A Comparative Study of Neural Networks Based Learning Strategies for Collective Robotic Search Problem
One important application of mobile robots is searching a geographical region to locate the origin of a specific sensible phenomenon. A variety of optimization algorithms can be employed to locate the target source which has the maximum intensity of the distribution of illumination function. It is very important to evaluate the performance of those optimization algorithms so that the researchers can adopt the most appropriate optimization approach to save a lot of execution time and cost of both collective robots and human beings. In this paper, we provide three different neural network algorithms: steepest ascent algorithm, combined gradients algorithm and stochastic optimization algorithm to solve the collective robotics search problem. Experiments with different pair of number of sources and robots were carried out to investigate the effect of sources size and team size on the task performance, as well as the risk of mission failure. The experimental results showed that the performance of steepest ascent method is better than that of combined gradient method, while the stochastic optimization method is better than steepest ascent method.
N. Zhang et al., "A Comparative Study of Neural Networks Based Learning Strategies for Collective Robotic Search Problem," Proceedings of SPIE - The International Society for Optical Engineering, vol. 4390, pp. 224-235, SPIE--The International Society for Optical Engineering, Jan 2001.
The definitive version is available at https://doi.org/10.1117/12.421174
SPIE Vol. 4390: Applications and Science of Computational Intelligence IV (2001: Apr. 17-18, Orlando, FL)
Electrical and Computer Engineering
Engineering Management and Systems Engineering
International Standard Serial Number (ISSN)
Article - Conference proceedings
© 2001 SPIE--The International Society for Optical Engineering, All rights reserved.