Intelligent Systems: Robots, Agents, and Humans
Schedule: Spring 2008, TR 9:00-10:15am
Location: HEC 302
Professor: Dr. Gita Sukthankar
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
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.
Due Dates
- Final Exam (take-home), out on Mar 25th, due on Apr 1st
- Paper Presentations: Apr 1-17th
- Homework: Apr 11th
- Final Project Writeup (latex template, word template): Apr 24th
- Final Project Demo: Apr 23rd 1-4pm HEC 111
Outline
- Introduction
- Multiagent Systems
- Introduction to Planning
- Planning in Computer Games
- Combining Planning and Learning
- Trading Agent Competition
- Bidding under Uncertainty
- TAC: Supply Chain
Management
- Reading: Teacy, W. T. L., T. D. Huynh, R. K. Dash, N. R. Jennings, J.
Patel, and M. Luck. The ART of IAM: The Winning Strategy for the 2006 Competition, The Workshop on Trust in Agent Societies at The Sixth International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS-2007), Honolulu, Hawaii, USA, May 15, pp. 102-111
- Agent Reputation and
Trust
- Reading: Peter Stone, Manuela Veloso, and Patrick Riley. The CMUnited-98 Champion Simulator Team. In M. Asada and H.Kitano, editors, RoboCup-98: Robot Soccer World Cup II Lecture Notes in Artificial Intelligence, pp. 61.76, Springer Verlag 1999.
- Robocup
- Urban Rescue Robots
- Reading: Leslie Pack Kaelbling, Michael L. Littman, and Andrew W. Moore. Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 4:237--285, May 1996
- Reinforcement Learning
- Reading: Peter Stone and Manuela Veloso. Team-Partitioned, Opaque-Transition Reinforcement Learning. In Minoru Asada and Hiroaki Kitano, editors, RoboCup-98: Robot Soccer World Cup II, Lecture Notes in Artificial Intelligence, pp. 261.72, Springer Verlag, Berlin, 1999. Also in
Proceedings of the Third International Conference on Autonomous Agents,
1999
- Multi-Agent Reinforcement Learning
- Transfer
Reinforcement Learning
- Multi-robot Coordination
- Multi-agent Coordination (Team Planning)
- No Class (Mar 11-13th)
- Emulating Humans (Emotion)
- Emulating Humans (Motion)
- Emulating Humans (Teamwork)
- No Class; Take-home Exam (Mar 27)
- Student Paper Presentations (Apr 1-17th)
- Apr 1 Presenter: Phillip Verbancsics, Paper: R. Pienaar and J. Kruger,
An egocentric approach to machine intelligence
Presenter: Bryan Rosander, Paper: A. Sanchez-Ruiz, S. Lee-Urban, H.
Munoz-Avila, B. Diaz-Augdo, P. Gonzalez-Calera, Game AI for a Turn-based Strategy Game with Plan Adaptation and
Ontology-based Retrieval
- Apr 3 Presenter: Robert Hauser, Paper: T. Balch and M. Hybinette, Social Potentials for Scalable Multi-Robot
Formations Proceedings of IEEE International Conference on Robotics and
Automation, 2000
Presenter: J.T. Folsom-Kovarik Paper: S. Whiteson, P. Stone
Evolutionary Function Approximation for Reinforcement Learning, Journal
of Machine Learning Research, 2006
- Apr 8 Presenter: Dan DeBlasio, Paper: Uchibe, E.; Asada, M., Incremental Coevolution With Competitive and Cooperative Tasks in a Multirobot Environment, Proceedings of the IEEE , vol.94, no.7, pp.1412-1424, July 2006
Presenter: Matt Meighan, Paper: E. Jones, B. Browning, M. Dias, B. Argall,
M. Veloso, and A. Stentz, Dynamically
Formed Heterogeneous Robot Teams Performing Tightly Coordinated Tasks
International Conference on Robotics and Automation, May, 2006, pp. 570 -
575
- Apr 10 Presenter: David Lyle, Paper: C. Scrapper, S. Balakirsky, and E.
Messina, MOAST and
USARSim- A Combined Framework for the Development and Testing of Autonomous
Systems, Proceedings of the SPIE Defense and Security Symposium, 2006
Presenter: Mikel Rodriguez, Paper: S. Bahadori and L. Iocchi, Human Body Detection in the RoboCup Rescue Scenario, Proc. Int. RoboCup Symposium, 2003
- Apr 15 Presenter: Richard Lum, Paper: C. Yunpeng, C. Jiang, Y. Jinyi, and L. Shi, Global Planning from Local
Perspective: An Implementation of Observation-based Plan Coordination in
RoboCup Simulation Games, RoboCup 2001: Robot Soccer World Cup V
Presenter: Craig Dean, Paper: MIT Urban Challenge Tech
Report
Presenter: Gautham Anil, Paper: R. Paul
Wiegand, M. Potter, D. Sofge, and W. Spears, ,
A Generalized Graph-Based Method for Engineering Swarm Solutions to Multiagent Problems, Parallel Problem Solving from Nature PPSN IX, 2006
- Apr 17 Presenter: John Reeder, Paper: Yuriy Nevmyvaka, Normative Approach to Market Microstructure Analysis (9.b.iii Pages 163 - 182), 2005
Presenter: Siddharth S.
Somvanshi, Paper: Baldassarre G., Parisi D., Nolfi S., Coordination and Behaviour
Integration in Cooperating Simulated Robots In S. Schaal, A. Ijspeert, A. Billard, S. Vijayakumar, J. Hallam and J-A. Meyer (Eds.), From Animals to Animats 8: Proceedings of the VIII International Conference on Simulation of Adaptive Behavior, pp. 385-394. MIT Press, Cambridge, MA
- Final Project Demos (Wed, Apr 23rd, HEC 111, 1-4pm)
1:00-1:30 Gautham Anil, Siddharth Somvanshi
1:30-1:45 Craig Dean
1:45-2:00 David Lyle
2:00-2:15 Dan deBlasio
2:15-2:45 JT Folsom-Kovarik, Philip Verbancsics
2:45-3:00 Robert Hauser
3:00-3:15 Richard Lum
3:15-3:30 Matt Meighan
3:30-3:45 Bryan Rosander
3:45-4:00 Mikel Rodriguez