DexROV
Project ID: 635491Finanziato nell'ambito di:
Dexterous ROV: effective dexterous ROV operations in presence of communication latencies.
Dettagli del progetto
Costo totale:
EUR 5 336 006,25Contributo UE:
EUR 4 631 182,50Coordinato in:
BelgiumInvito a presentare proposte:
H2020-BG-2014-2See other projects for this callMeccanismo di finanziamento:
RIA - Research and Innovation actionObiettivo
Underwater operations (e.g. oil industry) are demanding and costly activities for which ROV based setups are often deployed in addition to deep divers – contributing to operations risks and costs cutting.
However the operation of a ROV requires significant off-shore dedicated manpower – such a setup typically requires a crew consisting of: (1) an intendant, (2) an operator, and (3) a navigator. This is a baseline, and extra staffing is often provisioned. Furthermore, customers representatives often wish to be physically present at the off-shore location in order to advise on, or to observe the course of the operations. Associated costs are high.
In order to reduce the burden of operations, DexROV will work out more cost effective and time efficient ROV operations, where manned support is in a large extent delocalized onshore (i.e. from a ROV control center), possibly at a large distance from the actual operations - thus with latencies in the communication. As a main strategy to mitigate them, DexROV will develop a real time simulation environment to accommodate operators’ requests on the onshore side with no delays. The simulated environment will exploit cm accuracy 3D models of the environment built online by the ROV, using data acquired with underwater sensors (3D sonar and vision based). A dedicated cognitive engine will analyse user’s control requests as done in the simulated environment, and will turn them into primitives that the ROV can execute autonomously in the real environment, despite the communication latencies.
Effective user interfaces will be developed for dexterous manipulation, including a double advanced arm and hand force feedback exoskeleton. The ROV will be equipped with a pair of new force sensing capable manipulators and dexterous end-effectors: they will be integrated within a modular skid.
The outcomes of the project will be integrated and evaluated in a series of tests and evaluation campaigns, culminating with a realistic offshore trial.
Deliverables
-
Autonomous navigation primitives
Consists of (1) the software modules wrapped in the ROS middleware containing the main functionalities developed within T4.1 and (2) a compact technical report.
-
Representative test mockup
Representative test mockup development completed, based on use case defined in WP2.Ready for deployment at sea.
-
Early Underwater Localization & Perception Framework
Software (and supporting documentation) related to the first release of the perception framework: focusing on online localization through low-cost methods (T3.1), and early outcomes related to 3D data acquisition and fusion (T3.2).
-
Autonomous arm primitives
Consists of (1) the software modules wrapped in the ROS middleware containing the main functionalities developed within T4.2 and refinement of modules developed within T4.1, and (2) compact technical report.
-
Main control center infrastructures
Dedicated space with consoles, computers, screen walls, communication channels provision.
-
Visual user interface
Main release of the immersive visual interface as detailed in T6.3.
-
Ground truth simulation setup: initial release
Ground truth simulation setup: initial release (relates to T8.3).
-
Protocols for offline training and preparation of a mission
Software and report on the offline training protocol (as worked out in T7.1).
-
Simulation environment main release
Overall simulation framework enabling force feedback and visual feedback through dedicated engines.
-
Ground truth simulation setup: intermediate release
Ground truth simulation setup: intermediary release (relates to T8.3). Updated partners models, and simulation setup minor fixes/improvements if deemed necessary.
-
Intermediary Underwater Localization & Perception Framework
Software (and supporting documentation) related to the second release of the perception framework: will focus on a consolidated system for data acquisition and fusion (T3.2) and early outcomes for 6 DoF registration, 3D mapping and 3D object modeling (T3.3).
-
Report on integration step 1 and 1st evaluation campaign
Reporting on the first integration step and first evaluation campaign.
-
System requirements elicitation and operational concept
Will report on the elicited system requirements and will provide details on the operational concept and operational architecture of the system
-
Interface Control Document
Will contain formal specification of every subsystems interface – both hardware and software (including communication protocols, data formalisms, etc.).
-
Reference DexROV use cases
Will report on the collected user requirements and consolidated reference use cases.
-
Functional and physical architecture
Will contain the specification of the functional architecture and physical architecture of the whole system, with a first iteration on subsystem detailed specification (to be further addressed in detail in WPs addressing respective subsystems).
-
System integration and evaluation plan
Detail of the system integration and evaluation plan (may be subject to revisions/adaptations, as the results of the project are released).
-
Communication and dissemination package for Y3
Dissemination package to be used by the consortium during Y3: : leaflet, posters, project presentation slides, etc
-
Communication and dissemination package for Y2
Dissemination package to be used by the consortium during Y2: : leaflet, posters, project presentation slides, etc
-
Project web site and media channels
Project website release, electronic channels enabled, project identity material: logo, color palette, templates for documents and presentation, etc.
