1. FUZZy TimeE-critical Spatio-Temporal Pong (FUZZ-TEST Pong)
Brandon Cook
Faculty Mentor: Kelly Cohen
University of Cincinnati, Department of Aerospace Engineering
(Fuzzy Logic Inferencing Pong)
Objectives
Methods
Results
Achievements
Create a doubles PONG game with:
Advanced ball control
Rotation of paddles
2-on-2 gameplay
Fuzzy Logic based opponents
Create Simulation
Observe Human Collaboration: Tennis Matches
Create Fuzzy Inference System
Models Human-Like Behavior
Beta Testing
Compile Results
Added degree of freedom to PONG
New bounce capabilities (angel of incidence)
Improved Boundary Conditions
Rotate/Translate Simultaneously
Humans vs. Robots Capable
Robots vs. Robots Capable
Strategy
Larger paddle rotations: more offensive
Introduction
Fuzzy Logic
Allows classification of variables for more human-like reasoning
Common terms:
Inputs
Rules
Outputs
Membership Function
Fuzzy Inference System (FIS)
Figure 1: The light spectrum is fuzzy, as is nature.
Fuzzy Reasoning
Example of how Fuzzy Paddles assign discrete outputs
Figure 5: Breakdown of Fuzzy Paddle (Offensive vs. Defensive)
Back up partner: more defensive
Figure 7: Added Rotational Degree of Freedom
Conclusion
Fuzzy logic is an effective tool for:
Emulating human-like reasoning
Collaborative linguistic reasoning between autonomous robots
Adapting to situations where linear model controllers are not feasible
Figure 3: Fuzzy Logic Reasoning
Figure 6: Fuzzy Team Defensive Strategy (Red Team)
PONG
Classic arcade game created by Atari
Gameplay Objective: Score by hitting the ball past opponent
First team to 21 points wins
Creates spatio-temporal environment
Fuzzy Inference System (FIS)
Example of strategy FIS
Future Work
Beta Testing
Adding varying degrees of difficulty selections
Easy, Medium, Hard
Add trickery components to Intelligent Team
Additional inputs and modified outputs to take opponents current rotation in to account
Implement collaborative robotics into real world, 3-dimensional, simulation (e.g. disaster relief situations)
Table 1: Doubles Robot Team vs. Robot Team Results
Simulation proved Fuzzy teams are evenly matched
Each volley lasted nearly 5 minutes
Logic proved effective at :
Intercepting ball trajectory
Hitting ball towards open court positions
Figure 2: Doubles Pong Setup
Red Team
Blue Team
Winner
Robots vs. Robots 15
DRAW
Robots
Humans
Winner
Robots vs. Humans 42 2
ROBOTS
Red Team
Blue Team
Winner
Robots vs. Robots 15
DRAW
Red Team
Blue Team
Winner
Robots vs. Robots 15
DRAW
Figure 5. Real-World Collaborative Robots (i.e. Naos)
Table 2: Doubles Human Team vs. Robot Team Results
Figure 4: Fuzzy Inference System (FIS) File
Acknowledgements
References
Match #1 (first to 21 points)
Robots defeated Humans 21 to 2
Only scores on Robots due to small gameplay glitches (e.g. ball traveling through paddle)
Match #2 (first to 21 points)
Robots defeated Humans 21 to 0
Proved effectiveness of Fuzzy Logic Paddles
Sponsored by: The National Science Foundation
Grand ID No.: DUE
Academic Year – Research Experience for Undergraudates (AY-REU) Program
Sophia Mitchell
Original FLIP Simulation Creator (only translation)
Depending on Inputs:
Unoccupied regions of the court (Open)
Game Strategy: offensive/defensive (Game)
Current fuzzy paddle location
Assign discrete output strategy: Where to hit the ball (Strategy)
Kosko, Bart. Fuzzy Thinking: The New Science of Fuzzy Logic. New York: Hyperion, Print.
Mendel, Jerry M., and Dongrui Wu. "Interval Type-2 Fuzzy Sets." Perceptual Computing: Aiding People in Making Subjective Judgments. Piscataway, NJ: IEEE, Print.
2010 Australian Open – Men’s Doubles Final Bob & Mike Bryan vs. Nestor & Zimonjic [video]. Retrieved June, 2011, from youtube. com/watch?v=0C-pEt8d9ts
Barker, S. , Sabo, C. , and Cohen, K. , "Intelligent Algorithms for MAZE Exploration and Exploitation", AIAA Conference, St. Louis, MO, March 29-31, 2011, AIAA Paper
D. Buckingham, Dave’s MATLAB Pong, University of Vermont, Matlab Central, 2011
Federer & Mirka vs. Hewitt & Molik – part 3 [video]. Retrieved June, 2011, from youtube. com/watch?v=b0BAh_pRRTo
Sng H. L. , Sen Gupta and C. H. Messom, Strategy for Collaboration in Robot Soccer, IEEE International Workshop on Electronic Design, Test and Applications (DELTA), 2002
B. Innocenti, B. Lopez and J. Salvi, A Multi-Agent Architecture with Cooperative Fuzzy Control for a Mobile Robot, Robotics and Autonomous Systems, vol. 55, pp , 2007
D. Matko, G. Klancar and M. Lepetic, A Tool for the Analysis of Robot Soccer Game, International Journal of Control, Automation and Systems, vol. 1, pp – 228, 2003