We present a knowledge-based system for automatic 3D building reconstruction from aerial images. Our approach relies on combining pairs of stereo images with 2D GIS map and domain knowledge. Since most buildings can be described as aggregation of simple building types, the domain knowledge is represented in a building library containing building primitives (flat, gable, and hip roof building). ...

In this paper, we describe a 3D modeling program called RMBL3D, Realistic Maps Built like Legos, which manipulates the architectural repetition in building structures to produce realistic 3D models. This paper details the features and aspects of the RMBL3D program and tests the viability of using 3D objects as building blocks to generate a virtual map. RMBL3D is designed to be the visualization...

ÐAn active approach to sensing can provide the focused measurement capability over a wide field of view which allows correctly formulated Simultaneous Localization and Map-Building (SLAM) to be implemented with vision, permitting repeatable longterm localization using only naturally occurring, automatically-detected features. In this paper, we present the first example of a general system for a...

Mobile robot’s full autonomy widens their range of applicability. In this context, it is essential that a mobile robot is able to construct its own map based on sensors data readings, which are the only means the robot has to interact with its surroundings. Thus, map building, path planning, obstacle avoidance, and control are crucial in achieving full autonomy. Map building shall be carried ou...

An online map building evolutionary algorithm is proposed using multi-agent mobile robots with odometric uncertainty. The control algorithm for map building in each robot is identical and trained by online evolutionary algorithm (EA). Each robot has configuration uncertainty which increases as it moves, and it perceives the surrounding environment information by the limited range sensors. It co...

In this paper, we describe a 3D modeling program called RMBL3D, Realistic Maps Built like Legos, which manipulates architectural repetition in building structures to produce realistic 3D models of environments. This paper details the features and aspects of the RMBL3D program and tests the viability of using 3D objects as building blocks to build a virtual map. The program takes in a descriptio...

This paper analyzes the consistency of the classical extended Kalman filter (EKF) solution to the simultaneous localization and map building (SLAM) problem. Our results show that in large environments the map quickly becomes inconsistent due to linearization errors. We propose a new EKF-based SLAM algorithm, robocentric mapping, that greatly reduces linearization errors, improving map consisten...

A fundamental issue in mobile robotics is map building. The term refers to cases where a robot is forced to move in an unknown environment and has to build a map entirely based on its sensory information. In this paper we present a method for building robot maps by using a Kohonen’s self-organizing artificial neural network, and describe how path planning can be subsequently performed on such a...

Abstract— An active approach to sensing can provide the focused measurement capability over a wide field of view which allows correctly formulated Simultaneous Localisation and Map-Building (SLAM) to be implemented with vision, permitting repeatable long-term localisation using only naturally occurring, automatically-detected features. In this paper we present the first example of a general sys...

This paper presents a programmable logic-based agent control system that interleaves planning, plan execution and perception. In this system, a program is a collection of logical formulae describing the agent’s relationship to its environment. Two such programs for a mobile robot are described — one for navigation and one for map building — that share much of their code. The map building progra...