Professor
Computer Science Department
Swarthmore College
500 College Ave.
Swarthmore, PA 19081
610-328-8565
meeden@cs.swarthmore.edu
I am a professor in the Computer Science Department and participate in the interdisciplinary program Cognitive Science at Swarthmore College. I received my Ph.D. in Computer Science with a minor in Cognitive Science from Indiana University in 1994. I received my B.A. in Mathematics from Grinnell College in 1985.
Research
My current research is in the field of developmental robotics which focuses on the autonomous self-organization of general-purpose, task-independent robot control systems. It takes its inspiration from developmental psychology and developmental neuroscience. Developmental robotics is a move away from the engineering approach where a robot is designed to solve a particular pre-defined task (such as path planning to a goal location). In contrast, developmental robotics explores the kinds of perceptual, cognitive, and behavioral capabilities that a robot can discover through self-motivated actions based on its own physical morphology and the dynamic structure of its environment.
In particular, I am interested in how a robot could be designed so as to choose actions based on self-motivation. My collaborators and I have begun to build such an architecture using a connectionist framework. In our model, self-motivation is viewed as an emergent property arising from two competing pressures: the need to accurately predict the environment while simultaneously wanting to seek out novelty in the environment. The robot's internal prediction error about how its sensory input will change over time is used to generate a reinforcement signal that pushes the robot to focus on areas of high error or novelty.
Selected Papers
- Editorial: Introduction to Developmental Robotics, co-authored with Douglas Blank. Connection Science, Volume 18, Number 2, 2006.
- Bringing up robot: Fundamental mechanisms for creating a self-motivating, self-organizing architecture, co-authored with Douglas Blank, Deepak Kumar, and Jim Marshall. Cybernetics and Systems, Volume 36, Number 2, 2005.
- An emergent framework for self-motivation in developmental robotics, co-authored with James Marshall and Douglas Blank, presented at The Third International Conference on Development and Learning, 2004.
- Heterogeneity in the coevolved behaviors of mobile robots: The emergence of specialists, co-authored with Mitchell Potter and Alan Schultz, Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence, Morgan Kaufmann, 2001.
- REAPER: A Reflexive Architecture for Perceptive Agents, co-authored with Bruce Maxwell, Nii Saka Addo, Paul Dickson, Nathaniel Fairfield, Nik Johnson, Edward Jones, Suor Kim, Pukar Malla, Matthew Murphy, Brandon Rutter, and Eli Silk, AI Magazine, volume 22, number 1, 2001.
- Nature versus Nurture in Evolutionary Computation: Balancing the Roles of the Training Environment and the Fitness Function in Producing Behavior, co-authored with Jordan Wales and Jesse Wells, GECCO Late Breaking Paper, 2000.
- Integrating Robotics Research with Undergraduate Education, co-authored with Bruce Maxwell, Special Issue of IEEE Intelligent Systems, edited by Robin Murphy, volume 15, number 6, 2000.
- Trends in Evolutionary Robotics, co-authored with Deepak Kumar, Soft Computing for Intelligent Robotic Systems, edited by L.C. Jain and T. Fukuda, Physica-Verlag, New York, NY, pages 215-233, 1998.
- Bridging the gap between robot simulations and reality with improved models of sensor noise, Proceedings of the Third Annual Conference on Genetic Programming, edited by Koza, J.R, et. al., Morgan Kaufmann Publishers, San Francisco, CA, pages 824-831, 1998.
- A Hybrid Connectionist and BDI Architecture for Modeling Embedded Rational Agents, co-authored with Deepak Kumar, presented at the Workshop on Cognitive Robotics, AAAI Fall Symposium Series at MIT, October, 1998.
- Learning in autonomous robots: A summary of the 1996 Robolearn Workshop, co-authored with Henry Hexmoor, Knowledge Engineering Review, Volume 11, Issue 4, 1997.
- An incremental approach to developing intelligent neural network controllers for robots, IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Volume 26, Number 3, pages 474-485, 1996.
- Towards planning: Incremental investigations into adaptive robot control, unpublished dissertation done under the guidance of Mike Gasser at Indiana University, 1994.
- Emergent control and planning in an autonomous vehicle, co-authored with Gary McGraw and Doug Blank, Proceedings of the Fifteenth Annual Conference of the Cognitive Science Society, Lawrence Erlbaum Associates, Hillsdale, NJ, pages 735-740, 1993.
- Exploring the symbolic/subsymbolic continuum: A case study of RAAM, co-authored with Doug Blank and Jim Marshall, The Symbolic and Connectionist Paradigms: Closing the Gap, edited by J. Dinsmore, Lawrence Erlbaum Associates, Hillsdale, NJ, pages 113-148, 1992.
Teaching
Current courses
- On sabbatical (Fall 2008)
Past courses
- CS21 Introduction to Computer Science (Spring 2008)
- CS37 The Structure and Interpretation of Computer Programs (Spring 2006)
- CS63 Artificial Intelligence (Fall 2007)
- CS75 Compiler Construction (Spring 2007)
- CS81 Adaptive Robotics (Spring 2008, Fall 2006, Spring 2003)
- COGS1 Introduction to Cognitive Science (Spring 2007)
Grants
- NSF CCLI EMD grant (2003-2006) Beyond LEGOs: Hardware, Software, and Curriculum for the Next Generation Robot Laboratory
- The Pyro software developed with the support of the grant
- Pyro received the NEEDS 2005 Premier Award for Excellence in Engineering Education Courseware
- See publications resulting from the grant
- NSF ILI grant (1996-1998) A
robot-based laboratory for teaching Artificial Intelligence
- Developed as a result of the grant,
Resource kit: A robot laboratory for teaching AI
- Developed as a result of the grant,
Resource kit: A robot laboratory for teaching AI