📄 http:^^www.cim.mcgill.ca^~dudek^mobile.html
字号:
MIME-Version: 1.0
Server: CERN/3.0pre6
Date: Monday, 25-Nov-96 23:57:15 GMT
Content-Type: text/html
Content-Length: 19674
Last-Modified: Thursday, 31-Oct-96 14:43:52 GMT
<!DOCTYPE HTML PUBLIC "-//IETF//DTD HTML 2.0//EN"><HTML><head><META HTTP-EQUIV="ISBN" CONTENT="Mobile Robots DudekMR195"><META HTTP-EQUIV="AUTHOR" CONTENT="Gregory Dudek"><META HTTP-EQUIV="SHORTTITLE" CONTENT="MobileGD"><META HTTP-EQUIV="COPYRIGHT" CONTENT="© 1995, 1996. G. Dudek. All Rights Reserved Worldwide"><LINK REV="made" HREF="dudek@cim.mcgill.ca"><title>Mobile Robotics / Shape Group, CIM, McGill</title></head> <BODY><p><h1><!WA0><img src="http://www.cim.mcgill.ca/~dudek/mobile/mrl.gif" lowsrc="http://www.cim.mcgill.ca/~dudek/mobile/mrl-lr2.gif" WIDTH=279 HEIGHT=406 ALT="Robot Picture"> Information on the Mobile Robotics and Shape Recognition group at <!WA1><a href="http://www.cim.mcgill.ca/">CIM</a> </h1><P><!WA2><a href="http://www.cim.mcgill.ca/~dudek/mobile/robodaemon.html">Here is a special link re. ROBODAEMON</a>put in place for the McGill175th anniversary Open House.<P>The mobile robotics and shape recognition group is an informal grouping of people and projects at the centre. The group has at least three mobile robots sporting a collection of sensors including sonar, video, BIRIS, and infra-red reflectance, depending on the current experiments in progress. The primary computing resources are SGI Indigos and INDYs, some SUN sparc's, and a few other computingdevices integrated into the general CIM computing environment.<BR><I>Last update: October 1996.</I><P>This group is involved in issues of <B>form representation and discovery.</B>This relates specifically to the <UL><LI>exploration and representation ofunknown environments using mobile robots, <LI> and the representation andrecognition of objects.</UL>Key technical foci are the abstraction of shape models across scale,the relationship between signals and symbolic descriptions.<P>Some of the problems we areinterested in include the following.How can a moving observer such as a robot recognizewhere it is? How can it build but a virtual reality modelof its world for use by a human operator (this is important fortasks such as remote inspection)? How can a robot learn efficientlyabout where it is? How can a group of robots collaboate efficiently?<P>A typical prosaic objective create a robot thancan learn your office over the weekend:<em> It is delivered on Friday, you open the box, leave it on the floor, and go home. By Monday morning the robot would have explored the office and would be able to carry out delivery and search tasks (``Get my mail and find Mary and escort her to the conference room'').</em><P>Note: this page is informally maintainedby <!WA3><a href="ftp://ftp.cim.mcgill.ca/pub/mobile-robot/dudek.html">Professor Gregory Dudek </a>from the <!WA4><a href="http://www.cs.mcgill.ca/">School of Computer Science </a> and, as such, is not meant to be representative of research at the Centre for Intelligent Machines (CIM) or <!WA5><A HREF="http://www.mcgill.ca/">McGill</A> as a whole. It's rarely up-to-date.We are at <!WA6><a href="http://www.cim.mcgill.ca/~dudek/mtl.html">McGill University in Montreal. This link provides informationon visiting us.</a> <P ALIGN=CENTER><!WA7><img src ="http://www.cim.mcgill.ca/~dudek/mobile/movingdivider.gif" WIDTH=216 HEIGHT=5 ></P><HR><h2>Other Information</h2>A small amount of additional information, some papers and some demo software from the mobile robotics group is available for<!WA8><a href="ftp://ftp.cim.mcgill.ca/pub/mobile-robot">FTP access</a>.<A NAME="bibliography"></A><h3>Bibliography, by sub-topic</h3><P>A bibliography on mobile robotics, together withentries on related research topics, can be <!WA9><A HREF="http://www.cim.mcgill.ca/~dudek/mobile/mobilebib.html">searched on-line.</A> A slightly dated list of selected referencesis <!WA10><a href="ftp://ftp.cim.mcgill.ca/pub/mobile-robot/mrbib.ps">available in postscript form</a>. <BR>You areinvited to <!WA11><a href="http://www.cim.mcgill.ca/~dudek/mobile/bib-submit.html">submit additional entries to beincluded.</a><A NAME="movie"></A><h3>Movie</h3><BR>A two minutedemo movie is <!WA12><a href="ftp://ftp.cim.mcgill.ca/pub/mobile-robot/movie-MobRobotVision.QT.bin">available inquicktime format (7.4 Meg binhex encoded)<!WA13><img src ="http://www.cim.mcgill.ca/~dudek/mobile/4fanim.gif" WIDTH=160 HEIGHT=120 lowsrc="http://www.cim.mcgill.ca/~dudek/mobile/4fanim-lr.gif" ALT="illustrative 4-frame animation"></a>or in<!WA14><a href="ftp://ftp.cim.mcgill.ca/pub/mobile-robot/movie-MobRobts&Vision.MPG">MPEG format (3.1 Meg).