•   When: Friday, February 24, 2017 from 02:00 PM to 03:00 PM
  •   Speakers: Jory Denny, Assistant Professor, Department of Mathematics and Computer Science, University of Richmond
  •   Location: Nguyen Engineering Room 4201
  •   Export to iCal

Abstract:

Motion is an essential component to robotics. Despite its importance, planning motions for general robots is computationally difficult. State-of-the-art approaches trade completeness for probabilistic completeness and improved efficiency. However, the probability of their success is directly related to the expansiveness, or openness, of the underlying planning space. In other words, narrow passages, complex systems, and various constraints are still difficult for these methods. On the other hand, humans can often determine approximate solutions for these problems quickly. In this work, we explore human (user)-guided planning approaches. First, we create and analyze simple models of common user-guided and heuristic-guided motion planning methods. Our models encompass three common forms of user input: configuration-based, region-based, and path-based input. From this study, we gain insight into user-guided planning and propose a novel region-based collaboration framework that allows a user to define regions in the workspace to bias and/or restrict the search of a sampling-based motion planner. Finally, we extend region steering to both non-holonomic robotic systems and a human-inspired approach to motion planning. Our results indicate that our framework can aid many variants of sampling-based planning, reduce computation time, support solution customization, and can be used to develop advanced heuristic methods for solving motion planning problems.

About the Speaker: 
Jory Denny is am Assistant Professor of Computer Science in the Department of Mathematics and Computer Science at the University of Richmond. He received his PhD in 2016 and B.S. in 2011 in Computer Science from Texas A&M University. During his graduate studies, he was the recipient of an NSF Graduate Research Fellowship (2013-2016) and was a finalist for the 2011 CRA Outstanding Undergraduate Research Award. During his graduate studies, he mentored high school student, Kensen Shi, who was the national winner of the 2012 Siemens Foundation Research Competition that included a $100K college scholarship. Jory has also earned multiple awards during his graduate studies including excellence in Graduate Leadership (both in 2014 and in 2015), Teaching Assistantship (2014), Mentoring (2013), and Undergraduate Research (2011). His research interests include robotics, computational geometry, artificial intelligence and machine learning, and computer graphics.

Posted 9 months, 3 weeks ago