This paper presents a method to estimate and correct the positions of an indoor mobile robot. Scene matching is based on geometric hashing[9, 101. An optimization method[l2] of maximizing cross-correlation of image regions is used to estimation correction. We assume that the robot is equipped with two or more video cameras, a 2 0 laser range finder and an odometry system. The 3 0 CAD model of i...

In this paper, we present an idea for a sparse approach to calculate camera poses from RGB images and laser distance measurements to perform subsequent facade reconstruction. The core idea is to guide the image recording process by choosing distinctive features with the laser range finder, e.g. building or window corners. From these distinctive features, we can establish correspondences between...

NASA’s space-borne nulling interferometer (the Terrestrial Planet Finder – TPF) will look for the traces of early life in the infrared spectra of extrasolar planets, beginning in roughly 2010. We point out that this instrument will also be sensitive to deliberate laser transmissions from a technologically advanced civilization. A kilowatt-class infrared laser with a 10-m beam director would pro...

We present an intuitive method to generate visually convincing 3D models of indoor environments from data collected by a single 2D laser range finder and a color camera. The 2D map created from the laser data forms the basis of a line model which serves as floor plan for the 3D model. The walls of this model are textured using the color images. In contrast to panoramic images where the resoluti...

This paper presents a 3-D local map building approach for real-time obstacle avoidance using visually-recognized laser patterns. Precise estimate of the local map provides essential information for navigation and control of a mobile robot in unknown environments. Existing navigation and control approaches typically require expensive sensing devices, such as sonar or laser range finder. In this ...

In this study, localization of a mobile robot is accomplished using laser range finder, compass and natural landmark. Corners in a room are used as natural landmarks. It is assumed that mobile robot is positioned to sense corners and there is no other corner like objects in the environment. Once a corner is sensed, the position of this corner is determined using the robot heading which is indic...

I present methods for using neural-networks to recognize sensor views from a laser range-finder for robotic navigation. First, I show that a simple back-propagation network can form a highly accurate recognizer when supervised training data is available. Then I investigate the use of the “Chorus of Prototypes” model for representing sensor views suitably for unsupervised exploration. Some probl...

This paper presents a new 3D scene analysis system that automatically reconstructs the 3D model of real-world scenes from multiple range images acquired by a laser range finder on board of a mobile robot. The reconstruction is achieved through an integrated procedure including range data acquisition, geometrical feature extraction, planning the next view, registration and integration of multipl...

In this paper we present a fast approach to range image segmentation. The segmentation results are intended to serve as input to the perception system of a domestic service robot. In the first step “ghost points” at depth discontinuities are identified. This is followed by extracting step and roof edges. Planar patches are detected with a focus on horizontal and vertical planar structures. Fina...