Kinematic calibration of robot hands through touch during manipulation
Multi-fingered robot hands make possible tasks no gripper can perform, but their precision rests on a geometric model, that is, the exact locations of every joint, which changes with collisions with the environment. Recovering those values is called kinematic calibration, and today it is slow, manual and impractical in production. This project turns the problem around by using the contacts generated during ordinary manipulation, sensed through tactile sensors, to identify the hand's parameters continuously, with no dedicated motions and no external measurement system.
The experimental platform combines a five-finger hand instrumented with tactile sensors, mounted on an industrial arm, and a replica of the setup in simulation.
How to apply
To apply, send a complete application for the NSERC Canada Graduate Scholarship (CGS) Doctoral Program (written in English) to Prof. Philippe Nadeau. The CGS is the primary funding mechanism for PhD students in Canada, and competition for it is fierce. Preparing a full application up front may look like extra work, but it pays off: you'll arrive with a strong first draft of your CGS application well ahead of the deadline, improving your odds of being funded by the time you join the group.
Note: If you are considering applying for a Master's with thesis, the same steps apply but we will be using your application package to apply for the appropriate funding sources.
Required knowledge
- Robot kinematics
- State estimation and parameter identification
- Linear algebra and optimization
- Python.