The CADDY project aims at replacing a human buddy diver with a robotic team. Autonomous underwater and surface vehicles improve monitoring, assistance, and safety of the diver’s mission
The FP7 CADDY (Cognitive Autonomous Diving Buddy) project is funded by the European Commission and was started in January 2014[ds_preview]. A group of seven partner institutions (University of Zagreb, Croatia; National Research Council, Italy; Instituto Superior Tecnico, Portugal; University of Newcastle, UK; Jacobs University, Germany; University of Vienna, Austria; Divers Alert Network Europe, Malta) came together in order to pursue collaborative R&D work aimed at enhancing cognitive robotics in the underwater arena; specifically, to develop robots capable of cooperating with divers.
The main motivation for the CADDY project was the fact that divers operate in harsh and poorly monitored environments in which the slightest unexpected disturbance, technical malfunction, or lack of attention can have catastrophic consequences. They manoeuvre in complex 3D environments and carry cumbersome equipment while performing their missions. To overcome these problems, CADDY aims to establish an innovative set-up between a diver and companion autonomous robots (underwater and surface) that exhibit cognitive behaviour through learning, interpreting, and adapting to the diver’s behaviour, physical state, and actions.
The CADDY framework is composed of three components: an autonomous surface vehicle, an autonomous underwater vehicle, and the diver. The autonomous surface vehicle is responsible for communicating with the diver and the underwater robot, as well as serving as a communication relay link to a command centre. It also plays the key role of navigation aid for the underwater agents – it must adapt its motion to optimize communication efficiency and navigational accuracy of underwater agents. The autonomous underwater vehicle, on the other hand, manoeuvres in the vicinity of the diver and exhibits cognitive behaviour with regard to the diver actions by determining the diver’s intentions and the state of the diver’s body.
The CADDY project replaces a human buddy diver with an autonomous underwater vehicle and adds a new autonomous surface vehicle to improve monitoring, assistance, and safety of the diver’s mission. The resulting system plays a threefold role similar to those that a human buddy diver should have: i) the buddy »observer« who continuously monitors the diver; ii) the buddy »slave« who is the diver’s »extended hand« during underwater operations performing tasks such as »do a mosaic of that area«, »take a photo of that« or »illuminate that«; and iii) the buddy »guide« who leads the diver through the underwater environment.
This envisioned threefold functionality will be realized through S&T objectives which must be achieved within three research themes: the »Seeing the Diver« research theme focuses on 3D reconstruction of the diver model (pose estimation and recognition of hand gestures) through remote and local sensing technologies, thus enabling behaviour interpretation; the »Understanding the Diver« theme focuses on adaptive interpretation of the model and physiological measurements of the diver in order to determine the state of the diver; while the »Diver-Robot Cooperation and Control« theme is the link that enables diver interaction with underwater vehicles with rich sensory–motor skills, focusing on cooperative control and formation keeping with the diver as an integral part.
At the current stage of development and with still one year until the end, the CADDY project has collected many successful results: The underwater robot is now able to detect and recognize different hand gestures performed by the diver; single or sequences of gestures are mapped into simple up to more complex actions that the robotic system has to execute to support the specific diver operation. The cooperative guidance executed by surface/underwater vehicles allows to follow or guide the diver in the exploration of the underwater environment. The achievement of such results requires strong efforts by all the partners involved who, during each project meeting and at-field integration & test phases, put their equipment and personnel into play, combined with their knowledge and unevaluable experience.
The complete system integration and final validation trial will take place in October in Biograd Na Moru (Croatia) to demonstrate the feasibility and reliability of this cutting-edge project and sparking new ideas for a project follow-up in the direction of industrial and societal exploitation.
Author: Marco Bibuli, Ph.D.
Robotics, Automation and Control
Engineer, National Research of Italy
CNR – ISSIA
Marco Bibuli
