Active Sensing approach for Range-Only SLAM using Gaussian Mixture Models.
F. Caballero, L Merino and A. Ollero. Active Sensing approach for Range-Only SLAM using Gaussian Mixture Models. Proceedings of the ROBOT 2011. 28-29 November, 2011. Sevilla (Spain)
Radio signal-based localization and mapping is becoming more interesting as applications involving the collaboration between robots and static wireless devices are more common. Under certain assumptions, the problem is basically equivalent to the range-only localization and mapping. This paper presents a method for mapping with a mobile robot the position of a set of nodes using radio signal measurements. It uses a Gaussian Mixtures Model (GMM) to solve the undelayed initialization of the position of the wireless nodes, characterized as a multiple hypotheses problem. The paper shows how the approach can be integrated within a Kalman Filter in such a way that information can be used in the filter since the very first measurement. The paper presents results obtained with experimental data involving one mobile robot and a set of range sensors. Moreover, the paper extends the method to consider active sensing strategies in order to better map the nodes. Entropy variation is used as a measurement of information gain, and allows to prioritize control actions of the robot. However, as there is no analytical expression for the entropy of a GMM, upper bounds of the entropy, for which close form computation is possible, are used instead. The paper describes simulations and experiments that show the feasibility of the approach.