CS 5973: Neuro/Cognitive Robotics (Fall 2005)

Designing control systems for robots performing a wide range of tasks in human environments is a non-trivial process, due in part to the complexities of constructing flexible and extensible representations of the environment, motor action, and task. However, many of these representational and computational problems have already been solved in human and non-human primates. In this course, we will examine a range of computational theories of representation, learning, and control from the neuro- and cognitive science domains and explore 1) the application of these theories in the design of robot control systems, and 2) the use of robotic implementations in testing these theories.

Topics will include:
  • The representation and learning of sequential motor skill (with particular focus on visual attention, reaching, grasping, and manipulation)

  • Action-oriented visual processing: the "how" and "what" visual pathways and their relationship to "affordances"

  • The use of affordances in the perception of the actions made by other agents

  • Symbol grounding and proto-language learning through perception and through interaction with the environment

  • The direct interface between brain and robot

  • Agent-agent interaction in learning and collaboration

This course will be taught in a seminar style. Readings will be drawn from the current literature in robotics, neuroscience, and cognitive psychology. Students will be responsible for leading several class discussions and for performing a project on a topic of the student's choosing.

Meeting Details

Meeting times: Tuesday/Thursday 3:00-4:15

Location (tentative): Carson 438

Requirements

Because this is an interdisciplinary topic, I am anticipating a range of different backgrounds. However, having a background in at least one of the related areas (computer science or engineering, cognitive psychology, or neuroscience) is important. In addition, having some training in probability and statistics will be helpful for all.

This course will be taught at the graduate level; I will consider also allowing advanced undergraduate students to participate, but on a case-by-case basis.


Critical Resources


fagg [[at]] ou.edu

Last modified: Sun Sep 11 21:34:33 2005