Underwater Robotics Project

CAE model of the Target, UUV, sensor and turbid environment will be developed to test the concepts on a graphic workstation with kinematic and kinetic effects. Data communication protocols will be elaborated in this work package. 

• Simulator
  - Object models to complicate the environment for pose estimation capabilities
  - Different environments can be simulated based on the turbidity of water
  - Using the simulator as a platform to evaluate the novelties/ concepts of work

• Multi-Mode Control: Incorporating the Physical ROV modules into the multimode system
  - Low-level controls, PID controls
  - Sensor modules: RealSense optical camera, Blueprint M750d sonar, Advance Navigation INS
  - Physical mini-ROV

• Graphical User Interface
  - “dashboard” and “config” UI system
  - include a record feature for a pilot to record the data

The improvement of Close-range Pose-Estimation via Illumination of Objects' Salient Features:

• At close-ranges, optical modalities for UW 3D Perception (adequate visibility + higher resolution) 
  
• Turbid waters cause significant noise with objects' spatial details obscured even after noise removal.
  
• Objects using a powerful illumination source to highlight these features, for easier shape detection & formation by Computer Vision processes.
  
• we thus propose the usage of a laser-illuminator component to enhance close-range  2D and 3D Perception of AUVs:
   -  Illuminator would project a powerful laser light in a scanning motion onto objects on a perpendicular plane for multiple frames; 
  -  Merging images obtained per scan to approximate the shape of the object;
  -  Triangulation principles to construct the ‘Z’ height of an object and 3D position of points; 
  -  Expected better result for 3D approximation of object's shape via Triangulation principle  from  multiple Optical RGB frames of RGB camera.

Robust multi-target tracking would be required. The study on the perception and tracking uses the down-selected sensors from work package 2 to carry out on the developed laboratory-scale water tank.  The perception task will be conducted in two different contexts:

• Close-range object detection and tracking (<10 m)
• Long-range object detection and tracking  (>10 m)

To define and develop the tracking module and integrate it into the existing control & communication framework of Saab UUV. The system is programmed in the Robotic Operating System (ROS).

A proof-of-concept needs to evolve to a fully functional prototype before a product is ready for market. Tests are required to fine-tune system specifications and recognize realistic requirements under natural water resources (e.g., coastal waters) using our robotic platform. Experiments will be carried out in two different water conditions:  swimming pool  (clear water)  and Nanyang Lake (turbid water). Data will be collected and analyzed to test the effectiveness of our detection and tracking algorithms. 

                                  Swimming Pool                                                                                      Nanyang Lake