Optimal Control for Simultaneous Localisation and Mapping Problems in Indoor Environments with Stereo Vision

Abstract

This paper proposes a optimal control method for simultaneous localisation and mapping (SLAM) in an indoor environment using stereo vision. Specially designed artificial landmarks distributed in the environment are observed and extracted from a camera image. The disparity map obtained from the stereo vision system is used to obtain the ranges to these landmarks. The main contribution of the paper is the formulation of the mathematical framework for SLAM for a robot moving on a planar surface among landmarks distributed in three dimensional space. The paper also presents the results of experiments for optimal control conducted using a Pioneer robot and a Triclops stereo vision system. It is demonstrated that accurate robot and feature locations can be obtained using the proposed technique.

Neural network based stereo matching algorithm utilizing vertical disparity

“…Step 4: The crossover operator is applied to two parents, p 1 and p 2 through tournament selection from P. Then two children are produced in an intermediate population P' as following:…”

“…The stereo vision has been developed to the robot system for many applications such as localization [1] and navigation [2]. It can be used to determine the depth of an object or a point in a scene based on the disparity [3], [4].…”

Experimental comparison of 3D vision sensors for mobile robot localization for industrial application: Stereo-camera and RGB-D sensor

“…In [10] stereo vision is used for localization and SLAM (Simultaneous Localization and Mapping), using a stereo-camera that acquires the position of known landmarks, in indoor environment. Conversely, the work in [11] presents an outdoor visual localization application, that exploits an omni-directional camera to acquire the relative positions of some features of the environment, namely edges.…”