Fuzzy sets as a basis for a theory of possibility
Fuzzy Sets and Systems
Bayesian Multiple Target Tracking
Bayesian Multiple Target Tracking
The Geometry of Multiple Images: The Laws That Govern The Formation of Images of A Scene and Some of Their Applications
Estimation with Applications to Tracking and Navigation
Estimation with Applications to Tracking and Navigation
Multiple View Geometry in Computer Vision
Multiple View Geometry in Computer Vision
A probabilistic framework for entire WSN localization using a mobile robot
Robotics and Autonomous Systems
Multirobot object localization: a fuzzy fusion approach
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Delayed-state information filter for cooperative decentralized tracking
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Scalable control of decentralised sensor platforms
IPSN'03 Proceedings of the 2nd international conference on Information processing in sensor networks
Decentralized sensor fusion with distributed particle filters
UAI'03 Proceedings of the Nineteenth conference on Uncertainty in Artificial Intelligence
Exactly Sparse Delayed-State Filters for View-Based SLAM
IEEE Transactions on Robotics
Decentralized multi-robot cooperation with auctioned POMDPs
International Journal of Robotics Research
Hi-index | 0.00 |
This paper presents a decentralized data fusion approach to perform cooperative perception with data gathered from heterogeneous sensors, which can be static or carried by robots. In particular, a decentralized delayed-state information filter (DDSIF) is described, in which full-state trajectories (that is, delayed states) are considered to fuse the information. This approach allows obtaining an estimation equal to that provided by a centralized system and reduces the impact of communication delays and latency in the estimation. The sparseness of the information matrix maintains the communication overhead at a reasonable level. The method is applied to cooperative tracking, and some results in disaster management scenarios are shown. In this kind of scenario, the target might move in both open-field and indoor areas, so the fusion of data provided by heterogeneous sensors is beneficial. The paper also shows experimental results with real data and integrating several sources of information.