Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Algorithmic foundations of robotics X : Proceedings of the 10th Workshop on the Algorithmic Foundations of Robotics
Frazzoli E., Lozano-Perez T., Roy N., Rus D., Springer Publishing Company, Incorporated, New York, NY, 2013. 640 pp. Type: Book (978-3-642362-78-1)
Date Reviewed: Oct 18 2013

In June of 2012, MIT hosted the 10th Biannual Workshop on the Algorithmic Foundations of Robotics. The proceedings of that workshop have been compiled into this volume, edited by Emilio Frazzoli, professor of aeronautics and astronautics at MIT; Tomás Lozano-Pérez, MIT School of Engineering Professor in Teaching Excellence; Nicholas Roy, associate professor at MIT; and Daniella Rus, professor and director of the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). Lozano-Pérez has been associate director of the lab and received the 2011 IEEE Robotics Pioneer Award. Roy also works at the MIT laboratory and received the National Science Foundation (NSF) Career Award in 2006. Springer, the publisher of this compendium, lists 63 related publications by Rus. With a group of editors of this caliber, it is no surprise that the chapters in this book are all about cutting-edge algorithmic technologies for robotics motion planning and other related applications.

The workshop was started in 1994 and has continued to be a fundamental source of information for critical research in the robotics community. The current volume brings together expanded papers from the tenth symposium in this series of excellent conferences. Appropriately, Springer published these proceedings in its “Springer Tracts in Advanced Robotics” (STAR) series, which has as its mission to provide the research community with up-to-date information on the very latest technologies in robotics. The book contains 37 chapters (from a total of 74 submissions) written collectively by 94 authors.

Before discussing some of the papers, I’d like to make two interesting points. First, an extensive amount of organization went into the conference and the resulting proceedings. Every chapter is approximately 16 pages long, so as to give equal attention to the research of all participants. In a similar manner, the chapters of the book were not segregated into different sections, but were presented consecutively. Second, the five invited speakers at the conference spoke to the attendees, but their presentations were not intended for the proceedings. As such, their names do not appear in the author list in the table of contents. The 37 chapters span a total of 625 pages. Nine of these chapters concern theoretical matters, 17 more concentrate on experimental algorithmics, and the other 11 chapters present both theoretical and practical results.

Chapter 2 presents the first decision-theoretic planner for navigation among movable objects. While efficient planners exist, they are typically hard to implement. This research overcomes dimensionality issues by integrating ideas from hierarchical reinforcement learning with Monte Carlo methods using a decision tree search, which can be applied to uncertain environments. Chapter 5 considers a thin flexible wire of fixed length that is held on each side by a robotic gripper. The curve that can be traced out by the wire is shown to be a smooth manifold of finite dimension. Chapter 7 is an interesting exploration of ray shooting, which is an important technique used in computer graphics to detect collisions in two or three dimensions. This paper extends the algorithm to general dimensions and applies a number of ray shooting algorithms to robotics applications.

Chapter 8 explores optimal gap navigation for a disc robot. The authors globally optimize navigation for a disc-shaped differential drive robot placed into an unknown simply connected polygonal region. Chapter 36 introduces a new class of algorithms that map streaming global positioning system (GPS) data in real-time. An efficient expectation maximization algorithm trains the filter on new data without the need for ground truth observations. This system was deployed inside a traffic information system and used to map fleets of vehicles in San Francisco and elsewhere. The last chapter introduces a novel method to predict pedestrian trajectories using agent-based velocity space reasoning to improve the human-robot interaction. The motion model for each agent uses statistical inferences from noisy data. Experimentation demonstrated improved accuracy in the predicted trajectories.

The editors have kept up the reputation of the proceedings of these workshops with this compendium of cutting-edge results for those in the robotics community.

Reviewer:  R. Goldberg Review #: CR141650 (1312-1078)
Bookmark and Share
  Featured Reviewer  
 
Robotics (I.2.9 )
 
 
Conference Proceedings (A.0 ... )
 
 
General (F.2.0 )
 
 
General (I.2.0 )
 
 
Artificial Intelligence (I.2 )
 
 
General (A.0 )
 
Would you recommend this review?
yes
no
Other reviews under "Robotics": Date
Movement problems for 2-dimensional linkages
Hopcroft J. (ed), Joseph D., Whitesides S. SIAM Journal on Computing 13(3): 610-629, 1984. Type: Article
Feb 1 1985
Robot motion planning with uncertainty in control and sensing
Latombe J. (ed), Lazanas A., Shekhar S. Artificial Intelligence 52(1): 1-47, 1991. Type: Article
Oct 1 1992
Dictionary of robot technology in four languages: English, German, French, Russian
Bürger E., Korzak G., Elsevier North-Holland, Inc., New York, NY, 1986. Type: Book (9789780444995193)
Mar 1 1988
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy