Research Fellow, Intervention
6 days left
- Full Time
Your daily schedule will include frequent interactions with members of a multi-disciplinary team.
- You are comfortable working at sea trials and pool tests, instead of a normal cubicle in office.
- You build safe and scalable robotic systems with clean and documented code.
The scope for this position is in intervention (or underwater manipulation) development for a Hover Capable Autonomous Underwater Vehicle in SS3 - SS4 swell conditions and currents of up to 4 knots for stability in offshore conditions. In the most basic level you will be developing the AUV manoevres required for 1-3 Degree of Freedom non-destructive testing coupled with multiple linear actuators and mechanisms and accounting for the necessary forces and force feedback required to ensure the task is completed. In the more advanced case, you will be developing the path tracking of a 5 to 7 Degree of Freedom manipulator for the same task but now on a sloped surface. These tasks are all part of the requirement for a hover capable AUV to conduct Inspect Repair and Maintenance work on offshore structures. You will be required to interface with the other intervention, perception and remote operations groups and testbed the technology at the Technology Centre for Offshore Marine Singapore (TCOMS) ocean basin and in the open waters and fast currents of Singapore.
- Research and implement perception and fusion algorithms utilising camera and sonar.
- Research and implement control strategies for multi DOF robotic manipulators.
- Implement inverse kinematics and path planning algorithms for multiple degree of freedom manipulators.
- Exploration of new methods such as reinforcement learning if necessary to ensure a high level of success rate and repeatability. Atomic actions are not part of the equation, the key is fusing both perception with path planning on a mobile platform.
- Integration of robotics stack with the software architecture.
- Test and debug of robotics algorithms in software in the loop simulation
- PhD in Computer Engineering/ Mechatronics/Mechanical Engineering (Robotics Equivalent)
- Experience with 5 to 7 Degree of Freedom robot manipulator control and strategies
- Experience with perception and fusion algorithms and libraries including OpenCV, Pointcloud library, Tracking filters, Computer vision techniques
- Experience with AI, deep learning and machine learning algorithms such as YOLO and Faster RCNN
- Experience with path planning algorithms with obstacle collision avoidance such as A*STAR, PRMs etc.
- Familiarity with inverse kinematics.
- Experience with reinforcement learning is a bonus.
- Proficient in Python and C++
- Proficient in Linux
Location: Kent Ridge Campus
Department : Mechanical Engineering
Employee Referral Eligible: No
Job requisition ID : 6919