Abstract | ||
---|---|---|
We evolve a neural network controller for a boat that learns to maintain a given bearing and range with respect to a moving target in the Lagoon 3D game environment. Simulating realistic physics makes maneuvering boats difficult and thus makes an evolutionary approach an attractive alternative to hand coded methods. We evolve the weights of simple recurrent neural networks trained with a fitness function designed to combine multiple fitness objectives based on speed, heading, and position to create a robust maintain station behavior. Results with an enforced subpopulation neural-evolution genetic algorithm indicate that we can consistently evolve robust maintain controllers for realistically simulated boats in Lagoon. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/CEC.2008.4631248 | Evolutionary Computation, 2008. CEC 2008. |
Keywords | Field | DocType |
boats,computer games,control engineering computing,genetic algorithms,neurocontrollers,robust control,Lagoon 3D game,evolutionary approach,fitness function,moving target,multiple fitness objectives,neural network controller,neuro-evolving maintain-station behavior,recurrent neural networks,simulated boats,subpopulation neural-evolution genetic algorithm | Distance measurement,Control theory,Computer science,Recurrent neural network,Robustness (computer science),Fitness function,Artificial intelligence,Neural network controller,Robust control,Artificial neural network,Machine learning,Genetic algorithm | Conference |
ISBN | Citations | PageRank |
978-1-4244-1823-7 | 0 | 0.34 |
References | Authors | |
5 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nathan A. Penrod | 1 | 0 | 0.68 |
David Carr | 2 | 0 | 0.34 |
Sushil J. Louis | 3 | 541 | 93.79 |
Bobby D. Bryant | 4 | 58 | 6.70 |