AE Presents: “Learning from the Field: Physically-based Deep Learning to Advance Robot Vision in Natural Environments"

Event Details
  • Date/Time:
    • Thursday October 3, 2019
      3:00 pm - 4:00 pm
  • Location: Guggenheim 442
  • Phone:
  • URL:
  • Email:
  • Fee(s):
  • Extras:
No contact information submitted.

Summary Sentence: Dr. Katie Skinner will give a talk

Full Summary: No summary paragraph submitted.

Related Files

You're invited to attend the talk


“Learning from the Field: Physically-based Deep Learning to Advance Robot Vision in Natural Environments"


Dr. Katie Skinner

Aerospace Engineering | Postdoctoral Fellow
Georgia Institute of Technology


Thursday, October 3
3 - 4 PM
Guggenheim 442

About the Talk

Field robotics refers to the deployment of robots and autonomous systems in unstructured or dynamic environments across air, land, sea, and space. Robust sensing and perception can enable these systems to perform tasks such as long-term environmental monitoring, mapping of unexplored terrain, and safe operation in remote or hazardous environments. In recent years, deep learning has led to impressive advances in robotic perception. However, state-of-the-art methods still rely on gathering large datasets with hand-annotated labels for network training. For many applications across field robotics, dynamic environmental conditions or operational challenges hinder efforts to collect and manually label large training sets that are representative of all possible environmental conditions a robot might encounter. This limits the performance and generalizability of existing learning-based approaches for robot vision in field applications.

In this talk, I will discuss my work to develop approaches for unsupervised learning to advance perceptual capabilities of robots in underwater environments. The underwater domain presents unique environmental conditions to robotic systems that exacerbate the challenges in perception for field robotics. To address these challenges, I leverage physics-based models and cross-disciplinary knowledge about the physical environment and the data collection process to provide constraints that relax the need for ground truth labels. This leads to a hybrid model-based, data-driven solution. I will also present work that relates this framework to challenges for autonomous vehicles in other domains.

About the Speaker
Katherine Skinner is a Postdoctoral Fellow in Aerospace Engineering at Georgia Tech. She received a Ph.D. from the Robotics Institute at the University of Michigan in 2019. She also holds a B.S.E. in Mechanical and Aerospace Engineering with a Certificate in Applications of Computing from Princeton University and an M.S. in Robotics from the University of Michigan.

Additional Information

In Campus Calendar

College of Engineering

Invited Audience
Faculty/Staff, Postdoc, Public, Graduate students, Undergraduate students
No keywords were submitted.
  • Created By: Kelsey Gulledge
  • Workflow Status: Published
  • Created On: Sep 30, 2019 - 11:43am
  • Last Updated: Sep 30, 2019 - 11:43am