Estimating the absolute position of a mobile robot using position probability grids
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2
A tutorial on particle filters for online nonlinear/non-GaussianBayesian tracking
IEEE Transactions on Signal Processing
Locating and tracking multiple dynamic optima by a particle swarm model using speciation
IEEE Transactions on Evolutionary Computation
A PSO-based algorithm designed for a swarm of mobile robots
Structural and Multidisciplinary Optimization
| Hi-index | 0.00 |
Achieving robot autonomy is a fundamental objective in Mobile Robotics. However in order to realize this goal, a robot must be aware of its location within an environment. Therefore, the localization problem (i.e.,the problem of determining robot pose relative to a map of its environment) must be addressed. This paper proposes a new biology-inspired approach to this problem. It takes advantage of models of species reproduction to provide a suitable framework for maintaining the multi-hypothesis. In addition, various strategies to track robot pose are proposed and investigated through statistical comparisons.The Bacterial Colony Growth Algorithm (BCGA) provides two different levels of modeling: a background level that carries on the multi-hypothesis and a foreground level that identifies the best hypotheses according to an exchangeable strategy. Experiments, carried out on the robot ATRV-Jr manufactured by iRobot, show the effectiveness of the proposed BCGA.