Roman Mazl

Building a 2D environment map from laser range-finder data

The contribution describes a robust but simple approach to 2D environment mapping making-use of a TOF-based laser ranging system. As the used mobile system has no absolute positioning system the task has been split into two parts. The first deals with preprocessing of odometry and range measurements towards determination of position and heading of the platform in the environment. The other step maintains (updates) the internal world model via search for correspondences between existing map and observed entities with subsequent application of renewal rules.

Train locator using inertial sensors and odometer

The paper describes a solution to railway vehicle localization problem for the cases, where no global positioning information (like GPS) is temporarily unavailable. The given solution also assumes no additional landmarks or other extraordinary installations aside the train track. The presented approach is based on smart fusion of onboard-gathered data making use of Kalman filter. The available data sources include a vehicle odometer and accelerometer.

Methods for Personal Localisation and Mapping

Abstract This paper presents methods for beaconless localisation of a human being in indoor conditions. The base of the localisation is so-called human dead reckoning, which is implemented with inertial sensors and a self-made stride length measurement sensor. The focus of the paper is to study the possibility of using a laser range finder for human localisation and mapping. The paper discusses the differences between the traditional robot localisation and human localisation problems. Methods for scan matching, mapping and localisation using a priori map are presented.

A Control System for Multi-Robotic Communities

This paper describes a design, development and experience with an universal multi-robotic robot control system. The overall message-driven system concept is introduced together with its open modular architecture. Besides the description of functionalities of basic modules, the approach to the system configuration and hardware abstraction layer is discussed. The control system allows to manage different types of robots in one team, whereas each team member is able to share and interchange any information with other team members. Since a lot of robotic tasks are computationally intensive and cannot be computed onboard, the system allows to distribute selected subtasks among remote computers. The system has been designed as a test-bed for research of new algorithms from an area of cooperative robotics.

Range scan-based localization methods for mobile robots in complex environments

The work introduces design and comparison of different-brand methods for position localization of indoor mobile robots. Both the methods derive the robot relative position from a structure of the working environment based on measurements gathered by a TOF-based laser ranging system. The first presented method applies statistical description of the scene while the other one relies on a feature-based matching approach. Both the approaches provide method-specific behavior, which has been recognized in experiments with real data. The obtained results are compared and further improvements of the localization robustness via their combination are discussed.

Building of 3d environment models for mobile robotics using self-organization

In this paper, we present a new parallel self-organizing technique for three dimensional shape reconstruction for mobile robotics. The method is based on adaptive input data decomposition, parallel shape reconstruction in decomposed clusters using Kohonen Self-Organizing Map, which creates mesh representation of the input data. Afterwards, the sub-maps are joined together and the final mesh is re-optimized. Our method overcomes a problem of fitting one mesh to complex non-continuous shapes like building interiors. The method allows to process unordered data collected by mobile robots. The method is easily paralelizable and gives promising results.

Towards Environment Modeling by Autonomous Mobile Systems

The process of how to acquire knowledge about the operating environment is one of the most challenging problems that autonomous mobile robots must solve. The quality of the model depends on a number and the kind of sensors used and upon the precision the robot recovers its position. This paper introduces two crucial components of the map building procedure: the position localization based on data gathered from laser rangefinders and the deadreckoning system together with a novel method for map-building through data fusion from a monocular camera and a laser range-finder.

Statistical and Feature-Based Methods for Mobile Robot Position Localization

The contribution introduces design and comparison of different-brand methods for position localization of indoor mobile robots. The both methods derive the robot relative position from structure of the working environment based on range measurements gathered by a LIDAR system. As one of the methods uses statistical description of the scene the other relies on a feature-based matching approach. The suggested localization methods have been experimentally verified and the achieved results are presented and discussed.