MARIS: Marine Autonomous Robotics for InterventionS


National Project PRIN (2013-16)

The general goal of the MARIS project is the development of cooperating AUVs for undersea intervention in the offshore industry, in search-and-rescue tasks, and in various flavours of scientific exploration. As a key distinctive feature, MARIS aims at the development of autonomous vehicles capable also of interacting with and in the underwater environment by object manipulation. he specific contribution of UNIPR in MARIS is the investigation of methodologies and techniques for underwater object recognition and for synthesizing and planning appropriate grasps based on object shape and type as well as on task requirements and additional constraints.

Experiments: Albaro, Genova, 2015-2016

The video shows one trial of the experiments performed at the water pool in Albaro, Genova. It shows the Autonomous Underwater Vehicle (AUV) equipped with a 7 d.o.f.'s manipulator, a robot hand and a stereo camera. The robot detects the target object and estimate its pose with the vision, approaches it and finally grasps it. These experiments have been performed through the cooperation with following research units of MARIS project:







New Dataset Acquisition: Portofino, September 6th 2014

A new underwater acquisition session took place near Porfofino on Sept. 6th 2014 with the great logistic support from the Federazione Italiana Attività Subacquee (FIAS) of Parma. The scuba divers brough the underwater stereo vision system designed by RIMLab 10 m depth in order to acquire this new dataset consisting of about half-an-hour sequence of image frame pairs. Such synchronized frames allows the 3D reconstruction of objects and of the (amazing!) underwater environment.









Copyright Notice

RIMLab is the copyright holder of all the images included in the dataset.
If you use this dataset, please cite one of the following papers:

  • F. Oleari, F. Kallasi, D. Lodi Rizzini, J. Aleotti, S. Caselli, An Underwater Stereo Vision System: from Design to Deployment and Dataset Acquisition, Proc.~of the IEEE/MTS OCEANS, Pages 1-6, May 19-21, 2015. DOI http://dx.doi.org/10.1109/OCEANS-Genova.2015.7271529 [DOI] . [bib] [project]
  • F. Kallasi, D. Lodi Rizzini, F. Oleari, J. Aleotti, Computer Vision in Underwater Environments: a Multiscale Graph Segmentation Approach, In Proc.~of the IEEE/MTS OCEANS, Pages 1-6, May 19-21, 2015. DOI 10.1109/OCEANS-Genova.2015.7271531 [DOI] . [bib] [project]
This data set is provided "as is" and without any express or implied warranties, including, without limitation, the implied warranties of merchantability and fitness for a particular purpose.




Dataset Description

[README]


Download

[MARIS_Dataset_set1.tar.xz]
[MARIS_Dataset_set2.tar.xz]
[MARIS_Dataset_set3.tar.xz]










Initial results

In summer 2013, we acquired an initial dataset close in the Lake Garda. The raw dataset in rosbag format is available here. If you use this dataset, please cite one of the following papers:

  • D. Lodi Rizzini, F. Kallasi, F. Oleari, and S. Caselli. Investigation of Vision-based Underwater Object Detection with Multiple Datasets. International Journal of Advanced Robotic Systems (IJARS), 12(77):1-13, may 2015. DOI 10.5772/60526 [DOI] [bib] [project]
  • F. Oleari, F. Kallasi, D. Lodi Rizzini, J. Aleotti, and S. Caselli. Performance Evaluation of a Low-Cost Stereo Vision System for Underwater Object Detection. In Proc. of the World Congr. of the International Federation of Automatic Control (IFAC), pages 3388-3394, Aug. 24-29, 2014. ISSN: 09210296, DOI 10.3182/20140824-6-ZA-1003.01450 [DOI] . [bib] [project]

Example of trivial target object detection in underwater image.


References

D. Lodi Rizzini, F. Kallasi, J. Aleotti, F. Oleari and S. Caselli. Integration of a stereo vision system into an autonomous underwater vehicle for pipe manipulation tasks. Computers & Electrical Engineering, Available online 8 September 2016, ISSN 0045-7906, http://dx.doi.org/10.1016/j.compeleceng.2016.08.023. [DOI] [bib] [project]

G. Casalino, M. Caccia, S. Caselli, C. Melchiorri, G. Antonelli, A. Caiti, G. Indiveri, G. Cannata, E. Simetti, S. Torelli, A. Sperindé, F. Wanderlingh, G. Muscolo, M. Bibuli, G. Bruzzone, E. Zereik, A. Odetti, E. Spirandelli, A. Ranieri, J. Aleotti, D. Lodi Rizzini, F. Oleari, F. Kallasi, G. Palli, U. Scarcia, L. Moriello, E. Cataldi. Underwater Intervention Robotics: An Outline of the Italian National Project MARIS. The Marine Technology Society Journal 50 (4) (2016) 98-107, DOI 10.4031/MTSJ.50.4.7 [DOI] [bib]

F. Oleari, D. Lodi Rizzini, F. Kallasi, J. Aleotti and S. Caselli. Issues in High Performance Vision Systems Design for Underwater Interventions. The 42nd Annual Conference of IEEE Industrial Electronics Society (IECON), pages 1-6, Oct. 24-27, 2016. DOI - [DOI] . [bib] [project]

D. Lodi Rizzini, F. Kallasi, F. Oleari, and S. Caselli. Investigation of Vision-based Underwater Object Detection with Multiple Datasets. International Journal of Advanced Robotic Systems (IJARS), 12(77):1-13, may 2015. DOI 10.5772/60526 [DOI] [bib] [project]

F. Oleari, F. Kallasi, D. Lodi Rizzini, J. Aleotti, S. Caselli, An Underwater Stereo Vision System: from Design to Deployment and Dataset Acquisition, Proc.~of the IEEE/MTS OCEANS, Pages 1-6, May 19-21, 2015. DOI http://dx.doi.org/10.1109/OCEANS-Genova.2015.7271529 [DOI] . [bib] [project]

F. Kallasi, D. Lodi Rizzini, F. Oleari, J. Aleotti, Computer Vision in Underwater Environments: a Multiscale Graph Segmentation Approach, In Proc.~of the IEEE/MTS OCEANS, Pages 1-6, May 19-21, 2015. DOI 10.1109/OCEANS-Genova.2015.7271531 [DOI] . [bib] [project]

F. Oleari, F. Kallasi, D. Lodi Rizzini, J. Aleotti, S. Caselli, Performance Evaluation of a Low-Cost Stereo Vision System for Underwater Object Detection, The 19th World Congress of the International Federation of Automatic Control (IFAC), Cape Town (South Africa), 24-29 Aug. 2014 [DOI] [bib]

F. Kallasi, F. Oleari, M. Bottioni, D. Lodi Rizzini, S. Caselli, Object Detection and Pose Estimation Algorithms for Underwater Manipulation, Advances in Marine Robotics Applications (AMRA), Padova, Jul. 15, 2014. [link] [pdf] [bib] [project]

F. Kallasi, F. Oleari, M. Bottioni, D. Lodi Rizzini, S. Caselli, Bio-Inspired Object Detection and Pose Estimation Algorithms for Underwater Environments, International Advanced Robotics Program (IARP), Workshop-Conference on Bio-inspired Robotics, ENEA-Frascati, Roma (IT), May 14-15, 2014. [link] [bib] [project]