Newsgroups: comp.robotics
Path: brunix!news.Brown.EDU!agate!howland.reston.ans.net!cs.utexas.edu!utnut!utcsri!newsflash.concordia.ca!hobbit.ireq.hydro.qc.ca!NetNews.ireq.hydro.qc.ca!gamin
From: gamin@ireq-robot.hydro.qc.ca (Martin Boyer)
Subject: Re: Future Robots in Industry (cont)
In-Reply-To: buluswar@cs.umass.edu's message of 18 Nov 93 15:40:28 EDT
Message-ID: <GAMIN.93Nov19125120@pellan.ireq-robot.hydro.qc.ca>
Lines: 25
Sender: news@ireq.hydro.qc.ca (Netnews Admin)
Organization: Le laboratoire de robotique de l'Institut de recherche
	d'Hydro-Quebec
References: <752897110.F00002@ocitor.fidonet> <2cgj3cINN1cm@ymir.cs.umass.edu>
Date: Fri, 19 Nov 1993 16:51:20 GMT

>>>>> Shashi Buluswar writes:

>I think one of the problems that is holding back the entire
>field of robotics from an explosion into many areas of 
>application is Vision.  

This is kind of short-sighted.

It looks as if you are implying that good computer vision is enough
to assemble complex parts or to carry out tasks in an unstructured
environment.  That's not true; dealing with contact forces or inertia
is a hot research topic (and a hard practical problem, believe me).

Specially in the field I'm working in, telerobotics, there are some
parameters that depend exclusively on the manipulator side of things.
Stable control in contact is still not trivial.  High acceleration,
high precision are still expensive.  And there are no robots with the
versatility of the human arm.  Robust software is still a research
issue.

--
Martin Boyer                            mboyer@ireq-robot.hydro.qc.ca
Institut de recherche d'Hydro-Quebec    mboyer@ireq-robot.uucp
Varennes, QC, Canada   J3X 1S1
+1 514 652-8412
