Robotics Thesis Defense

  • Remote Access Enabled - Zoom
  • Virtual Presentation
  • Ph.D. Student
  • Robotics Institute
  • Carnegie Mellon University
Thesis Orals

Data-Driven Robotic Grasping in the Wild

Humans can effortlessly grasp a wide variety of objects in diverse environments. On the other hand, robotic grasping has been extremely challenging in practice and is far from matching human dexterity. Despite recent progress in the community, most research is still largely focused on constrained environments like picking individual objects on a table-top setting. This is in stark contrast to the overall ambition of roboticists in building a general-purpose personal robot that can manipulate objects in unstructured environments. In this thesis, we explore important directions in scaling data-driven grasping to the diversity and constraints imposed by the real world.
We first discuss how we can go beyond picking individual objects in isolation to 6-DOF grasping in clutter. Since most existing policies are trained on datasets collected in curated settings (in lab or simulation), they may not cope with the mismatch in data distribution when deployed in the wild. We build and open-source a low-cost mobile manipulator platform to parallelize data collection in challenging environments like homes and show that policies trained on this data generalize to novel objects in unseen homes. Furthermore, we also discuss ideas for scaling robot learning with several robots and transferring policies between different hardware. Yet, we hypothesize that visual perception alone is insufficient for robustness and present a self-supervised tactile-based re-grasping framework to close the loop on grasp execution.
In this talk, we will discuss these contributions and highlight our recent work on generalizing grasping to diverse semantic tasks. We do so by scaling task-oriented grasping datasets with crowdsourcing and learning from semantic information like knowledge graphs. We hope that this work motivates the application of grasping beyond robotic pick-and-place.
Thesis Committee:
Abhinav Gupta (Chair)
Oliver Kroemer
David Held
Dieter Fox (University of Washington)
Sonia Chernova (Georgia Institute of Technology)

Additional Thesis Information

Zoom Participation. See announcement.

For More Information, Please Contact: