Invited Speakers
We are pleased to have the following invited speakers at SoCS 2015:
 Stuart Russell |
Talk Title: Effective Desicion Making
Abstract:How can we design systems that can achieve reasonable decision quality over long time scales? One approach is based on temporal abstraction, allowing deliberation over action choices of long duration. The talk will explore this idea in the contexts of classical planning and hierarchical reinforcement learning. Two important open problems will be discussed: the adequacy of standard STRIPS-like languages for defining actions and the possibility of metalevel control over hierarchical deliberation. [Joint work with Ron Parr, David Andre, Bhaskara Marthi, Andy Zimdars, David Latham, Carlos Guestrin, Jason Wolfe, and Nick Hay] About the Speaker:Stuart Russell received his B.A. with first-class honours in physics from Oxford University in 1982 and his Ph.D. in computer science from Stanford in 1986. He then joined the faculty of the University of California at Berkeley, where he is Professor (and formerly Chair) of Electrical Engineering and Computer Sciences and holder of the Smith-Zadeh Chair in Engineering. He is also an Adjunct Professor of Neurological Surgery at UC San Francisco. He is a recipient of the Presidential Young Investigator Award of the National Science Foundation, the IJCAI Computers and Thought Award, the Mitchell Prize of the American Statistical Association and the International Society for Bayesian Analysis, and the ACM Karlstrom Outstanding Educator Award. In 1998, he gave the Forsythe Memorial Lectures at Stanford University and from 2012 to 2014 he held the Chaire Blaise Pascal in Paris. He is a Fellow of the American Association for Artificial Intelligence, the Association for Computing Machinery, and the American Association for the Advancement of Science. He has published over 150 papers on a wide range of topics in artificial intelligence including machine learning, probabilistic reasoning, knowledge representation, planning, real-time decision making, multitarget tracking, computer vision, computational physiology, and global seismic monitoring. His books include "The Use of Knowledge in Analogy and Induction", "Do the Right Thing: Studies in Limited Rationality" (with Eric Wefald), and "Artificial Intelligence: A Modern Approach" (with Peter Norvig). For more details of Prof. Russell, see the wikipedia page about him. Prof. Russell will be the invited speaker in the joint ICAPS-SoCS session on the first day of SoCS/last day of ICAPS. |
 Maxim Likhachev |
Talk Title: Heuristic Search-based Planning in Robotics and its Extension to Learning from Experiences and Demonstrations
Abstract:Abstract: In this talk, I will first give an overview of the research my group does on heuristic search-based planning for various robotic systems ranging from ground to aerial to mobile manipulation. In particular, I will present some of the lessons we learned and what I think are pros and cons of using heuristic searches to control robotic systems. In the second part, I will talk in more details about one particular aspect of planning that my group has recently started to pursue, namely heuristic search with learning from experience and demonstrations. To this end, I'll present Experience Graph developed by my group, some of its extensions and its application to complex mobile manipulation tasks.About the Speaker:Prof. Maxim Likhachev from Carnagie Mellon University (CMU) has written numerous papers on using heuristic search techniques on real robots, including an RSS (the top venue in robotics) best paper award, and is also well known for his influential work on anytime and adaptive search, including well-known algorithms such as Anytime Repairing A* (ARA*), D*, and D*-lite. |
 Nathan Sturtevant |
Talk Title: The Grid-Based Path-Planning Competition (GPPC)
Abstract:Path planning in general is a common task in AI with a rich history. In the last decade significant progress was made on planning on road networks, spurred by the availability of large road maps. With the widespread availability of grid-based path planning problems, there has been similar progress on techniques for grid-based maps, which significant overlap between these areas. This talk will briefly trace milestones in grid-based path planning, talk about similarities between existing approaches, and then present results from the 2014 Grid-Based Path Planning Competition (GPPC). In addition to highlighting recent improvements, we will present future challenges and new directions for those in the field. About the Speaker:Prof. Nathan Sturtevant from Denver University (DU), has written numerous papers on heuristic search and has authored several influential papers on pathfinding in grids and on the use of heuristic search in digital entertainment. Also, he maintains the standard grid-based pathfinding benchmark suite, which has already been used in more than 70 academic papers. Prof. Sturtevant chaired the Grid-Based Path Planning competition (GPPC) for the past 3 years, and in his talk he will survey recent methods in pathfinding in grid and share his experience from the current and past path planning competition. |