A Biologically Inspired Adaptive Working Memory System for Efficient Robot Control and Learning

An NSF ITR project

 

HOME     OVERVIEW     PEOPLE     PUBLICATIONS     RESOURCES

 

In the mammalian brain, the tension between the desire for flexibility and the need for efficiency is thought to be largely addressed by the interaction between working memory and executive control faculties in the prefrontal cortex (PFC) and systems supporting relatively automatic forms of behavior in more posterior areas. The efficient reactive processes of posterior brain areas typically drive behavior in common situations, and they are modulated by frontal systems when special circumstances arise. The frontal cortex is well equipped to maintain task-relevant information in a kind of working memory, and it is well positioned to guide action selection when flexibility is needed. Inspired by the utility of PFC in biological systems, we are implementing an adaptive working memory system for efficient robot control and learning based on computational neuro-science models, and we will assess the contribution of such a system to the successful performance of robot navigation and object manipulation tasks in dynamically changing environments.

 

 

 

Vanderbilt University

University of Missouri-Columbia

Investigators:

Mitch Wilkes

Marge Skubic

 

David Noelle

Jim Keller

 

Kaz Kawamura

 

 

 

 

Students:

Joshua Phillips 

Sam Blisard

 

Albert Spratley

Bob Luke

 

Palis Ratanaswasd

Charlie Huggard

 

Will Dodd

Erik Stone

 

Julia High

 

Mert Tugcu

 

 

 

PROJECT PUBLICATIONS

·        S. Blisard and M. Skubic, “Modeling Spatial Referencing Language for Human-Robot Interaction,” in Proc. of the IEEE Intl. Workshop on Robot and Human Interactive Communication (RO-MAN), Nashville, TN, Aug., 2005 (Best student paper award).  Paper

·        R.H. Luke, S. Blisard, J. Keller and M. Skubic, “Linguistic Descriptions of Three Dimensional Scenes Using SIFT Keypoints,” in Proc. of the IEEE Intl. Workshop on Robot and Human Interactive Communication (RO-MAN), Nashville, TN, Aug., 2005.  Paper

·        J. Phillips and D. Noelle, “A Biologically Inspired Working Memory Framework for Robots,” in Proc. of the IEEE Intl. Workshop on Robot and Human Interactive Communication (RO-MAN), Nashville, TN, Aug., 2005.

·        K. Kawamura, "Cognitive Approach to a Human Adaptive Robot Development", in Proc. of the IEEE Intl. Workshop on Robot and Human Interactive Communication (RO-MAN), Nashville, TN, Aug., 2005. Paper

·        M. Wilkes, M. Tugcu, J. Hunter, and D. Noelle, "Working Memory and Perception", in Proc. of the IEEE Intl. Workshop on Robot and Human Interactive Communication (RO-MAN), Nashville, TN, Aug., 2005.

·        W. Dodd and R. Gutierrez, "The Role of Episodic Memory and Emotion in a Cognitive Robot", in Proc. of the IEEE Intl. Workshop on Robot and Human Interactive Communication (RO-MAN), Nashville, TN, Aug., 2005.

·        P. Ratanaswasd, S. Gordon and W. Dodd, "Cognitive Control for Robot Task Execution", in Proc. of the IEEE Intl. Workshop on Robot and Human Interactive Communication (RO-MAN), Nashville, TN, Aug., 2005.

·        R.H. Luke, J.M. Keller, M. Skubic and S. Senger, “Acquiring and Maintaining Abstract Landmark Chunks for Cognitive Robot Navigation,” in Proc. of the IEEE Intl. Conf. on Robots and Intelligent Systems (IROS), Edmonton, Alberta, Canada, Aug., 2005.  Paper

·        J.L. Phillips and D.C. Noelle, “A Biologically Inspired Working Memory Framework for Robots,” in Proc. of the 27th Annual Meeting of the Cognitive Science Society, Stresa, Italy, July 2005.   Paper   Poster

·        P. Ratanaswasd, W. Dodd, K. Kawamura, and D. Noelle, "Modular behavior control for a cognitive robot," Proc. of the 12th Int'l Conf. on Advanced Robotics (ICAR), Seattle WA, July, 2005.  Paper

·        K. Kawamura, W. Dodd, P. Ratanaswasd, and R.A. Gutierrez, "Development of a Robot with a Sense of Self", Proc. of the 6th IEEE Intl. Symp. on Computational Intelligence in Robotics and Automation (CIRA), Espoo, Finland, June, 2005.  Paper

·        M. Skubic, “Qualitative Spatial Referencing for Natural Human-Robot Interfaces,” invited paper for Interactions, special issue on Human-Robot Interaction, vol. 12, issue 2, March-April, 2005, pp. 27-30.

·        Blisard, S., "Modeling Spatial References for Unoccupied Spaces for Human-Robot Interaction", M.S. thesis, Computer Science Dept., University of Missouri-Columbia, 2004.

·        M. Skubic, D. Noelle, M. Wilkes, K. Kawamura, J. Keller, “A Biologically Inspired Adaptive Working Memory for Robots,” AAAI 2004 Fall Symposium, Workshop on The Intersection of Cognitive Science and Robotics: From Interfaces to Intelligence, Washington, D.C., Oct. 21-24, 2004.   Abstract    Paper   

 

 

Project mailing list:  robot-pfc@elijah.vuse.vanderbilt.edu   (subscribers only)

Project Resources:   http://www.vuse.vanderbilt.edu/~noelledc/resources/RobotPFC/

 

Funded by the NSF (EIA-0325641)

M. Skubic
October, 2005