Toward Autonomous Robotics: From High-Level Tasks to Low-Level Motions Erion Plaku Faculty Candidate Rice University Friday, February 15th, 2008 11:00 am – 12:00 pm Fuller Labs 320 ABSTRACT: A significant challenge confronting autonomous robotics in transportation, exploration, and search-and-rescue missions lies in the area of automatic motion planning. The goal is to be able to specify a task in a high-level language and have the robot automatically plan a sequence of low-level motions that enables the robot to complete the task. While progress has been made in planning paths that avoid collisions, it remains particularly challenging to plan motions that enable robots with nonlinear dynamics to complete high-level tasks. This talk presents a novel framework that automatically plans low-level motions that enable robots with nonlinear dynamics not only reach a final destination while avoiding collisions, but also complete high-level tasks specified using linear temporal logic (LTL). LTL allows for complex specifications, such as sequencing, coverage, and other combinations of intermediate objectives. The framework draws from research in robotics, control theory, logic, and AI to effectively combine high-level discrete planning with low-level motion planning. Extensive experiments on physically-realistic models of cars, differential drives, unicycles, and other second-order systems demonstrate the effectiveness of the framework. This work has also led to new approaches in hybrid-system verification, large-scale distribution, and dimensionality reduction, and the implementation of a publicly-available package, OOPSMP, that can be used for research, teaching, or developing applications in robotics. ________ Erion Plaku is receiving a Ph.D. degree in computer science at Rice University in May 2008. His research focuses on automatic motion planning for high-dimensional robotic systems with nonlinear dynamics, and verification of safety properties for hybrid systems. His research interests encompass robotics, hybrid systems, AI, logic, data mining, and large-scale distributed computing. He received a B.S. degree in computer science and mathematics from the State University of New York, Fredonia, NY, in 2000 and a M.S. degree in computer science from Clarkson University, Potsdam, NY, in 2002. For more information visit http://www.cs.rice.edu/~plakue Host: Michael Gennert Refreshments will be served Maintained by webmaster@cs.wpi.edu Last modified: Feb. 7, 2008

Department of Computer Science - Worcester Polytechnic Institute
100 Institute Road, Worcester, MA 01609-2280
Phone: +1-508-831-5357 - Fax: +1-508-831-5776 - cs@wpi.edu