///MSR Thesis Talk – Harjatin Baweja
Loading Events
This event has passed.

MSR Speaking Qualifier

August

5
Mon
Harjatin Singh Baweja MSR Student Robotics Institute,
Carnegie Mellon University
Monday, August 5
12:00 pm
- 1:00 pm
NSH 1305
MSR Thesis Talk – Harjatin Baweja

Title: Leveraging Computer Vision and Reinforcement Learning for contact and non-contact based plant phenotyping.  

 

Abstract: 

Effective plant breeding requires scientists to find correspondences between genetic markers and desirable physical traits (phenotypes) of the genotype. Robotics can aid the acceleration of breeding pipeline by facilitating high throughput plant phenotyping. In this thesis we propose a computer vision pipeline for non-contact based plant phenotyping and a Reinforcement Learning framework to learn visiomotor policies for contact based phenotyping.  Reinforcement learning is known to be sample inefficient, preventing its application to many real-world problems, especially with high dimensional observations like images. Learning auxiliary tasks along with the reinforcement learning objective could be a powerful tool to improve the learning efficiency. We propose a principled online learning algorithm that dynamically combines different auxiliary tasks to speed up training for reinforcement learning.

 

Committee:

George Kantor (advisor, RI)

David Held (RI)

Brian Okorn (PhD, RI)