|
Developmental Robotics: Where developmental psychology meets autonomous robotics
Course: COMP 7/8514, PSYC 7/8514
Course meetings: Wednesdays 12:30 to 3:30 pm
Seminar presentations: Wednesdays 1:30-3:00 pm
Course room: FedEx Institute of Technology room 405-7
(Taken from http://developmentalrobotics.org/): Developmental Robotics is a new approach in artificial intelligence and robotics that focuses on the autonomous self-organization of general-purpose, task nonspecific control systems. It takes its inspiration from developmental psychology and developmental neuroscience. Developmental robotics is a move away from task-specific methodologies where a robot is designed to solve a particular pre-defined task (such as path planning to a goal location).
This new approach 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. Initially a developmental system might bootstrap itself with some innate knowledge or behavior, but with experience could create more complex representations and actions, leading to complete Autonomous Mental Development (AMD). Developmental robotics is different from many learning and evolutionary systems in that the reinforcement signal, teacher target, or fitness function comes from within the system. In this manner, these systems are designed to rely more on mechanisms such as self-motivation, homeostasis, or "emotions."
This semester, we will explore the psychological, philosophical, and computational aspects of this ground-breaking, interdisciplinary area of research. We will investigate from foundations all the way through the latest cutting-edge architectures that allow robots to develop and learn in the same manner as humans.
Expectations of enrolled students
Students will be expected to participate in a team project that examines and implements a developmental robotics architecture either in simulation or in a real robot. Psychology students will be paired with Computer Science students for the project. The Psychology students will be required to provide psychological foundations and discussion as well as the psychological description of the implementation. The Computer Science students will be required to implement the architecture in code and explain the technical aspects of the implementation. All students will be required to present at least one of the topics during the semester. Ph.D. students will be required to present at least twice and will be expected to introduce novel aspects to their projects. Here is a link to Google’s list of robotics simulators: directory.google.com/Top/Computers/Robotics/Software/Simulation/
Semester Schedule and Materials
The following table lists the presentations to be made from 1:30 to 3:00 PM each Wednesday. The table also includes references to suggested reading materials on the day’s topic. From 12:45-1:30, enrolled students will discuss that day’s topic. The first such period will be a time for getting acquainted. The final meeting during exam week is set aside for students to present their projects.
|
Date
|
Topic
|
Speaker(s)
|
|
January 18
|
Introduction
|
McCauley
|
|
January 25
|
Autonomous Mental Development by Robots and Animals
|
McCauley
|
|
February 1
|
Rethinking Infant Knowledge: Toward an Adaptive Process Account of Successes and Failures in Object Permanence Tasks
|
Dana
|
|
February 8
|
The Epigenesis of Meaning in Human Beings, and Possibly in Robots
|
Jason and Kyle
|
|
February 15
|
Modeling Cognitive Development in the Human Brain
|
Rodrigo and Bethany
|
|
February 22
|
Developmental Stages of Perception and Language Acquisition in a Physically Grounded Robot
|
TBA
|
|
March 1
|
Bootstrapping Grounded Word Semantics
|
Patrick
|
|
March 15
|
A Unified Model of Early Word Learning: Integrating Statistical and Social Cues
|
TBA
|
|
March 22
|
Bringing up robot: Fundamental mechanisms for creating a self-motivated, self-organizing architecture
|
Blank?
|
|
March 29
|
Incorporating Motivation in a Hybrid Robot Architecture
|
Stoytchev?
|
|
April 5
|
An Emergent Framework for Self-Motivation in Developmental Robotics
|
TBA
|
|
April 12
|
LIDA
|
Franklin
|
|
April 19
|
Neural Schema Mechanism
|
McCauley
|
|
April 26
|
Robot Rights
|
Grossman?
|
|
May 3 (10:00 – 12:00)
|
Student discussion of projects
|
Students
|
|
|
