Abstract | ||
---|---|---|
In this paper we present neuro-evolution of neural network controllers for mobile agents in a simulated environment. The controller is obtained through evolution of hypercube encoded weights of recurrent neural networks (HyperNEAT). The simulated agent's goal is to find a target in a shortest time interval. The generated neural network processes three different inputs --- surface quality, obstacles and distance to the target. A behavior emerged in agents features ability of driving on roads, obstacle avoidance and provides an efficient way of the target search. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-04277-5_78 | ICANN (2) |
Keywords | Field | DocType |
simulated agent,neural network,obstacle avoidance,target search,combining multiple inputs,neural network controller,different input,hypercube encoded weight,mobile agent,recurrent neural network,hyperneat mobile agent controller,simulated environment | Obstacle avoidance,Control theory,Computer science,Mobile agent,Recurrent neural network,HyperNEAT,Time delay neural network,Artificial intelligence,Artificial neural network,Hypercube,Machine learning | Conference |
Volume | ISSN | Citations |
5769 | 0302-9743 | 2 |
PageRank | References | Authors |
0.37 | 12 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jan Drchal | 1 | 26 | 3.68 |
Ondrej Kapral | 2 | 2 | 0.37 |
Jan Koutník | 3 | 552 | 36.31 |
Miroslav Šnorek | 4 | 49 | 6.41 |