I am interested robotics and machine learning with a focus on planning
and control under uncertainty. I am particularly interested in
applications to robot manipulation.
Prospective Students
I am looking for motivated Ph.D. students who are interested in
robotics or machine learning. Please send a transcript and CV if
interested. For general background regarding topics that are important
in my research, please
see this page.
Teaching
Spring 2012, SUNY Buffalo: Introduction to Robot Algorithms
Fall 2009, Rice University: Seminar: Robot Manipulation
Fall 2007, Rice University: Introduction to Robotics
Research Highlights
Planning under uncertainty
One of the primary reasons robotics and autonomy problems are hard is
that the world is incompletely observed. For example, there is no
oracle telling a factory robot the exact location of a transmission
relative to the engine block to which it must be mounted. This
essential information must be estimated using perception techniques
that may fail. In these contexts, it is insufficient just to identify
the most likely state of the world; the system must be aware of what
it knows and what is not known. Furthermore, when the state of the
world is uncertain, the system must be capable of acting in order to
gain information. We have developed a new approach to planning under
uncertainty that performs well in continuous state, action, and
observation spaces and over long time horizons. Although we sacrifice
optimality, we still provide technical guarantees on convergence and
performance.
Our approach has important implications on robot grasping,
manipulation, and assembly. A big challenge in robot manipulation is
developing methods that are robust. We need methods that can guarantee
that a large percentage of manipulation attempts will be
successful. Our work provides an avenue toward achieving this. In our
approach, the robot "knows what it knows" and is capable to taking
information gathering actions as necessary. As a result, we can
guarantee a specified minimum likelihood of success with respect to
the modeled, but unknown, variables. For example, a robot that must
grasp an object would be capable of continuing to take information
gathering actions until it is sufficiently confident of success.
The animation at right illustrates our approach. There are two boxes
at the top and a robot end-effector moving at the bottom. Mounted to
the end-effector is a laser scanner that perceives the red scan dots
that are moving in the image. The objective is to simultaneously
localize and grasp the box on the right. The system has a model of
what the laser range finder will see in different box
configurations. It also has a model of how the boxes will move (based
on an assumed center of friction) when pushed. Initially, the system
expects that the boxes will be separated by a large gap and it will
be able to see them well. However, when the system looks, it finds
that the boxes are too close together. Therefore, the system pushes
the left box out of the way and, as a result, subsequently localizes
the box sufficiently well. Notice that in this example, there are no
predefined "pushing" action primitives. The system is actively
reasoning about every aspect of the information gathering.
State estimation for flexible materials manipulation
In the last decade, Bayesian inference has been successfully applied
to simultaneous localization and mapping (SLAM) problems in mobile
robot contexts. However, these approaches are infrequently applied to
manipulation problems. At NASA, we explored state estimation in the
context of manipulating soft or flexible materials. This turns out to
be an extremely important problem. Some of the most ergonomically
challenging work that automotive factory workers perform involves
mounting flexible materials such as cables, bags, or covers that
exposes the workers to repetitive motion injury.
At NASA and working jointly with General Motors, my collaborators and
I have developed strategies for using Bayesian filtering to localize
buttons or grommets in flexible materials using touch sensors. The
sequence of images below illustrates an application of the technique
to a grommet insertion task. The key to this work was modeling how the
material feels based on training data rather than attempting to
analytically model the unpredictable nature of the flexible materials
interaction. To our knowledge, this is the first application of
Bayesian filtering to the problem of interpreting subtle tactile
information. The research has resulted in an application that enables
Robonaut 2 to autonomously locate a snap or grommet embedded in fabric
and mate it with a fastener. It is among many capabilities that may be
demonstrated aboard the international space station when Robonaut 2
travels there in December, 2010.
As part of my graduate work at UMass Amherst, I explored a
special-purpose approach to managing the partially observable nature
of robot grasping problems. Rather than confronting the grasp problem
directly, we reduce grasping to a fully observable projection of the
original problem that is solvable using standard control methods. In
the reduced problem, controller state is always measurable using
fingertip force sensors. We demonstrated that solutions to the reduced
problem are also solutions to the original problem and that the
resulting grasp controller is guaranteed to eventually reach these
solutions. The approach was validated using Dexter, a robot at UMass,
and found to be very effective in practice. Essentially, the robot
``feels'' its way into a grasp configuration.
Abdallah, M., Platt, R., Wampler, C., Decoupled Torque Control of Tendon-Driven Fingers with Tension Management, Submitted to the International Journal of Robotics Research.
Platt, R., Kaelbling, L., Lozano-Perez, T., Tedrake,
R. Non-Gaussian Belief
Space Planning: Correctness and Complexity, IEEE Int'l
Conf. on Robotics and Automation, 2012. (The final version of the
paper posted here fixes some errors that were present in the proofs in
the submitted version.)
