Title:

Choreographic Abstractions for Embodied Design of Heterogeneous Robotic Behavior

Abstract:

How do you get a robot to do the disco? Or perform a cheerleading routine? These acts require a quantitative understanding of two distinct movement behaviors and pose new problems for the high-level control of robots. The ability to easily create and control movement programs tailored to a specific task or context by untrained operators is key to bringing robots out of specialized roles for high volume manufacturing processes and into more rapidly changing scenarios,working alongside human operators. Thus, abstractions for robotic control need to align with the embodied experience of human movement. This talk will discuss the use of Laban/Bartenieff Movement Studies (LBMS), a framework and taxonomy for movement, as a formal, embodied inroad to this experience and to facilitate the production of diverse robotic behaviors. In this talk, a `behavior' will be defined by a set of movement primitives that are scaled and sequenced differently in different instances. Methods for scaling and sequencing of movement primitives using optimal control and linear temporal logic (LTL) and for extracting primitives automatically from human movement using inverse optimal control will be discussed. These methods will be applied to real robotic platforms and presented in a context that motivates the fundamental value of high-level abstractions that allow for embodied design of a wide array of robotic behavior.

Bio:

Amy LaViers is an Assistant Professor in Mechanical Science and Engineering at the University of Illinois at Urbana-Champaign and director of the Robotics,Automation, and Dance (RAD) Lab where she develops robotic algorithms inspired by movement and dance theory. As a faculty member she has worked in the area of advanced manufacturing through an industry-university consortium, the Commonwealth Center for Advanced Manufacturing (CCAM), and forged interdisciplinary ties with the UVA Dance Program and the Laban/Bartenieff Institute for Movement Studies, where she is pursuing a Certification in Movement Analysis (CMA). Prior to UIUC she held a position as an Assistant Professor for two years in Systems and Information Engineering at the University of Virginia. She completed her Ph.D. in Electrical and Computer Engineering at Georgia Tech where she was the recipient of the ECE Graduate Teaching Excellence Award and a finalist for the CETL/BP Outstanding Graduate Teaching Award. Her dissertation included a live performance exploring the concepts of style she developed there. Her research began at Princeton University where she earned a certificate in Dance and a degree in Mechanical and Aerospace Engineering. Her senior thesis, which quantitatively compared two styles of dance, earned top honors in the MAE department, the School of Engineering and Applied Science, and the Lewis Center for the Arts.