Mobile robot navigation

About: Mobile robot navigation is a research topic. Over the lifetime, 14713 publications have been published within this topic receiving 263092 citations.

An evaluation of image feature detectors and descriptors for robot navigation

Abstract: The detection and matching of feature points is crucial in many computer vision systems. Successful establishing of points correspondences between concurrent frames is important in such tasks as visual odometry, structure from motion or simultaneous localization and mapping. This paper compares of the performance of the well established, single scale detectors and descriptors and the increasingly popular, multiscale approaches.

Fuzzy traversability index: A new concept for terrain‐based navigation

Abstract: Fuzzy Traversability Index is introduced in this paper as a new and simple measure for quantifying the ease of traversal of natural terrains by field mobile robots. This index provides a simple means for incorporating the terrain quality data into the robot navigation strategy and is used for terrain-based navigation of field mobile robots. The Traversability Index is expressed by fuzzy sets that quantify the suitability of the terrain for traversal based on its geometrical and physical properties, such as slope, roughness, and hardness. This descriptive representation of terrain traversability in a natural language using linguistic variables and conditional statements is easily comprehensible, more appealing, and closer to human intuition than a mathematical formulation of traversability. A set of fuzzy navigation rules is developed using the Fuzzy Traversability Index to guide the robot toward the safest and the most traversable terrain. In addition, another set of fuzzy rules is developed to drive the robot from its initial position to a user-specified goal position. These two rule sets are integrated in a two-stage procedure for autonomous robot navigation without a priori map-based knowledge about the environment. In the first stage, the traverse-terrain and seek-goal rule sets make their individual, independent recommendations for robot turn and move commands. In the second stage, these recommendations are integrated by using appropriate weighting factors to generate the combined, coordinated recommendation for the robot navigation based on the robot status. Three simulation studies are presented to demonstrate the capability of the mobile robot to reach the goal safely while avoiding impassable terrains. ©2000 John Wiley & Sons, Inc.

A navigation system for robots operating in crowded urban environments

Abstract: Over the past years, there has been a tremendous progress in the area of robot navigation. Most of the systems developed thus far, however, are restricted to indoor scenarios, non-urban outdoor environments, or road usage with cars. Urban areas introduce numerous challenges to autonomous mobile robots as they are highly complex and in addition to that dynamic. In this paper, we present a navigation system for pedestrian-like autonomous navigation with mobile robots in city environments. We describe different components including a SLAM system for dealing with huge maps of city centers, a planning approach for inferring feasible paths taking also into account the traversability and type of terrain, and a method for accurate localization in dynamic environments. The navigation system has been implemented and tested in several large-scale field tests in which the robot Obelix managed to autonomously navigate from our university campus over a 3.3 km long route to the city center of Freiburg.

Tele-presence robot system with multi-cast features

Abstract: A graphical user interface for a remote controlled robot system that includes a robot view field that displays information provided by a robot and an observer view field that display observer information about one or more observers that can receive the robot information. The interface has various features that allow a master user to control the observation and participation of the observers.