Three Talks on Motion Control: Flappy Bird Game, Entertainment Robots, and Legged Robots
Prof. Pranav Audhut Bhounsule, University of Illinois at Chicago
3:30 p.m.–4:30 p.m., April 27, 2021 | Zoom
Flappy bird is a popular smartphone game that involves tapping the screen repeatedly to maneuver a bird through gaps between successive pipes. Each time the bird passes through the gap, the score is incremented by one. It’s a hard game with single-digit scores not uncommon. Furthermore, playing the game extensively does not lead to mastery, much to the frustration of people who have spent countless hours playing the game. Prof. Bhounsule will demonstrate how his team used tools in model-based optimal control to automate the game and subsequently achieve high scores.
Entertainment robots, specifically Disney’s Audio-Animatronics have been choreographed to amuse people at Walt Disney theme parks. Since their debut in the 1960s, these robots have been hand-tuned by artists. A laborious process that takes weeks in order to get a few minutes of choreographed motion. The presence of joint flexibility and low fidelity control of low-pressure hydraulics makes it difficult to apply control theory tools. Prof. Bhounsule will describe how his team used iterative learning control to automate the fine-tuning of the motion and demonstrate the approach on 36 degrees of freedom humanoid robot.
Legged robots, unlike humans, are either energy-effective or agile but not both at the same time. While energy effectiveness provides extended operational time, agility or the ability to change speed/direction is fundamentally important for practical applications. Prof. Bhounsule will describe how tools in optimal and feedback control may be used to exploit the natural dynamics to create energy-efficient, stable gaits. The resulting algorithm is demonstrated on a bipedal robot that walked 40 miles non-stop on a single battery charge using 500 watt-hours of electricity (about 6 cents worth). He will also demonstrate how multiple energy-efficient gaits may be combined using tools in dynamical systems theory and learning to create agile gaits.
A playlist of robot videos from the Bhounsule lab can be accessed here.
Prof. Pranav Bhounsule is an assistant professor in the Department of Mechanical and Industrial Engineering at the University of Illinois at Chicago. He is broadly interested in developing model-based and learning-based control algorithms for manipulators and legged systems.
He received his bachelor’s degree in Mechanical Engineering from the Goa Engineering College, India, followed by a master’s degree in Engineering Mechanics from the Indian Institute of Technology Madras, and a Ph.D. in Mechanical Engineering from Cornell University.
He spent two years as a post-doctoral researcher at Disney Research Pittsburgh. There, he developed automation tools for entertainment humanoids, also called Audio-Animatronics Figures, deployed at Disney theme parks around the world. For his Ph.D., he developed energy-efficient control algorithms for walking robots that lead to a record 40 mile non-stop robot walk on a single battery charge.
His research work has been featured in Engadget, IEEE spectrum, Gizmag, PC world, MSNBC, Wired News, Popular science, 3ders. He has won two best conference paper awards and his research has been supported by the National Science Foundation.
Contact Carly Reynolds for Zoom link.