unique sensor system, similar to a moth's smell-tracking mechanism

Detecting odors for robots, for long, has been a difficult goal to achieve. Species of living organisms have individual and unique smell-detecting mechanisms. However, when it comes to robots, something that uses a combination of human engineering and evolutionary engineering that too which works in every possible direction. Exploring this possibility, the researchers at Osaka University, SoftBank Corporation, and Tokyo Institute of Technology applied the technique of particle image velocimetry to develop a robotic drone to address the problem of 3-dimensional odor source localization. The robotic drone can identify odors and track them to their sources in horizontal as well as vertical directions, a technique that can be highly beneficial in search and rescue operations and in preventing industrial accidents. Developing a plume-tracking robot essentially requires the integration of high-end technologies such as deep learning algorithms, high-end platforms, and movement planners, that in turn require neurofuzzy methodology to refine and recall its actions repetitively. The paper was published in IEEE Transactions on Instrumentation and Measurement.

The robot drone has integrated sensors at its frontal and upper surfaces to track the odors so that a 3-dimensional sensing environment is created. This kind of sensor arrangement is unique, similar to the one that exists in smell-tracking mechanism among moths. The researchers could achieve this mechanism through a 3D casting algorithm for the drone to detect chemical plumes. "Research on 3D odor source localization using a drone is still in its developmental stage. In our previous studies, we mounted one or two odor sensors on a drone, which moved widely in height and crosswind directions to find the odor source. We found that this method is very inefficient, and given the short flight time of the drone, it was necessary to significantly improve the 3D odor tracking performance" Shunsuke Shigaki, one of the researchers who carried out the study, told TechXplore." Researchers say their strength lies in using the airflow visualisation technique, one which is commonly employed by laboratories to test air flow in biosafety cabinets and chemical fume hoods. "Focusing on the changes in airflow produced by a drone, we noticed that the drone intakes odor differently depending on the height of the odor source. Therefore, we designed an odor sensor arrangement and an algorithm that can continuously track an odor regardless of what direction it comes from," says Shigaki.

After a trial of visualization and localisation experiments, the researchers could develop an algorithm superior to previous ones with the ability to track plumes even in conditions of changing wind direction. And further, the researchers are planning to develop a plume tracking robotic system to work in highly erratic, uncertain, and rugged environments to establish itself as a fundamental technology for future odor-detecting drones.