Sensor Modeling and Multi-Sensor Data Fusion
Final progress rept. 1 Nov 2004-31 Jan 2005
DUKE UNIV DURHAM NC DEPT OF MECHANICALENGINEERING AND MATERIALS SCIENCE
Pagination or Media Count:
This research report presents a novel strategy to develop a sensor model based on a probabilistic approach that would accurately provide information about individual sensors uncertainties and limitations. The strategy also establishes the dependence of sensors uncertainties on some of environmental parameters or parameters of any feature extraction algorithm used in estimation based on sensors outputs. The approach makes use of a neural network that is trained with the help of an innovative technique that obtains training signal from a maximum likelihood estimator. The proposed technique was applied for modeling stereo-vision sensors and an Infra-Red IR proximity sensor used in the robotic work cell available in the Robotics and Manufacturing Automation RAMA Laboratory at Duke University. In addition, the report presents an innovative method to fuse the probabilistic information obtained from these sensors based on Bayesian formalism in an occupancy grid framework to obtain three-dimensional occupancy model and key features of the robotic workspace. The capability of the proposed technique in accurately obtaining three-dimensional occupancy profile and efficiently removing individual sensor uncertainties was validated and compared with other methods via experiments carried out in the RAMA lab during this project.
- Information Science