</a>The quicktime version is a compressed MacBinary file. TheMPEG version has no audio track; a major disadvantage.Be warned that to keep the size down, the movie has been severlycompressed and the quality isn't great (image size is 160x120 but itshould be played a double size on most machines).<h3>Newton books</h3><p><DIR><LI> Much is this information is also available in the form of a Newton Book for perusal using an Apple Newton device. <!WA15><A HREF="ftp://ftp.cim.mcgill.ca//pub/mobile-robot/Mobile_Robotics@McGill.pkg.sit">Click here to obtain a "stuffit" archive of this book.</A> (Note: some of the terms above may be tradmarked by their respective owners.)<LI> A brief abstract of some of our work on position estimation in different contexts is also available <!WA16><A HREF="ftp://ftp.cim.mcgill.ca//pub/mobile-robot/position.pkg.hqx">for download as a Newton book</A>.</DIR><p>More information sources are mentioned at the end of this page.<P><HR><A NAME="students"></A><h2>Graduate students</h2>If you want to apply to be a grad student working in this group, you canget <!WA17><a href="http://www.cs.mcgill.ca/page/graduate.html">further information </a> from the school of computer science.Note that CIM is not an "academic unit" and different faculty are officially associated with different departments.<P ALIGN=CENTER><!WA18><img src ="http://www.cim.mcgill.ca/~dudek/mobile/movingdivider.gif" WIDTH=216 HEIGHT=5 ></P><HR><A NAME="projects"></A><h2>Some specific projects</h2><!WA19><img src ="ftp://ftp.cim.mcgill.ca/pub/mobile-robot/RWI+PTU_clipped_8b.GIF" ALT="Cute Robots!"><ul><li>Distributed Robot Control Software Environment<BR><h4><!WA20><a href="http://www.cim.mcgill.ca/~dudek/mobile/dudek.html">G. Dudek</a></h4>A Distributed, device independent mobile robot controller and simulator.It supports distributed computation and visualization and can control one or more real Nomad or RWI robots. <!WA21><a href="http://www.cim.mcgill.ca/~dudek/mobile/daemon.html">Some additional details and a picture are available.</a> </li><p><li>Environment Shape and Layout from Active Shadows<BR><h4><!WA22><a href="http://www.neci.nj.nec.com/homepages/langer.html">M. Langer (NEC)</a>, M. Daum,G. Dudek, S. W. Zucker</h4>This project deals with the inference of environmental structure from shadow information.<!WA23><a href="http://www.cim.mcgill.ca/~dudek/mobile/shadows.html">Click here for an abstract</a><p><li>Multi-Robot Exploration and Rendezvous<BR><h4>N. Roy, I, Rekleitis, G. Dudek.</h4>This project deals with the exploration of an unknownenvironment using two or more robots working together.Key aspects of the problems coordination, and particularlyrendezvous, between the robots, and efficient decompositionof the exploration task.<p><li>Object description and recognition<BR><h4>W. Alami, G. Dudek, Nigel Ayoung-Chee, Frank Ferrie</h4><!WA24><a href="http://www.cim.mcgill.ca/~dudek/mobile/pose.html">Click here for abstract</a><p><li>Mobile Robot Exploration by using Fused Data from Two Sensors<BR><h4><!WA25><a href="http://www.cim.mcgill.ca/~yiannis/">Yiannis Rekleitis,</a>G. Dudek, P. Freedman</h4>This research investigates the combined use of a sonar range finder and a laser rangefinder (QUADRIS or BIRIS) for exploring a structured indoor environment.The methodology is called "just-in-time" sensing. <!WA26><a href="http://www.cs.mcgill.ca/~yiannis/mrobot.html">A longer abstract is also available.</a><p><li>Reliable Vehicle Trajectory Planning<BR><h4>G. Dudek, Chi Zhang</h4>We are using a hybrid method for vehicle path planning that guarantees globally acceptable solutions yet has limit time and space complexity. This depends on a combination of variational methods with other approaches.<p><li>Localizing a Robot with Minimum Travel <BR><h4>Gregory Dudek (dudek@cim.mcgill.ca), Kathleen Romanik (romanik@dimacs.rutgers.edu), Sue Whitesides (sue@cs.mcgill.ca)</h4><!WA27><a href="http://www.cim.mcgill.ca/~dudek/mobile/soda.html">Click here for abstract</a><p><li>Multi-Robot Collaboration<BR></a><h4>G. Dudek in collaboration with Professors E. Milios and <!WA28><a href="http://www.cs.yorku.ca/People/jenkin/Welcome.html">M. Jenkin⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -