Download presentation
Presentation is loading. Please wait.
1
www.kovan.ceng.metu.edu.tr Parallelized Evolution System Onur Soysal, Erkin Bahçeci Erol Şahin Dept. of Computer Engineering Middle East Technical University http://www.kovan.ceng.metu.edu.tr ISCIS’03 04/11/2003
2
ISCIS’03www.kovan.ceng.metu.edu.tr Evolutionary Methods Simulation of Natural Evolution Using evolution mechanisms to solve optimization problems Survival of the fittest........... Generation n Chrom.1: 0101011001... Chrom.2: 1100110111............ Generation n+1 Select Reproduce Mutate........... Chrom.1: 1010001110... Chrom.2: 0011110101............ Population n Population n+1
3
ISCIS’03www.kovan.ceng.metu.edu.tr Genetic Algorithms Encoding Binary representation Stochastic search Guided by measure of fitness Problem-specific fitness function Genetic operators Mutation Crossover
4
ISCIS’03www.kovan.ceng.metu.edu.tr Evolutionary Robotics Motivation Controller: Sensor-actuator relationship Difficult to design manually in nontrivial tasks To be in the shoes of a robot? Solutions of evolutionary robotics Evolving controllers SensorsActuators Controller ???
5
ISCIS’03www.kovan.ceng.metu.edu.tr Genotype Phenotype: Generic Controller 010101 100111... Sensor data Actuator outputs Convert to controller parameters Use the controller in robots Controller Chromosome
6
ISCIS’03www.kovan.ceng.metu.edu.tr Genotype Phenotype: Neural Network Controller 010101 100111... Sensor data Actuator outputs Convert to neural network weights Use the neural network to control robots Chromosome
7
ISCIS’03www.kovan.ceng.metu.edu.tr Fitness Evaluation Use controller on physical robots on simulated robots Observe behavior Calculate fitness value Repeat for each generation for each chromosome
8
ISCIS’03www.kovan.ceng.metu.edu.tr Physics Based Simulation Importance of realistic simulations Pros Much faster runtime compared to physical implementation Behavioral similarity to physical robots Realistic interactions Cons High processing demand! Example libraries: ODE, Vortex, Havok
9
ISCIS’03www.kovan.ceng.metu.edu.tr Single Machine Limitations Computation required Solving Ordinary Differential Equations Increasing complexity with more collisions Time estimates for single computer Order of minutes for a single evaluation For 100 chromosomes and 100 generations Total time > a week on a single machine
10
ISCIS’03www.kovan.ceng.metu.edu.tr Cluster Computing Cheap alternative to supercomputers Large-grained problems Example application SETI@home: Search for Extraterrestrial Intelligence at home
11
ISCIS’03www.kovan.ceng.metu.edu.tr Cluster Computing Solution to Evolutionary Robotics Fitness evaluations dominate computation time Fitness evaluations are independent Master-Slave model Master: GA Slaves: Fitness evaluations
12
ISCIS’03www.kovan.ceng.metu.edu.tr Parallel Evolution System (PES) Parallel Genetic Algorithm library Distributed fitness evaluation Central genetic algorithm Supports interoperability of multiple platforms
13
ISCIS’03www.kovan.ceng.metu.edu.tr PES Architecture Server: GA Clients: Fitness evaluation PES-C Client Application PES-S Server Application
14
ISCIS’03www.kovan.ceng.metu.edu.tr PES Communication Model PES Network Adapter PES-C PES Network Adapter PES-S Ping mechanism Task and result packets ping ping reply task result
15
ISCIS’03www.kovan.ceng.metu.edu.tr PES-S Architecture Server Application GA Engine Task Manager PES-S Task generator Best solutions Network Adapter
16
ISCIS’03www.kovan.ceng.metu.edu.tr PES-C Architecture Client Application Network Adapter Task Fitness PES-C
17
ISCIS’03www.kovan.ceng.metu.edu.tr PES Usage: Server Server Code #include int main() { PES_INIT(); for each generation { PES_EVAL_INDIVIDUALS(); PES_NEXT_GENERATION(); } }
18
ISCIS’03www.kovan.ceng.metu.edu.tr PES Usage: Client Client Code #include int main() { PES_INIT(); while true { RECEIVE_TASK(); EVAL_TASK(); SEND_RESULT(); } }
19
ISCIS’03www.kovan.ceng.metu.edu.tr PES Features Multi-platform support Linux and Windows via PVM Improved fault tolerance Ping mechanism to detect non-responding clients Supplies GA facilities Built-in crossover, mutation and selection functions Simplified usage Automatic task distribution / fitness collection Single line for evaluating fitness of whole population Basic load balancing
20
ISCIS’03www.kovan.ceng.metu.edu.tr Our Application Task: Aggregation Getting 10 robots as close as possible Minimal sensors and communication Modified single layer NN for control No memory/learning No world knowledge Probabilistic inputs Fitness evaluation 2000 steps of simulation Total distance as fitness measure 1 2 3 1 3 2 312 312 R
21
ISCIS’03www.kovan.ceng.metu.edu.tr Sample Application Results
22
ISCIS’03www.kovan.ceng.metu.edu.tr Processor Load Balancing Dynamic simulation Varying number of collisions Varying task complexity Varying processor load Diamonds: tasks Solid lines: Start of new generation
23
ISCIS’03www.kovan.ceng.metu.edu.tr Fault Tolerance Processor 2 fails Detected at ping at 15 th sec Task restart at 19 th sec Red lines: Ping Blue lines: Generation Numbers: Task index
24
ISCIS’03www.kovan.ceng.metu.edu.tr Efficiency & Speedup
25
ISCIS’03www.kovan.ceng.metu.edu.tr Discussions & Future Work Generation gap Asynchronous reproduction Dynamic host list Progress monitor Extension to the Internet
26
ISCIS’03www.kovan.ceng.metu.edu.tr PES Sources & Documentation Source distribution under Gnu Public License (GPL) User manual Functional reference Sample applications http://www.kovan.ceng.metu.edu.tr/software/PES
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.