Part of the Illinois Computer Science Speakers Series.
In this talk I will describe my group’s work in advancing AI for creating autonomous robots for harsh, uncertain, and dynamic environments. Increasing the level of autonomy while keeping costs low leads to many key technical barriers facing ubiquitous adoption of field robots. I will present several ways in which my group is advancing AI algorithms and robotic systems to tackle these barriers. A key highlight will be our recent work in agricultural robotics. Specifically, our lightweight, compact, and autonomous field robot TerraSentia, designed for high-throughput under-canopy phenotyping. I will highlight our contributions to autonomous robot navigation, adaptive control, and trait quantification in cluttered agricultural environments with algorithms designed to leverage different sensors on the robot. I will also discuss our work in learning-based planners that learn to coordinate teams of robots to weed large areas under partial observability. These direct applications will help me make the case for the advances in reinforcement learning and adaptive control that are necessary to usher in the next generation of autonomous field robots that operate with little supervision for weeks, months, or longer.
Girish Chowdhary is an assistant professor and Donald Biggar Willet Faculty Fellow at the University of Illinois at Urbana-Champaign. He is the director of the Field Robotics Engineering and Science Hub (FRESH) at UIUC and the Chief Scientist on the Illinois Autonomous Farm. Girish is affiliated with Agricultural and Biological Engineering, Coordinated Science Lab, Computer Science, Electrical Engineering, and Aerospace Engineering at UIUC. He holds a PhD (2010) from Georgia Institute of Technology. He was a postdoc at the Laboratory for Information and Decision Systems (LIDS) of the Massachusetts Institute of Technology (2011-2013), and an assistant professor at Oklahoma State University’s Mechanical and Aerospace Engineering department (2013-2016). He also worked with the German Aerospace Center's (DLR's) Institute of Flight Systems for around three years (2003-2006). Girish’s work on AI and adaptive flight control has led to several key advances to flight-control and his Dave Ward memorial award by the Aerospace Guidance and Controls committee. Some highlights include creation of an autopilot that can handle severe failure cases mid-flight in real-time. Girish is the author of over 90 publications in autonomy and robotics, and PI on NSF, NIFA, AFOSR, ARPA-E, and DOE grants, and an ONR MURI. He is the winner of the Air Force Young Investigator Award, and several best paper awards, including a best systems paper award at RSS 2018 for his recent work on the agricultural robot TerraSentia, which has since been heralded as the device that can usher in a new era in high throughput phenotyping. He is the co-founder of EarthSense Inc. (www.earthsense.co), working towards making sustainable farming profitable with ultralight field robots.
Faculty Host: Kris Hauser