Opportunistic Multi-sensor Fusion for Robust Navigation in Smart Environments

This paper presents the design of a navigation system for multiple autonomous robotic platforms. It performs multisensor fusion using a Monte Carlo Bayesian filter, and has been designed to maximize information acquisition. Apart from sensors equipped in the mobile platform, the system can dynamically integrate observations from friendly external sensing entities, increasing robustness and making it suitable for both indoor and outdoor operation. A multi-agent layer manages the information acquisition process, making it transparent for the core filtering solution. As a proof of concept, some preliminary results are presented over a real platform using the part of the system specialized in outdoor navigation.

[1]  Fredrik Gustafsson,et al.  Particle filters for positioning, navigation, and tracking , 2002, IEEE Trans. Signal Process..

[2]  Sebastian Thrun,et al.  Decentralized Sensor Fusion with Distributed Particle Filters , 2002, UAI.

[3]  Lili Huang,et al.  Tightly-coupled LIDAR and computer vision integration for vehicle detection , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[4]  Richard T. Vaughan,et al.  The Player/Stage Project: Tools for Multi-Robot and Distributed Sensor Systems , 2003 .

[5]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[6]  Jeffrey Zampieron,et al.  Self-localization in ubiquitous computing using sensor fusion , 2006 .

[7]  Nando de Freitas,et al.  The Unscented Particle Filter , 2000, NIPS.

[8]  José M. Molina López,et al.  Multi-sensor and Multi Agents Architecture for Indoor Location , 2010, DCAI.

[9]  Bernardo Wagner,et al.  Robust Self-Localization in Industrial Environments based on 3D Ceiling Structures , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  Yang Cheng,et al.  Particle Filtering for Attitude Estimation Using a Minimal Local-Error Representation , 2009 .

[11]  Greg Welch,et al.  Welch & Bishop , An Introduction to the Kalman Filter 2 1 The Discrete Kalman Filter In 1960 , 1994 .

[12]  Gérard Lachapelle,et al.  Low Cost INS/GPS Integration: Concepts and Testing , 2000 .

[13]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[14]  Y. Takahashi,et al.  Tray carrying robot for hospital use , 2005, 2005 IEEE International Conference on Industrial Technology.