http:^^www.ai.mit.edu^projects^handarm-haptics^manipulation.html

This data set contains WWW-pages collected from computer science departments of various universities

<table border=5 cellspacing=5 cellpadding=5>
<tr>
<a name="S2.1"><th bgcolor=steelblue>Robust Grasping in Unstructured
Environments</th></a>
</tr>
<tr>
<td align=center><!WA22><img src="http://www.ai.mit.edu/projects/handarm-haptics/images/picksort.gif" width=478 height=357></td>
</tr>
<tr>
<td>
One of our current projects, funded by NASA/JPL, is to develop a
fundamental understanding of the problem of combining real time vision
and touch sensor data with robot control, to yield robust, autonomous
and semi-autonomous grasping and grasp-stabilization. The research
is focused on providing conceptual and experimental support of planned
and on-going NASA missions utilizing earth-orbiting and planetary
surface robotics.
<P>

We have implemented a high-speed active vision system, a
multi-processor operating system, and basic algorithms for acquisition and
grasp of stationary spherical and cylindrical objects using coordinated
robotic vision, touch sensing, and control.  Preliminary experiments on the
tracking of moving objects have also been completed.  Concurrently,
research into an integrated wrist-hand design used for
performing sensor guided grasps, and a preliminary design for a
next-generation miniature end-effector are being completed.
</td>
</tr>
</table>
</center>
<p>


<center>
<table border=5 cellspacing=5 cellpadding=5>
<tr>
<a name="S2.2"><th colspan=2 bgcolor=steelblue>Robotic Catching of
Free Flying Objects</th></a>
</tr>
<tr>
<td colspan=2>
Another direction of our research, funded by Fujitsu, Furukawa, and
the Sloan Foundation, is to accomplish real-time robust
catching of free flying objects.  We are currently focusing on
spherical balls of various sizes.  We are also
experimenting with additional objects with different dynamic
characteristics such as sponge balls, cylindrical cans, and paper
airplanes.
</td>
</tr>
<tr>
<td colspan=2 align=center><!WA23><img src="http://www.ai.mit.edu/projects/handarm-haptics/images/wam7-2.gif" width=446
height=297></td>
</tr>
<tr>
<td colspan=2>
Our system uses low cost vision processing hardware for simple
information extraction.  Each camera signal is processed independently
on vision boards designed by other members of the MIT AI Laboratory
(the <!WA24><a href="http://www.newtonlabs.com/">Cognachrome Vision Tracking
System</a>).  These vision boards provide us with the center 
of area, major axis, number of pixels, and aspect ratio of the color
keyed image.  The two Fast Eye Gimbals allow us to locate and track
fast randomly moving objects using "Kalman-like" filtering methods
assuming no fixed model for the behavior of the motion.  Independent
of the tracking algorithms, we use least squares techniques to fit
polynomial curves to prior object location data to determine the
future path.  With this knowledge in hand, we can calculate a path for
the WAM to match trajectories with the object to accomplish catching
and smooth object/WAM post-catching deceleration. 
<P>

In addition to the basic least squares techniques for path prediction, 
we study experimentally nonlinear estimation algorithms to give "long term"
real-time prediction of the path of moving objects, with the goal of robust
acquisition.  The algorithms are based on stable on-line construction of
approximation networks composed of state space basis functions localized in
both space and spatial frequency. As a initial step, we have studied the
network's performance in predicting the path of light objects thrown in
air. Further application may include motion prediction of objects rolling,
bouncing, or breaking up on rough terrains.
<P>

Some recent successful results for the application of this network
have been obtain in catching of sponge balls and even paper airplanes!
</td>
</tr>
<tr>
<td align=center>
<!WA25><a href="http://www.ai.mit.edu/projects/handarm-haptics/catching.html"><!WA26><img src="http://www.ai.mit.edu/projects/handarm-haptics/images/wamcatch.gif" width=166
height=250></a><br>Click to view <!WA27><a href="http://www.ai.mit.edu/projects/handarm-haptics/catching.html">WAM
catching</a>.
</td>
<td align=center>
<!WA28><a href="http://www.ai.mit.edu/projects/handarm-haptics/airplane.html"><!WA29><img src="http://www.ai.mit.edu/projects/handarm-haptics/images/airp-catch.gif" width=168
height=250></a><br>Click to view <!WA30><a href="http://www.ai.mit.edu/projects/handarm-haptics/airplane.html">WAM Airplane
catching</a>.
</td>
</tr>
<tr><td>
&copy 1995 Photo courtesy of <!WA31><a
href="http://www.scinetphotos.com/">Hank Morgan</a>
</td></tr>
</table>
</center>
<p>

<hr>
<center>
<!WA32><a href="#S0">[Introduction]</a>
<!WA33><a href="#S1">[Our Robots]</a>
<!WA34><a href="#S2">[Our Research]</a>
<!WA35><a href="#S3">[References]</a>
</center>
<hr>

<!--------------------------------------->
<!------------ References --------------->
<!--------------------------------------->

<center>
<a name="S3"><h1>Partial List of References</h1></a>
</center>

<!WA36><IMG SRC="http://www.ai.mit.edu/gifs/ball.red.gif" ALT="*"> 
<!WA37><A HREF="http://www.ai.mit.edu/projects/handarm-haptics/abstracts/aiaa96-abst.html"><I>Autonomous Rock Acquisition</I></A>,
D.A. Theobald, W.J. Hong, A. Madhani, B. Hoffman, G. Niemeyer, L.
Cadapan, J.J.-E. Slotine, J.K. Salisbury, Proceedings of the AIAA
Forum on Advanced Development in Space Robotics, Madison, Wisconsin,
August 1-2, 1996.<P>

