Abstract
Global localization problem is one of the classical and important problems in mobile robot. In this paper, we present an approach to solve robot global localization in indoor environments with grid map. It combines Hough Scan Matching (HSM) and grid localization method to get the initial knowledge of robot's pose quickly. For pose tracking, a scan matching technique called Iterative Closest Point (ICP) is used to amend the robot motion model, this can drastically decreases the uncertainty about the robot's pose in prediction step. Then accurate proposal distribution taking into account recent observation is introduced into particle filters to recover the best estimate of robot trajectories, which seriously reduces number of particles for pose tracking. The proposed approach can globally localize mobile robot fast and accurately. Experiment results carried out with robot data in indoor environments demonstrates the effectiveness of the proposed approach.
Highlights
The problem of localization has attracted immense attention in the robotic literatures
There are mainly three kinds of approaches providing a solution to global localization problem: Extented Kalman Filter (EKF) algorithms (Thrun, S. et al, 2005), Grid localization and Monte
This paper proposes a new approach to solve the global localization problem in indoor environments represented by grid maps
Summary
The problem of localization has attracted immense attention in the robotic literatures. There are mainly three kinds of approaches providing a solution to global localization problem: Extented Kalman Filter (EKF) algorithms (Thrun, S. et al, 2005) , Grid localization and Monte. Grid localization method seems more robust to non‐linearity and arbitrary noise distributions, but it ignores the computational complexity problem, when applied to large scale environments To overcome these limitations, MCL was introduced as an effective solution to solve pose tracking (Dellaert, F. et al, 1999 ; Thrun, S. et al, 2005). The main problem of particle filter approach is their complexity, measured in terms of the number of required particles Reducing this quantity is International Journal of Advanced Robotic Systems, Vol 8, No 1 (2011) ISSN 1729-8806, pp 21-28 www.intechweb.org www.intechopen.com one of the major challenges of this family of algorithms (Grisetti, G., 2007).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have