Abstract
Because of their high maneuverability and fast deployment times, aerial robots have recently gained popularity for automating inspection tasks. In this paper, we address the visual inspection of vessel cargo holds, aiming at safer, cost-efficient and more intensive visual inspections of ships by means of a multirotor-type platform. To this end, the vehicle is equipped with a sensor suite able to supply the surveyor with imagery from relevant areas, while the control software is supporting the operator during flight with enhanced functionalities and reliable autonomy. All this has been accomplished in the context of the supervised autonomy (SA) paradigm, by means of extensive use of behaviour-based high-level control (including obstacle detection and collision prevention), all specifically devised for visual inspection. The full system has been evaluated both in laboratory and in real environments, on-board two different vessels. Results show the vehicle effective for the referred application, in particular due to the inspection-oriented capabilities it has been fitted with.
Highlights
Structural failures are the major cause of maritime accidents
We provide results from experiments performed within a laboratory facility fitted with a motion tracking system and within a wider in-campus facility of around 30 × 18 × 12 m (L × W × H), which permits evaluating the platform within a volume of a size similar to that of a typical cargo hold; and on-board real ships. (At this moment, it is worth noting the difficulties of testing inside real vessels because of the usual unavailability of these ships due to day-to-day operation, what requires looking for alternative testing environments.)
We show, among others, the final, fused pose produced by the Global Extended Kalman Filters (EKF) and the true positions supplied by the motion tracking system if available during the experiment; they are respectively labelled as global pose and ground truth in the different plots
Summary
Structural failures are the major cause of maritime accidents. For these reasons, an important part of the inspection effort focuses on ensuring that the hull surfaces and structures from the different vessel areas are all in good condition. The presence and spread of these defects are indicators of the state of the vessel hull and, as such, an early detection prevents the structure from buckling or fracturing In this regard, since visual inspections are and will be an important source of information for structure condition assessment, it seems necessary to try to reduce the effort and cost related to these activities with the introduction of new technological tools which can complement and make safer the human inspections. Cargo holds and cargo tanks, which can be found in e.g., bulk carriers, container ships, tankers or general cargoes, are vessel areas that are considered by the H2020 ROBINS project (www.robins-project.eu, accessed on 27 August 2021) as representative of the operational scenarios where costs and risks connected to inspection activities are more significant These environments feature wide volumes with significant heights, which typically require costly access means to reach highest points. The rest of the paper is organized as follows: Section 2 overviews the platform requirements and reviews related works; Section 3 overviews the system developed, while Section 4 details the hardware integrated into the robot, and Section 5 describes the platform’s control architecture; Section 6 focuses on the interface with the user, considering either the available platform operation modes and commands, as well as the platform feedback to the operator, all this available through the system ground station; Section 7 reports on experimental results, collected from both laboratory environments and field trials; Section 8 summarizes main conclusions and findings
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
