Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Robotics : Science and Systems VI
Matsuoka Y., Durrant-Whyte H., Neira J., The MIT Press, Cambridge, MA, 2011. 344 pp. Type: Book (978-0-262516-81-5)
Date Reviewed: Aug 2 2012

The collection of 40 papers selected and presented at the 2010 Robotics: Science and Systems Conference appears in this volume, edited by Matsuoka and others. As in any conference proceedings, it is not possible to find a real organization of the papers. I clustered them according to the 12 topics indicated in the call for papers, in order to list the areas and comment on a few representative papers.

The first topic is mechanisms, exploring new robot design and controllers to move on difficult terrains or in the air.

The kinematics, dynamics, and control area contains advanced models of control, and as expected is the one strictly using the methods of automatic control, with the aim to improve the dynamic control of such complex activities as jumping and walking.

Human-robot interaction, a hot topic in robotics, is represented here in only two papers, mostly devoted to the physical interaction. In particular, “A non-invasive real-time method for measuring variable stiffness,” by Grioli and Bicchi, tackles the problem of measuring, instead of estimating, the stiffness of an artificial or natural limb.

Distributed systems is an area of long tradition in robotics. Here, papers about path planning, cooperation, and allocation of robots in a distributed system are presented. Most of the papers are about developing software models and obtaining results in simulation, so it is quite unusual to see the contribution “Study of group food retrieval by ants as a model for multi-robot collective transport strategies,” by Berman and others, that also develops elastic structures to measure the forces that the ants apply in the transportation task.

Mobile systems and mobility is a large and advanced area in robotics, with a strong emphasis on probabilistic methods. It contains, between various simultaneous location and mapping (SLAM) papers, “Probabilistic lane estimation using basis curves,” by Huang and Teller. This paper shows how the development of automatic guiding systems is still challenging. The correct estimation of the lanes traveled by the vehicle is approached using a basic curve function for a lane, and estimating its parameters from vision or light detection and ranging (LIDAR) data. The estimation problem is formulated to use the Kalman filter and obtain robust solutions.

The papers on manipulation, an area of recent interest for humanoid robotics, discuss hands and their control, particularly force control for grasping, using automatic control methods.

Field robotics is only represented by a couple of papers. Moreover, the methods are only developed at the algorithmic level and tested in simulation, communicating the impression that real field robotics is still far away.

Medical robotics, a field with its own specialized literature, is present with one work on exoskeletons, “On the kinematic design of exoskeletons and their fixations with a human member,” by Jarrasse and Morel. They propose a method to analyze the degrees of freedom of the fixation that has to connect a human limb with a kinematically similar mechanical chain.

An interesting paper on biological robotics, “The smooth curvature flexure model: an accurate, low-dimensional approach for robot analysis,” by Odhner and Dollar, deals with modeling flexible structures. Considering the shift in the robotics field from stiff to soft structures, the traditional approach of modeling rigid bodies and rigid joints needs new methods and tools.

Robot perception addresses sensor placement and computation for navigation and user interfaces. The paper “Segmentation and unsupervised part-based discovery of repetitive objects,” by Triebel and others, is in the area of giving semantics to the sensory data, a recent inception in robotics. The authors have developed an unsupervised method to segment point clouds and detect objects that have multiple occurrences in the scene. Each segment is considered as an instance of a potential object part; objects are defined as a combination of their parts. Object detection is obtained through clustering in the feature space and then in the geometric space. The method worked well to discriminate between five classes (ceiling, wall, floor, chair, other) of objects.

The papers on planning and algorithms present different methods either to integrate trajectory planning with the controller or to develop optimal motion planning. Two unusual additions in this active and traditional research line are: “Remotely powered propulsion of helical nanobelts,” by Hwang and others, that considers the electro-osmotic force to control in closed-loop nano-robots, using more concepts of physics than mechanics, and “A molecular algorithm for path self-assembly in 3 dimensions,” by Schulman and Yurke, which develops a probabilistic approach that departs from the usual geometry-based path planning.

Learning is mostly about learning the sensory motor system, the most approached area in robot learning in recent years. “Closing the learning-planning loop with predictive state representations,” by Boots and others, instead develops the learning of the environment model. In this case, the planning method is an extension of partially observable Markov decision processes (POMDPs), and the algorithm is devised to compute the predictive state representation and to generalize it through linear transformations. The results, in simulation, show how to successfully close the loop between learning from (simulated) data and planning in the learned model.

The book will be of interest to researchers in the whole robotics field, and perhaps to researchers in the aspects of artificial intelligence that are strongly based on probabilistic methods.

The papers and supplementary material are freely available on the Web site for the book (http://www.roboticsproceedings.org/rss06/index.html).

Reviewer:  G. Gini Review #: CR140442 (1212-1216)
Bookmark and Share
  Featured Reviewer  
 
Robotics (I.2.9 )
 
 
Conference Proceedings (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