Abstract

The Portuguese context has fostered the innovation geared to the blue growth. However, the aquatic environment imposes many restrictions to mobile robots, as their perceptual capacity becomes severely limited. DIIUS aims to strengthen the perception of distributed robotic systems to improve the current procedures for inspection of aquatic structures (constructions and/or vessels). The perception of large working areas from multiples robots raises a number of unresolved inference problems and calls for new interaction patterns between multiple disciplines, both at the conceptual and technical level. To address this important challenge, the DIIUS project seeks to reinforce the current state-of-art in several scientific domains that fit into artificial intelligence, computer vision, and robotics. Through casestudies focused on 3D mapping of aquatic structures (ex., maritime constructions and adduction tunnels), the project investigates new spatiotemporal data association techniques, including the correlation of sensors from heterogeneous robot formations operating in environments with communications constraints.

From a scientific perspective, the DIIUS project focuses on two challenges: the correlation of heterogeneous sensor information and the association of distributed (in space and time) perceptual 3D data. Contributions of the project include the specification of a visibility level strategy formed by a decentralized hierarchical structure based on multiple robots, where each robot has a limited capability of perceiving the environment, and accommodates temporal contributions for refining the global information during the navigation of each robot. Moreover, the project investigates and evaluates several data association techniques during realistic case studies. These techniques aggregate multiple 3D maps, in particular, through the application of machine learning techniques for extracting iterative features and to conduct a robust spatiotemporal correlation between distinct observations.

Currently, it’s clear to the scientific community that the use of distributed systems will be a predominant research line since it provides an unbeaten robustness and complementarity that otherwise would be difficult to reach. DIIUS materializes this growing interest in exploring new forms of distributed robotic perception, proposing areas of research that could be applied potentially to other application domains.