Publications
-
Set-Based Tasks within the Singularity-Robust Multiple Task-Priority Inverse Kinematics Framework: General Formulation, Stability Analysis, and Experimental ResultsAuthor(s): Signe Moe, Gianluca Antonelli, Andrew R. Teel, Kristin Y. Pettersen, Johannes SchrimpfPublished in: Frontiers in Robotics and AI, issue 3, 2016. ISSN: 2296-9144DOI: 10.3389/frobt.2016.00016
-
A tutorial on task-parameterized movement learning and retrievalAuthor(s): Sylvain CalinonPublished in: Intelligent Service Robotics, issue 9/1, 2016. Page(s) 1-29. ISSN: 1861-2776DOI: 10.1007/s11370-015-0187-9
-
Learning Physical Collaborative Robot Behaviors From Human DemonstrationsAuthor(s): Leonel Rozo, Sylvain Calinon, Darwin G. Caldwell, Pablo Jimenez, Carme TorrasPublished in: IEEE Transactions on Robotics, issue 32/3, 2016. Page(s) 513-527. ISSN: 1552-3098DOI: 10.1109/TRO.2016.2540623
-
Whole body control of a dual arm underwater vehicle manipulator systemAuthor(s): E. Simetti, G. CasalinoPublished in: Annual Reviews in Control, issue 40, 2015. Page(s) 191-200. ISSN: 1367-5788DOI: 10.1016/j.arcontrol.2015.09.011
-
Learning Controllers for Reactive and Proactive Behaviors in Human–Robot CollaborationAuthor(s): Leonel Rozo, João Silvério, Sylvain Calinon, Darwin G. CaldwellPublished in: Frontiers in Robotics and AI, issue 3, 2016. ISSN: 2296-9144DOI: 10.3389/frobt.2016.00030
-
DexROV: Dexterous Undersea Inspection and Maintenance in Presence of Communication LatenciesAuthor(s): Jeremi Gancet, Diego Urbina, Pierre Letier, Michel Ilzokvitz, Peter Weiss, Frederic Gauch, Gianluca Antonelli, Giovanni Indiveri, Giuseppe Casalino, Andreas Birk, Max Folkert Pfingsthorn, Sylvain Calinon, Ajay Tanwani, Alessio Turetta, Cees Walen, Lisa GuilpainPublished in: IFAC-PapersOnLine, issue 48/2, 2015. Page(s) 218-223. ISSN: 2405-8963DOI: 10.1016/j.ifacol.2015.06.036
-
Advanced ROV Autonomy for Efficient Remote Control in the DexROV ProjectAuthor(s): Paolo Augusto Di Lillo, Enrico Simetti, Daniela De Palma, Elisabetta Cataldi, Giovanni Indiveri, Gianluca Antonelli, Giuseppe CasalinoPublished in: Marine Technology Society Journal, issue 50/4, 2016. Page(s) 67-80. ISSN: 0025-3324DOI: 10.4031/MTSJ.50.4.8
-
Learning Robot Manipulation Tasks With Task-Parameterized Semitied Hidden Semi-Markov ModelAuthor(s): Ajay Kumar Tanwani, Sylvain CalinonPublished in: IEEE Robotics and Automation Letters, issue 1/1, 2016. Page(s) 235-242. ISSN: 2377-3766DOI: 10.1109/LRA.2016.2517825
-
A Novel Practical Technique to Integrate Inequality Control Objectives and Task Transitions in Priority Based ControlAuthor(s): Enrico Simetti, Giuseppe CasalinoPublished in: Journal of Intelligent & Robotic Systems, 2016. ISSN: 0921-0296DOI: 10.1007/s10846-016-0368-6
Open Access
Open Access
Coordinatore
Contributo UE: EUR 1 438 437,50
Leuvensesteenweg 325
1932 ZAVENTEM
Belgium
Partecipanti
Contributo UE: EUR 787 125
BOULEVARD DES OCEANS 36
13009 MARSEILLE
France
Contributo UE: EUR 636 875
VIA BALBI 5
16126 GENOVA
Italy
Contributo UE: EUR 652 925
CAMPUS RING 1
28759 BREMEN
Germany
Contributo UE: EUR 0
RUE MARCONI 19
1920 MARTIGNY
Switzerland
Contributo UE: EUR 997 500
VIA GROPALLO 4/10
16122 GENOVA
Italy
Contributo UE: EUR 118 320
3E BINNENVESTGRACHT 23 F
2312 LEIDEN
Netherlands
Ultimo aggiornamento: 2017-08-08
Numero di registrazione: 193333
Ultimo aggiornamento 2017-08-08Share this page
