Relative positioning for team robot navigation

@article{citeulike:2767051, abstract = {Abstract\ \ The research presented in this paper approaches the issue of robot team navigation using relative positioning. With this approach each robot is equipped with sensors that allow it to independently estimate the relative direction of an assigned leader. Acoustic sensor systems are used and were seen to work very effectively in environments where datum relative positioning systems (such as GPS or acoustic transponders) are typically ineffective. While acoustic sensors provide distinct advantages, the variability of the acoustic environment presents significant control challenges. To address this challenge, directional control of the robot was accomplished with a feed forward neural network trained using a genetic algorithm, and a new approach to training using recent memories was successfully implemented. The design of this controller is presented and its performance is compared with more traditional classic logic and behavior controllers.}, author = {Mcdowell, Patrick and Bourgeois, Brian and Mcdowell, Pamela and Iyengar, S. and Chen, Jianhua }, citeulike-article-id = {2767051}, journal = {Autonomous Robots}, keywords = {robots, swarm}, month = {February}, number = {2}, pages = {133--148}, posted-at = {2008-05-07 18:31:14}, priority = {2}, title = {Relative positioning for team robot navigation}, url = {http://dx.doi.org/10.1007/s10514-006-9021-8}, volume = {22}, year = {2007} }

TY - JOUR ID - citeulike:2767051 L3 - citeulike-article-id:2767051 TI - Relative positioning for team robot navigation JF - Autonomous Robots VL - 22 IS - 2 SP - 133 EP - 148 N2 - Abstract  The research presented in this paper approaches the issue of robot team navigation using relative positioning. With this approach each robot is equipped with sensors that allow it to independently estimate the relative direction of an assigned leader. Acoustic sensor systems are used and were seen to work very effectively in environments where datum relative positioning systems (such as GPS or acoustic transponders) are typically ineffective. While acoustic sensors provide distinct advantages, the variability of the acoustic environment presents significant control challenges. To address this challenge, directional control of the robot was accomplished with a feed forward neural network trained using a genetic algorithm, and a new approach to training using recent memories was successfully implemented. The design of this controller is presented and its performance is compared with more traditional classic logic and behavior controllers. KW - robots KW - swarm AU - Mcdowell, Patrick AU - Bourgeois, Brian AU - Mcdowell, Pamela AU - Iyengar, S AU - Chen, Jianhua PY - 2007/02/14/ UR - http://dx.doi.org/10.1007/s10514-006-9021-8 ER -