On-plate autonomous exploration for an inspection robot using ultrasonic guided waves
MetadataShow full item record
Autonomous Robotic Exploration is a major research issue in robotics incorporating the aspect of how to make decisions for the next actions to maximize information gain and minimize costs. In this work, we elaborate an active-sensing strategy based on frontier-based exploration to enable the autonomous reconstruction of the geometry of a metal surface by a mobile robot relying on ultrasonic echoes. Such a strategy can be beneficial to the development of a fully autonomous robotic agent for the inspection of large metal structures such as storage tanks and ship hulls. Our exploration strategy relies on the occupancy grid generated by detecting the first echo of the signal referring to the closest edge to the sensor, and it employs a utility function that we define to balance travel cost and information gain using the plate’s geometry estimation. Next, the sensor is directed to the next best location. In simulation, the method developed is evaluated and compared with multiple algorithms, essentially closest and random frontier point selection. Finally, an experiment using a mobile robot equipped with co-localized emitter/receiver pair of transducers is used to validate the viability of the proposed approach.