Platt, R., Ihrke, C., Bridgwater, L., Linn, M., Diftler, M., Abdallah, M., Askew, S., Permenter, F., A miniature load cell suitable for mounting on the phalanges of human-sized robot fingers, IEEE Int'l Conf. on Robotics and Automation, Shanghai, May, 2011
Diftler, M., Mehling, J., Abdallah, M., Radford, N., Bridgwater, L., Sanders, A., Askew, S., Linn, D., Yamokoski, J., Permenter, F., Hargrave, B., Platt, R., Savely, R., Ambrose, R., Robonaut 2: The First Humanoid Robot in Space, IEEE Int'l Conf. on Robotics and Automation, Shanghai, May, 2011
Platt, R., Abdallah, M., Wampler, C., Multiple-priority impedance control, IEEE Int'l Conf. on Robotics and Automation, Shanghai, May, 2011
Platt, R., Abdallah, M., Wampler, C. Multi-Priority Cartesian Impedance Control, Proceedings of Robotics: Science and Systems 2010 (RSS), Zaragosa, Spain, June 27, 2010
Platt, R., Permenter, F., Pfeiffer, J., Inferring hand-object configuration directly from tactile data, Electronically published proceeding of the Mobile Manipulation Workshop, IEEE Conference on Robotics and Automation (ICRA), Anchorage, Alaska, May 2010
de Granville, C., Wang, D., Southerland, J., Platt, Jr. R., and Fagg, A. H.,
Grasping Affordances: Learning to Connect Vision to Hand Action,
``The Path to Autonomous Robots; Essays in Honor of George A. Bekey'' (Gaurav S. Sukhatme, Ed.), Springer, 2009
Robert Platt, Mars Chu, Myron Diftler, Toby Martin, Michael Valvo,
A Miniature Force Sensor for Prosthetic Hands, Workshop on
Robotic Systems for Rehabilitation, Exoskeleton, and Prosthetics,
Robotics: Science and Systems, University of Pennsylvania,
Philadelphia, PA, August 18, 2006.
Platt, R., Fagg, A. H., Grupen, R.,
Re-using Schematic Grasping Policies,
IEEE-RAS International Conference on Humanoid Robots,
Tsukuba, Japan, December 5-7, 2005
K. Rohanimanesh, R. Platt Jr., S. Mahadevan, and R. Grupen
Coarticulation in Markov Decision Processes ,
Eighteenth International Conference on Neural Information
Processing Systems (NIPS), December 2004 (ps:
447KB)
William Bluethmann, Robert Ambrose, Myron Diftler, Eric Huber, Andy
Fagg, Michael Rosenstein, Robert Platt, Roderic Grupen, Cynthia
Breazeal, Andrew Brooks, Andrea Lockerd, R. Alan Peters II, O. Chad
Jenkins, Maja Mataric, Magdalena Bugajska
Building an Autonomous Humanoid Tool User,
Proceedings of the 2004 IEEE International
Conference on Humanoid Robots, Los Angeles, CA, USA November 2004
A. Fagg, M. Rosenstein, R. Platt and R. Grupen,
Extracting User Intent in Mixed Initiative Teleoperator
Control, AIAA-2004-6309 AIAA 1st Intelligent Systems Technical
Conference, Chicago, Illinois, Sep. 20-22, 2004
T. Martin, M. Diftler and R. Ambrose, R. Platt, M. Butzer,
Tactile Sensors for the NASA/DARPA Robonaut, AIAA 1st
Intelligent Systems Technical Conference, Chicago, Illinois,
Sep. 20-22, 2004
The animation at right illustrates our approach. There are two boxes
at the top and a robot end-effector moving at the bottom. Mounted to
the end-effector is a laser scanner that perceives the red scan dots
that are moving in the image. The objective is to simultaneously
localize and grasp the box on the right. The system has a model of
what the laser range finder will see in different box
configurations. It also has a model of how the boxes will move (based
on an assumed center of friction) when pushed. Initially, the system
expects that the boxes will be separated by a large gap and it will
be able to see them well. However, when the system looks, it finds
that the boxes are too close together. Therefore, the system pushes
the left box out of the way and, as a result, subsequently localizes
the box sufficiently well. Notice that in this example, there are no
predefined "pushing" action primitives. The system is actively
reasoning about every aspect of the information gathering.
In the last decade, Bayesian inference has been successfully applied
to simultaneous localization and mapping (SLAM) problems in mobile
robot contexts. However, these approaches are infrequently applied to
manipulation problems. At NASA, we explored state estimation in the
context of manipulating soft or flexible materials. This turns out to
be an extremely important problem. Some of the most ergonomically
challenging work that automotive factory workers perform involves
mounting flexible materials such as cables, bags, or covers that
exposes the workers to repetitive motion injury.
As part of my graduate work at UMass Amherst, I explored a
special-purpose approach to managing the partially observable nature
of robot grasping problems. Rather than confronting the grasp problem
directly, we reduce grasping to a fully observable projection of the
original problem that is solvable using standard control methods. In
the reduced problem, controller state is always measurable using
fingertip force sensors. We demonstrated that solutions to the reduced
problem are also solutions to the original problem and that the
resulting grasp controller is guaranteed to eventually reach these
solutions. The approach was validated using Dexter, a robot at UMass,
and found to be very effective in practice. Essentially, the robot
``feels'' its way into a grasp configuration.