SLIDE 1
Bradley University
GENETIC PROGRAMMING OF AUTONOMOUS AGENTS
Scott O’Dell Advisors Dr Joel Schipper Dr Arnold Patton
1
GPAA
- Genetic Programming (GP)
- Project Description
- Results
- Conclusion
2
GENETIC PROGRAMMING OF AUTONOMOUS AGENTS Scott ODell Advisors Dr - - PowerPoint PPT Presentation
GENETIC PROGRAMMING OF AUTONOMOUS AGENTS Scott ODell Advisors Dr - - PowerPoint PPT Presentation
GENETIC PROGRAMMING OF AUTONOMOUS AGENTS Scott ODell Advisors Dr Joel Schipper Dr Arnold Patton Bradley University 1 GPAA Genetic Programming (GP) Project Description Results Conclusion 2 GPAA Genetic Programming
SLIDE 2
SLIDE 3
GPAA
- Genetic Programming (GP)
- Project Description
- Results
- Conclusion
3
SLIDE 4
PRACTICAL GENETIC PROGRAMMING
SLIDE 5
INTRO TO GP
- Machine intelligence
- Theory of evolution
- What you want: fitness function
- How to get it: primitive set
- GP does the details
5
SLIDE 6
INTRO TO GP
Simulation of Evolution
6
SLIDE 7
GPAA
- Genetic Programming (GP)
- Project Description
- Results
- Conclusion
7
SLIDE 8
TRADITIONAL METHODS
- 1. Grid Domain
- Movement is unrealistic
- Space is warped
- 2. Complex Primitive Set
- Less creative
- More work for designer
SLIDE 9
PERIMETER MAINTENANCE
- Military defense application
- Intrusion detection
- Spatial reasoning
SLIDE 10
SOFTWARE
- GP framework and simulator
- Written for project
- Ruby
- quick development
- easy interfacing
10
SLIDE 11
GPAA
- Genetic Programming (GP)
- Project Description
- Results
- Conclusion
11
SLIDE 12
GRID-BASED SIMULATIONS
- Verify software operation
- Develop fitness function
- 4 guards
- Guard sensor range: 4 units
- Perimeter around base: 7 units
12
SLIDE 13
GRID-BASED SIMULATIONS
13
SLIDE 14
GRID-BASED SIMULATIONS
- Primitive Set
- Forward, Left, Right
- Distance from base
- Arithmetic: +, -, *, /, %
- if (a > b) then (c) else (d)
14
SLIDE 15
GRID-BASED SIMULATIONS
- Fitness Function Simulation
- Enemies randomly start at edge of grid
- Move directly to base
- Removed if guards sense them
- Removed in base perimeter
- Fitness Score = Number of enemies detected
15
SLIDE 16
HOMOGENOUS TEAM
- All guards have
same controller
- Optimal result
16
. . . . * . . * * . . * ^ * . * * * . . * . * . . * . . * . * . . * . . * . . * . . * . . * < . x . > * . . * . . * . . * . . * . . * . * . . * . . * . * . . * * * . * v * . . * * . . * . . . .
SLIDE 17
CO-EVOLUTION OF ENEMIES
- Homogenous Guards
- Base Perimeter: 7
17
SLIDE 18
GRID BASED SIMULATIONS
- Software works
- Exploits grid domain
- Results are not practical
18
SLIDE 19
CONTINUOUS SIMULATIONS
- Eliminates warping
- Realistic movement
- 4 guards
- Guard sensor range: 4 units
- Perimeter around base: 7 units
19
SLIDE 20
CONTINUOUS SIMULATIONS
- Primitive Set
- Base and Direction vector
- Store and Recall vectors
- Vector arithmetic: +, -, *
- Conditionals: vector magnitude and angle
- Controller returns vector; determines heading
20
SLIDE 21
HOMOGENOUS TEAM
21
SLIDE 22
CO-EVOLUTION OF ENEMIES
22
SLIDE 23
CONTINUOUS SIMULATIONS
- Successful strategies with vector arithmetic
- Realistic autonomous agent movement
- Unrealistically precise maneuvers
23
SLIDE 24
UNCERTAIN SIMULATIONS
- Generic noise to deal with uncertainty
- Develop cautious agents
24
SLIDE 25
HOMOGENOUS TEAM
25
SLIDE 26
NOISY SIMULATIONS
- GP can produce robust control programs
- Guards more cautious
- Basic strategy unchanged
26
SLIDE 27
GPAA
- Genetic Programming (GP)
- Project Description
- Results
- Conclusion
27
SLIDE 28
PRACTICAL GENETIC PROGRAMMING
SLIDE 29
FUTURE WORK
- Autonomous agent platform
- Accurately model noise
- Test on physical agent
29
SLIDE 30
QUESTIONS
SLIDE 31
SLIDE 32
NOISY SIMULATIONS
- Generic noise to deal with uncertainty
- Gaussian error added to sensors and movement
- Sensor: constant variance = size of guard
- Movement: variance = 1/10th of ideal movement
32