Monday, June 24, 3:30 pm
The Mathematics of Human Robot Interaction
For years, the focus of robot motion planning has been to produce functional motion: industrial robots move to weld parts, vacuuming robots move to suck dust, and personal robots move to clean up a dirty table. We have been exploring the thesis that although functional motion is ideal when robots perform tasks in isolation, it is insufficient for collaboration, where a human and a robot are manipulating in a tightly-coupled shared workspace. Our goal is to make this collaboration fluent and seamless. To this end, we have been developing algorithms where the notion of an observer watching the motion is woven into the fabric of the motion planner. This perspective has allowed us to formalize qualitative notions such as predictability and legibility in psychology in terms of Bayesian inference and inverse optimal control, and to develop generative models for such motion using functional gradient optimization. I will also describe some of our user studies on applying these algorithms to human-robot handovers, assistive teleoperation, and shared workspace collaboration, and ongoing work on deception, ambiguity, and emotive motion.
Siddhartha Srinivasa is an Associate Professor at the Robotics Institute at Carnegie Mellon University. His research focuses on manipulation, with the goal of enabling robots to robustly and gracefully interact with the world to perform complex manipulation tasks in uncertain, unstructured, and cluttered environments. His current research focuses on physics-based nonprehensile manipulation for reconfiguring clutter, functional gradient methods for motion planning, and formalizing HRI principles using machine learning, motion planning and optimization algorithms. Sidd is a recipient of the HRI Best Paper Award (2010), ONR Young Investigator Award (2012), Okawa Research Award (2012), and a best-paper finalist at RSS (2012, 2013), IEEE ICRA (2009, 2010, 2012), IEEE IROS (2010), and RO-MAN (2012). Sidd also captains the CMU squash team, and dreams of running ultra-marathons.
Monday, June 24, 4:30 pm
High-Level Verifiable Robotics
Why don’t we have robots fetching us coffee and finding our keys for us? While robots have become more capable and powerful, they are not yet integrated into everyday life. Part of the reason for this is that robots are difficult to program and even more difficult to verify. Therefore, to achieve the dream of a robot in every home, two key challenges must be addressed; people should be able to easily interact with robots, and robots must always do as they are told.
In this talk I will discuss the work done in my group to address these challenges. Specifically, I will describe the use of language and temporal logic to capture high-level task specifications and the development of formal methods that take the task specifications and produce correct robot behavior, if such behavior exists.
Hadas Kress-Gazit is an Assistant Professor at the Sibley School of Mechanical and Aerospace Engineering at Cornell University. She received her Ph.D. in Electrical and Systems Engineering from the University of Pennsylvania in 2008 and has been at Cornell since 2009. Her research focuses on formal methods for robotics and automation and more specifically on creating verifiable robot controllers for complex high-level tasks using logic, verification, synthesis, hybrid systems theory and computational linguistics. She received an NSF CAREER award in 2010 and a DARPA Young Faculty Award in 2012.