Intelligent Systems: Robots, Agents, and Humans
Schedule: Spring 2021, MW 6:00-7:15pm
Location: Zoom
Professor: Dr. Gita Sukthankar
Office Hours: Zoom, W 4:15-5:45pm or F 4:00-5:30pm
This course is a study of systems that exhibit intelligent attributes.
We cover practical techniques for designing intelligent agents capable of
planning, learning, and cooperation. There will be discussion of
psychological/social ramifications of the use and creation of intelligent
systems. Much of the course focuses on various challenge problems (e.g.
the Trading Agent Competition and Robocup) that have been used to benchmark the performance of intelligent systems.
Prerequisites
- CAP5610 or equivalent machine learning/AI course
Objectives
After completing the course, students should:
- understand design issues facing the creators of intelligent systems
- understand research issues relating to the problem of creating human-like systems;
- learn practical techniques in planning, learning, three-tier architectures, and cooperation relevant to multi-agent and multi-robot systems;
- implement intelligent agents for a variety of domains;
Additionally, students will refine their research, writing, and
presentation skills.
Evaluation
Students will be evaluated on 1) their command of the material contained in
the papers and 2) their ability to design and implement agents using the
algorithms described in the papers.
- Assignments (30%)
- Paper presentation (10%)
- Final project (30%)
- Final exam (30%)
Topics
- Agent Components
- Planning
- Reinforcement Learning
- Multi-agent coordination
- Autonomous Agent Challenge Problems
- Trading Agent Competition
- Robocup
- Starcraft
- Intro to Robotics
- Path Planning
- Localization
- Multi-robot Coordination
- Human-Robot Interfaces
- Modeling Humans
- Agent Based Social Models
- Virtual Humans
- AI in the News/Ethics