TY - GEN

T1 - A PSO-based mobile sensor network for odor source localization in dynamic environment

T2 - 2006 IEEE Congress on Evolutionary Computation, CEC 2006

AU - Jatmiko, Wisnu

AU - Sekiyama, Kosuke

AU - Fukuda, Toshio

PY - 2006/12/1

Y1 - 2006/12/1

N2 - This paper presents a problem of odor source localization in a dynamic environment, which means the odor distribution is changing over time. Most work on chemical sensing with mobile robots assume an experimental setup that minimizes the influence of turbulent transport by either minimizing the source-to-sensor distance in trail following or by assuming a strong unidirectional air stream in the environment, including our previous work. However, not much attention has been paid to the natural environment problem. Modification Particle Swarm Optimization is a well-known algorithm, which can continuously track a changing optimum over time. PSO can be improved or adapted by incorporating the change detection and responding mechanisms for solving dynamic problems. Charged PSO, which is another extension of the PSO, has also been applied to solve dynamic problems. Odor source localization is an interesting application in dynamic problems. We will adopt two types of PSO modification concepts to develop a new algorithm in order to control autonomous vehicles. Before applying the algorithm for real implementation, some important hardware conditions must be considered. Firstly, to reduce the possibility of robots leaving the search space, a limit to the value of velocity vector is needed. The value of vector velocity can be clamped to the range [-V max, V max]; in our case for the MK-01 Robot, the maximum velocity is 0.05 m/s. Secondly, in the standard PSO algorithm there is no collision avoidance mechanism. To avoid the collision among robot we add some collision avoidance functions. Finally, we also add some sensor noise, delay and threshold value to model the sensor response. Then we develop odor localization algorithm, and simulations to show that the new approach can solve such dynamic environment problems.

AB - This paper presents a problem of odor source localization in a dynamic environment, which means the odor distribution is changing over time. Most work on chemical sensing with mobile robots assume an experimental setup that minimizes the influence of turbulent transport by either minimizing the source-to-sensor distance in trail following or by assuming a strong unidirectional air stream in the environment, including our previous work. However, not much attention has been paid to the natural environment problem. Modification Particle Swarm Optimization is a well-known algorithm, which can continuously track a changing optimum over time. PSO can be improved or adapted by incorporating the change detection and responding mechanisms for solving dynamic problems. Charged PSO, which is another extension of the PSO, has also been applied to solve dynamic problems. Odor source localization is an interesting application in dynamic problems. We will adopt two types of PSO modification concepts to develop a new algorithm in order to control autonomous vehicles. Before applying the algorithm for real implementation, some important hardware conditions must be considered. Firstly, to reduce the possibility of robots leaving the search space, a limit to the value of velocity vector is needed. The value of vector velocity can be clamped to the range [-V max, V max]; in our case for the MK-01 Robot, the maximum velocity is 0.05 m/s. Secondly, in the standard PSO algorithm there is no collision avoidance mechanism. To avoid the collision among robot we add some collision avoidance functions. Finally, we also add some sensor noise, delay and threshold value to model the sensor response. Then we develop odor localization algorithm, and simulations to show that the new approach can solve such dynamic environment problems.

UR - http://www.scopus.com/inward/record.url?scp=34547238433&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:34547238433

SN - 0780394879

SN - 9780780394872

T3 - 2006 IEEE Congress on Evolutionary Computation, CEC 2006

SP - 1036

EP - 1043

BT - 2006 IEEE Congress on Evolutionary Computation, CEC 2006

Y2 - 16 July 2006 through 21 July 2006

ER -