HyperNEAT controlled robots learn how to drive on roads in simulated environment

Authors:
Jan Drchal;Jan Koutník;Miroslav Šnorek
Affiliations:
Computational Intelligence Group, Department of Computer Science and Engineering, Faculty of Electrical Engineering, Czech Technical University, Prague;Computational Intelligence Group, Department of Computer Science and Engineering, Faculty of Electrical Engineering, Czech Technical University, Prague;Computational Intelligence Group, Department of Computer Science and Engineering, Faculty of Electrical Engineering, Czech Technical University, Prague
Venue:
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Year:
2009

Citing 8
Cited 8

Evolving neural networks through augmenting topologies

Evolutionary Computation
Training Recurrent Networks by Evolino

Neural Computation
A novel generative encoding for exploiting neural network sensor and output geometry

Proceedings of the 9th annual conference on Genetic and evolutionary computation
Generating large-scale neural networks through discovering geometric regularities

Proceedings of the 9th annual conference on Genetic and evolutionary computation
Generative encoding for multiagent learning

Proceedings of the 10th annual conference on Genetic and evolutionary computation
Evolvability of Neuromodulated Learning for Robots

LAB-RS '08 Proceedings of the 2008 ECSIS Symposium on Learning and Adaptive Behaviors for Robotic Systems
Evolution of altruistic robots

WCCI'08 Proceedings of the 2008 IEEE world conference on Computational intelligence: research frontiers
Neuroevolution with analog genetic encoding

PPSN'06 Proceedings of the 9th international conference on Parallel Problem Solving from Nature

Combining Multiple Inputs in HyperNEAT Mobile Agent Controller

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
NEAT in HyperNEAT substituted with genetic programming

ICANNGA'09 Proceedings of the 9th international conference on Adaptive and natural computing algorithms
Evolving the placement and density of neurons in the hyperneat substrate

Proceedings of the 12th annual conference on Genetic and evolutionary computation
Evolving neural fields for problems with large input and output spaces

Neural Networks
Distance measures for HyperGP with fitness sharing

Proceedings of the 14th annual conference on Genetic and evolutionary computation
An enhanced hypercube-based encoding for evolving the placement, density, and connectivity of neurons

Artificial Life
Generating diverse behaviors of evolutionary robots with speciation for theory of mind

SEAL'12 Proceedings of the 9th international conference on Simulated Evolution and Learning
Critical factors in the performance of hyperNEAT

Proceedings of the 15th annual conference on Genetic and evolutionary computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we describe simulation of autonomous robots controlled by recurrent neural networks, which are evolved through indirect encoding using HyperNEAT algorithm. The robots utilize 180 degree wide sensor array. Thanks to the scalability of the neural network generated by HyperNEAT, the sensor array can have various resolution. This would allow to use camera as an input for neural network controller used in real robot. The robots were simulated using software simulation environment. In the experiments the robots were trained to drive with imaximum average speed. Such fitness forces them to learn how to drive on roads and avoid collisions. Evolved neural networks show excellent scalability. Scaling of the sensory input breaks performance of the robots, which should be gained back with re-training of the robot with a different sensory input resolution.