A frequentist approach to mapping under uncertainty

8 years 5 months ago
A frequentist approach to mapping under uncertainty
An asynchronous stochastic approximation based (Frequentist) approach is proposed for mapping using noisy mobile sensors under two different scenarios: 1) perfectly known sensor locations and 2) uncertain sensor locations. The frequentist methodology has linear complexity in the map components, is immune to the data association problem and is provably consistent. The frequentist methodology, in conjunction with a Bayesian estimator, is applied to the Simultaneous Localization and Mapping (SLAM) problem of Robotics. Several large maps are estimated using the hybrid Bayesian/ Frequentist scheme and results show that the technique is robust to the computational and performance issues inherent in the purely Bayesian approaches to the problem.
Suman Chakravorty, R. Saha
Added 12 May 2011
Updated 12 May 2011
Type Journal
Year 2011
Authors Suman Chakravorty, R. Saha
Comments (0)