How do you get a robot to do the disco?Â Or perform a cheerleading routine?Â These acts require a quantitative understanding of two distinct movement behaviors and pose new problems for the high-level control of humanoid robots.Â This talk will discuss the use of movement observation, taxonomy, and expert knowledge, for example, as found in Laban/Bartenieff Movement Studies, an embodied theoretical framework developed by dancers, to facilitate the production of diverse robotic behaviors.Â In this talk, a `behavior’ will be defined by a set of movement primitives that are scaled and sequenced differently in different behaviors.Â Methods toward extracting such primitives automatically from human movement will be discussed as well as methods that allow for different scaling sequencing schemes.Â These methods will be applied to real robotic platforms and presented in a context that motivates the fundamental value of high-level abstractions that produce a wide array of behavior.
Amy LaViers is an Assistant Professor in Systems and Information Engineering at the University of Virginia and director of the Robotics, Automation, and Dance (RAD) Lab where she studies develops algorithms for automation inspired by movement and dance theory.Â She completed her Ph.D. in Electrical and Computer Engineering at Georgia Tech. Her research began at Princeton University where she earned a certificate in Dance and degree in Mechanical and Aerospace Engineering.Â Her senior thesis earned top honors in the MAE department, the School of Engineering and Applied Science, and the Lewis Center for the Arts.Â At Georgia Tech, she was the recipient of the ECE Graduate Teaching Excellence Award and a finalist for the CETL/BP Outstanding Graduate Teaching Award. In her final months at Georgia Tech, she choreographed a contemporary dance show entitled âAutomatonâ that explores the ideas of style and automation outlined in her dissertation.Â She is currently enrolled in the Laban/Bartenieff Institute for Movement Studies’ Certification in Movement Analysis (CMA) program.
Co-sponsored by the Computer Science Program