Robotics Institute: Mark Moll

Navigator: RI | People | Mark Moll

Mark Moll
PhD Student, CS

No longer a member of RI.

Jump to: Research interests | Keywords | Labs & Groups | Publications

Research interests

I am mainly interested in minimalistic robotics. Typical research questions are:

What are the minimal sensing requirements for getting enough information to perform a certain task?
How many degrees of freedom (DOF) and what kinds of DOFs does a manipulator need to perform a certain task?
Is it possible to plan efficiently for a robot that satisfies the minimal sensing and manipulation requirements?

One project I have worked on involved developing strategies to orient three-dimensional parts with minimal sensing and manipulation. That is, we would like to bring a part from an unknown position and orientation to a known orientation (but possibly unknown position) with minimal means. In general, it is not possible to orient a part completely without sensors, but it is sufficient if a particular orienting strategy can bring a part into one particular orientation with high probability. The sensing is then reduced to a binary decision: a sensor only has to detect whether the part is in the right orientation or not. If not, the part is fed back to the parts orienting device. Assuming the orienting strategy succeeds with high probability, on average it takes just a few tries to orient the part. An alternative view of this type of manipulation is to consider it as manipulation of the pose distribution. The goal then is to find the pose distribution with minimal entropy, thereby maximally reducing uncertainty.

Currently I am working on active sensing: a combination of (tactile) sensing and manipulation. I would like to find strategies to reconstruct unknown objects from sensor data, recognize known objects and manipulate objects.

Research interest keywords

computational sensors, control, geometric modeling, manipulation, and sensors

Past Labs & Groups

Manipulation Lab - The Manipulation Laboratory at Carnegie Mellon University investigates fundamental modes of manipulation under uncertainty.

Publications

Note: This list may not be comprehensive. It contains only those publications in the RI publications database. Entries are listed in reverse chronological order.

Manipulation of Pose Distributions
M. Moll and M. Erdmann
International Journal of Robotics Research, Vol. 21, No. 3, March, 2002, pp. 277-292. [Abstract]
Download: pdf [406 KB] copyrighted
Aligning Parts for Micro Assemblies
M. Moll, K. Goldberg, M. Erdmann, and R. Fearing
Assembly Automation, Vol. 22, No. 1, February, 2002, pp. 46-54. [Abstract]
Download: pdf [108 KB] copyrighted
Reconstructing Shape from Motion Using Tactile Sensors
M. Moll and M. Erdmann
Proc. 2001 IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems, November, 2001. [Abstract]
Download: pdf [323 KB] copyrighted
Uncertainty Reduction Using Dynamics
M. Moll and M. Erdmann
Proceeding of the 2000 Conference on Robotics and Automation, April, 2000. [Abstract]
Download: pdf [224 KB] copyrighted
Manipulation of Pose Distribitions
M. Moll and M. Erdmann
Workshop on the Algorithmic Foundations of Robotics, A. K. Peters, March, 2000. [Abstract]
Download: pdf [716 KB], ps.gz [916 KB] copyrighted
Manipulation of Pose Distributions
M. Moll and M. Erdmann
tech. report CMU-CS-00-111, Computer Science Department, Carnegie Mellon University, March, 2000. [Abstract]
Download: pdf [702 KB], ps.gz [847 KB] copyrighted

The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.
For updates and comments, please see these instructions.
This page maintained by robotwebmaster@ri.cmu.edu