Presented By: Michigan Robotics
Data-Efficient Robotic Manipulation of Deformable One-dimensional Objects with Unreliable Dynamics
PhD Defense, Peter Mitrano
![A yellow quadruped robot with a grasping arm reaches for the end of a vacuum hose to drag it over an obstacle and toward a mess of blocks. A yellow quadruped robot with a grasping arm reaches for the end of a vacuum hose to drag it over an obstacle and toward a mess of blocks.](https://events.umich.edu/media/cache/event_large/media/attachments/2023/11/event_115234_original-1.jpeg)
This dissertation takes a step to increase the abilities of robots to manipulate deformable objects, like ropes and cables. I focus on two problems, our inability to accurately predict in all scenarios how a DOO will move or deform, and the cost of collecting training data in robotic manipulation. I present a system that can quickly learn to manipulation the DOO despite limited data and imperfect predictions, as well as plan grasps and regrasps when the robot gets stuck.
Chair: Dmitry Berenson
Meeting password: rope
Chair: Dmitry Berenson
Meeting password: rope
Explore Similar Events
-
Loading Similar Events...