FRC Seminar - Autonomous Peat Moss Harvesting
Carl Wellington
NREC Commercialization Specialist
National Robotics Engineering Center
Carnegie Mellon University
Wednesday, December 12th
Noon
NSH 1109
Pizza will be served
Noon
NSH 1109
Pizza will be served
Abstract
This presentation will describe recent work with John Deere to deploy a team of three autonomous tractors for coordinated peat moss harvesting at a Canadian farm. We provided the perception system that estimates the location of the dumping pile and detects ditches and other obstacles. These systems were deployed for three months of testing and successfully harvested and deposited several fields of peat moss autonomously.
After discussing this application and our long term partnership with John Deere, I will describe our sensor pod and perception system, including a Markov random field ground estimation algorithm used for pile estimation. I'll end with some lessons learned and a discussion of the challenges in making a perception system that was deployed for months of outdoor testing without us present.
Speaker Bio
Carl Wellington is a researcher at the National Robotics Engineering Center of Carnegie Mellon University's Robotics Institute. His current focus is on perception for autonomous ground vehicles and includes project work with John Deere and Darpa's UPI Crusher program. He received his PhD from Carnegie Mellon's Robotics Institute in 2005 and his BS in Engineering from Swarthmore College in 1999.
No comments:
Post a Comment