<!WA38><IMG SRC="http://www.ai.mit.edu/gifs/ball.red.gif" ALT="*"> 
<!WA39><A HREF="http://www.ai.mit.edu/projects/handarm-haptics/abstracts/iser95-abst.html"><I>Experiments in Hand-Eye
Coordination Using Active Vision</I></A>, W. Hong and J.J.E. Slotine,
Proceedings of the Fourth International Symposium on Experimental
Robotics, ISER'95, Stanford, California, June 30-July 2, 1995.<P>

<!WA40><IMG SRC="http://www.ai.mit.edu/gifs/ball.red.gif" ALT="*"> 
<!WA41><A HREF="http://www.ai.mit.edu/projects/handarm-haptics/abstracts/hong-msthesis-abst.html"><I>Robotic Catching and
Manipulation Using Active Vision</I></A>, W. Hong, M.S. Thesis,
Department of Mechanical Engineering, MIT, September 1995.<P>

<!WA42><IMG SRC="http://www.ai.mit.edu/gifs/ball.red.gif" ALT="*"> 
<!WA43><A HREF="http://www.ai.mit.edu/projects/handarm-haptics/abstracts/neurocomp95-abst.html"><I>Space-Frequency Localized Basis
Function Networks for Nonlinear System Estimation and Control</I></A>,
M. Cannon and J.J.E. Slotine, Neurocomputing, 9(3), 1995.<P>

<!WA44><IMG SRC="http://www.ai.mit.edu/gifs/ball.red.gif" ALT="*"> 
<!WA45><A HREF="http://www.ai.mit.edu/projects/handarm-haptics/abstracts/adaptvis-abst.html"><I>Adaptive Visual Tracking and
Gaussian Network Algorithms for Robotic Catching</I></A>, H. Kimura
and J.J.E. Slotine, DSC-Vol. 43, Advances in Robust and Nonlinear
Control Systems, Winter Annual Meeting of the ASME, Anaheim, CA, pp.
67-74, November 1992.<P>

<!WA46><IMG SRC="http://www.ai.mit.edu/gifs/ball.red.gif" ALT="*"> 
<!WA47><A HREF="http://www.ai.mit.edu/projects/handarm-haptics/abstracts/robotcatch-abst.html"><I>Experiments in Robotic
Catching</I></A>, B.M. Hove and J.J.E. Slotine,
Proceedings of the 1991 American Control Conference, Vol. 1, Boston, MA,
pp. 380-385, June 1991.<P>

<!WA48><IMG SRC="http://www.ai.mit.edu/gifs/ball.red.gif" ALT="*"> 
<!WA49><A HREF="http://www.ai.mit.edu/projects/handarm-haptics/abstracts/perfadapt-abst.html" ><I>Performance in Adaptive
Manipulator Control</I></A>, G. Niemeyer and J.J.E. Slotine,
International Journal of Robotics Research 10(2), December, 1988.<p>

<!WA50><IMG SRC="http://www.ai.mit.edu/gifs/ball.red.gif" ALT="*"> 
<i>Preliminary Design of a Whole-Arm Manipulation System (WAM)</i>,
J.K. Salisbury, W.T. Townsend, B.S. Eberman, D.M. DiPietro,
Proceedings 1988 IEEE International Conference on Robotics and 
Automation, Philadelphia, PA, April 1988.<P>

<!WA51><IMG SRC="http://www.ai.mit.edu/gifs/ball.red.gif" ALT="*"> 
<i>The Effect of Transmission Design on Force-Controlled Manipulator
Performance</i>, W.T. Townsend, PhD Thesis, Department of Mechanical
Engineering, MIT, April 1988.  See also MIT AI Lab Technical 
Report 1054.<P>

<!WA52><IMG SRC="http://www.ai.mit.edu/gifs/ball.red.gif" ALT="*"> 
<i>Whole Arm Manipulation</i>, J.K. Salisbury, Proceedings
4th International Symposium on Robotics Research, Santa Cruz, CA, August,
1987.<P>

<!WA53><IMG SRC="http://www.ai.mit.edu/gifs/ball.red.gif" ALT="*"> 
<!WA54><a href="http://www.ai.mit.edu/projects/handarm-haptics/abstracts/fegthesis-abst.html"><i>Design and Control of a
Two-Axis Gimbal System for Use in Active Vision</i></a>, N. Swarup,
S.B. Thesis, Dept. of Mechanical Engineering, MIT, Cambridge, MA,
1993.<p>

<!WA55><IMG SRC="http://www.ai.mit.edu/gifs/ball.red.gif" ALT="*"> 
<!WA56><A HREF="http://www.ai.mit.edu/projects/handarm-haptics/abstracts/portvis-abst.html"><I>A High Speed Low-Latency Portable
Vision Sensing System</I></A>, A. Wright, SPIE, September 1993.<P>
 

<hr>
<center>
<!WA57><a href="#S0">[Introduction]</a>
<!WA58><a href="#S1">[Our Robots]</a>
<!WA59><a href="#S2">[Our Research]</a>
<!WA60><a href="#S3">[References]</a>
</center>
<hr>
<p>

<i>Maintainer: <!WA61><a href="mailto:[e-mail]">[e-mail]</a>,
Comments to: <!WA62><a href="mailto:[e-mail]">[e-mail]</a><br>
Last Updated: Mon Aug 26 15:18:36 EDT 1996, [e-mail]<br>
&copy 1996, All rights reserved.
</i>
</body>