Robust placement planning for robotic manipulation

Grasping an object has been studied extensively; placing it has not. Yet whenever a robot must set a part down among others, on a bench, in a bin or into an assembly, the quality of the result depends on the shape, mass and friction of every object in contact. Choosing a pose that holds is what is called placement planning, and existing methods are either far too slow or limited to simple cases. This project develops algorithms that quickly find placements which stay stable despite real-world disturbance.

The project unlocks several applications: loading machined parts into fixtures, stacking packages, feeding machine tools, assembling kits of parts, and more generally any robotic cell that a small manufacturer has to reconfigure often. Every reconfiguration today costs weeks of engineering, and these algorithms aim to bring that cost down.

You will work on a station built around a Franka Research 3 arm, a six-axis force-torque sensor and a wrist-mounted depth camera, with a GPU workstation and the MuJoCo simulator for large-scale trials.

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.