Marine robotic system of self-organizing, logically linked physical nodes

Project Information
Funding Agency EU FP7
My Role Senior Researcher
Project Website
Duration February 2012 to January 2016
Coordinator Atlas Elektronik GmbH, Germany
Partners NATO Center for Marine Research and Experimentation, Italy
Jacobs University Bremen gGmbH, Germany
Technical University Ilmenau, Germany
University of Girona, Spain
Institut Francais de Recherche pour l'Exploitation de la Mer (ifremer), France
Consiglio Nazionale delle Ricerche (CNR), Italy
IMAR - Instituto do Mar, Azores, Portugal
Instituto Superior Tecnico, Lisbon, Portugal
Atlas Hydrographics GmbH, Germany

My role in the project

As a senior researcher, I was responsible for the co-supervision of contributions from Jacobs University to opto-acoustic simultaneous localization and mapping (SLAM) and stereo camera sensing as well as some coordination with international research partners. My own research contributions focused on robust SLAM methods, mainly implemented with stereo cameras. I was also responsible for producing technical and financial reports to the EC.

Executive Summary

The MORPH project focused on multi-vehicle large-scale underwater 3D mapping surveys. It investigated topics such as multi-vehicle distributed formation control, relative (opto-acoustic) localization, multi-vehicle acoustic networking, and visual simultaneous localization and mapping. The system, consisting of up to five vehicles contributed by different partners, was tested in multiple sea trials in France, Spain, and the Azores.

Video - Azores 2014

Video - St.Feliu 2015

Project Objectives

The MORPH project advances the novel concept of an underwater robotic system composed of a number of spatially separated mobile robot-modules, carrying distinct and yet complementary resources. Instead of being physically coupled, the modules are connected via virtual links that rely on the flow of information among them, i. e. inter-module interactions are allowed by underwater communication networks at distant and close ranges and supported by visual perception at very close range. The MORPH supra-vehicle (MSV) is thus in sharp contrast to classical monolithic vehicles or even cooperative groups of marine vehicles that operate safely away from each other. These lack the capability of mutual support and multi-sensor interaction.Without rigid links, the MSV can reconfigure itself and adapt in response to the shape of the terrain. This capability provides the foundation for efficient methods to map the underwater environment with great accuracy especially in situations that defy existing technology: namely, underwater surveys over rugged terrain and structures with full 3D complexity. This includes walls with a negative slope, where precise localization of a single vehicle is not possible.The possible applications of the MSV cover a wide range of scientific and commercial areas such as monitoring of cold water coral reefs, oil and gas pipeline inspection, or harbor and dam protection. The common characteristic of these areas is the need for operating multiple, complementary instruments at very close range to unstructured underwater terrain while accomplishing proper geo-referencing at the same time.The MORPH concept requires qualitatively new behaviors such as adaptive sensor placement for perception and navigation, as well as environmental modeling in complex environments. On site view planning will lead to a solution well beyond the operational state of the art for underwater cliff surveys and other similar missions. A final demonstration on a vertical cliff, unfeasible automatically with today’s technology, will validate the efficacy of the methods developed.

Related Papers

T. Łuczyński, M. Pfingsthorn and A. Birk. The Pinax-Model for Accurate and Efficient Refraction Correction of Underwater Cameras in Flat-Pane Housings. Ocean Engineering, Vol. 133, pp. 9-22, March 2017. Open Access
J. Kalwa, D. Tietjen, M. Carreiro-Silva, J. Fontes, L. Brignone, N. Gracias, P. Ridao, M. Pfingsthorn, A. Birk, T. Glotzbach, S. Eckstein, M. Caccia, J. Alves, T. Furfaro, J. Ribeiro and A. Pascoal. The European Project MORPH: Distributed UUV Systems for Multimodal, 3D Underwater Surveys. Marine Technology Society Journal, vol.50, no.4, pp. 26-41, July 2016.
M. Pfingsthorn and A. Birk. Generalized Graph SLAM: Solving Local and Global Ambiguities through Multimodal and Hyperedge Constraints. The International Journal of Robotics Research, 35: 601-630, May 2016. Open Access
A. Gomez Chavez, J. Fontes, P. Afonso, M. Pfingsthorn and A. Birk. Automated Species Counting using a Hierarchical Classification Approach with Haar Cascades and Multi-Descriptor Random Forests. IEEE/MTS OCEANS 2016 Shanghai, IEEE Press, April 2016.
M. Pfingsthorn, R. Rathnam, T. Luczynski and A. Birk. Full 3D Navigation Correction using Low Frequency Visual Tracking with a Stereo Camera. IEEE/MTS OCEANS 2016 Shanghai, IEEE Press, April 2016.
A. Gomez Chavez, M. Pfingsthorn, R. Rathnam and A. Birk. Visual Speed Adaptation for Improved Sensor Coverage in a Multi-Vehicle Survey Mission. IEEE/MTS OCEANS 2016 Shanghai, IEEE Press, April 2016.
I. Enchev, M. Pfingsthorn, T. Luczynski, I. Sokolovski, A. Birk and D. Tietjen. Underwater place recognition in noisy stereo data using FAB-MAP with a multimodal vocabulary from 2D texture and 3D surface descriptors. IEEE/MTS OCEANS 2015 Genova, Italy, IEEE Press, May 2015.
M. Pfingsthorn, A. Birk, F. Ferreira, G. Veruggio, M. Caccia and G. Bruzzone. Large-Scale Image Mosaicking using Multimodal Hyperedge Constraints from Multiple Registration Methods within the Generalized Graph SLAM Framework. International Conference on Intelligent Robots and Systems (IROS), IEEE Press, September 2014.
M. Pfingsthorn and A. Birk. Representing and solving local and global ambiguities as multimodal and hyperedge constraints in a generalized graph SLAM framework. International Conference on Robotics and Automation (ICRA), IEEE Press, June 2014. Conference Best Paper Finalist
M. Pfingsthorn. Generalized Simultaneous Localization and Mapping (SLAM) on Graphs with Multimodal Probabilities and Hyperedges. PhD Thesis, Jacobs University Bremen, awarded special distinction, March 2014. Open Access
M. Pfingsthorn and A. Birk. Simultaneous localization and mapping with multimodal probability distributions. The International Journal of Robotics Research, 32: 143-171, February 2013. Open Access
© 2015-2019 Max Pfingsthorn. Made with Hugo, Bootstrap, and FontAwesome.