Entropy based robust estimator and its application to line-based mapping
Robotics and Autonomous Systems
An Entropy Optimization Strategy for Simultaneous Localization and Mapping
Journal of Intelligent and Robotic Systems
| Hi-index | 0.00 |
In this paper we propose to continue in the same researchline initiated by Pronzato and Thierry [A minimum-entropy estimator for regression problems with unknown distribution of observation errors],[Entropy minimization of parameter estimator with unknown distribution of observation erros], recent works inspired in the minimum-entropy estimationhave been published by De la Rosa and Fleury [On the Kernel selection for Minimum-Entropy estimation],[Minimum-Entropy, pdf approximation and Kernel selection for measurement estimation] in the instrumentation framework. An statistical modelhas been established to represent some instrumental signals,similarly, some limited hypothesis over such a modelhave been made. In fact, we assume limited knowledge ofthe noise or external perturbations distribution that interactinto the system. The use of robust estimators in such situationsis very helpful, since the real systems are always exposedto continuous perturbations of unknown nature. Someapplications where the last is true are: medical instrumentation,industrial processes, in telecommunications amongothers. Some results of new minimum-entropy estimatorsfor linear and nonlinear models are presented, such resultscomplement those presented by Pronzato and Thierry.