COOPERAMOS project proposes to use a team of resident I-AUV’s to demonstrate collaborative assembly of complex structures underwater in an a priori unknown environment. A networking multimodal communication (VLC/RF/acoustics) architecture will be used to guarantee the vehicles coordination. A new MEMS laser scanner will provide 3D point clouds of the objects of interest which will be used by an object recognition architecture to identify and locate them for manipulation and semantic SLAM purposes. Images gathered from different vehicles of the fleet will be used to generate a detailed 3D map of the area of operation and for target localization too. COOPERAMOS will explore new AI techniques, focused on Mission Planning, and Learning Strategies applied to grasping, manipulation and sensing. Potential applications include oceanography (permanent observatories), offshore industry (oil & gas), fisheries, windfarms and nuclear industries.
Moreover, solving this multidisciplinary problem requires the coordination of a large team with different backgrounds and expertise. Therefore, the main added value coordinating COOPERAMOS is the attainment of the devised objectives and milestones themselves, which would be impossible without the engagement of each partner. In addition, quite a few benefits of the coordination may also be pointed out: the synergies and cross-fertilization of ideas among members of the different groups, both seniors and juniors; the training in new fields for most members of the project; the strong interrelation between theoretical development and experimental validation; the visibility of the results that will be exposed from several points of view to different scientific forums; the generation of new technological solutions ready for transfer, to mention but a few.
COOPERAMOS is a joint project with UJI and UIB, being coordinated by UdG. It in cludes 3 subprojects:
[UdG] PER2IAUV subproject focuses on the implementation of the Resident dual-arm I-AUV. To implement this concept it is necessary to design and implement a docking station to host the vehicle at the ocean bottom, providing power and communications with the shoreline. The use of dual arm vehicles is standard underwater since it offers more functionalities. Often one arm is used to hold the robot in a structure while manipulating an object with the other one. A Bi-manual I-AUV will ensure the accuracy, between both end-effectors, required to assemble objects. Moreover, a new MEMS Laser Scanner will be designed and developed. It will be able to project planar laser beams through water regarless the refraction process, achieving fast triangulation in real-time.
The laser scans will be useful for: 1) object recognition and location for manipulation, 2) SLAM and 3) building occupancy grid maps for motion planning. PER2IAUV will develop a cooperative mobile manipulation control architecture merging reactive behaviours of the I-AUV (programmed using the task priority framework) with deliberative motion planning. In both cases, the already existing single-arm I-AUV solutions will be extended to the dual arm system first, and to a cooperative I-AUV setup later on. Finally, new AI techniques for Autonomous Intervention will be researched. First, autonomous decision making (Task Planning) will be tackled using PDDL and ROSplan. Next, based on previous team experience using Reinforcement learning for AUV control, Deep Reinforcement Learning will be applied to the Underwater Manipulation Problem.
