Papers
7
Total Citations
86
H-Index
5
About
Jean Dezert is a leading figure in information fusion and uncertainty modeling, with a career dedicated to advancing the theory and application of belief functions in robotics and autonomous systems. His primary research areas include Dezert-Smarandache Theory (DSmT), evidential reasoning, and multi-sensor data fusion for environment perception. Dezert's major contributions lie in developing novel fusion rules, such as the Proportional Conflict Redistribution rules (PCR5 and PCR6), which address the limitations of classical Dempster-Shafer theory when handling highly conflicting and imprecise sources. His work on grid occupancy estimation using belief functions and PCR6 (2015, 13 citations) has significantly improved map reconstruction for mobile robot navigation. With over 46 citations for his foundational work on similarity measures for information fusion (2010), Dezert's impact is evident across defense, robotics, and perception applications. He has also pioneered sequential adaptive combination methods for unreliable evidence (2015, 6 citations) and advanced simultaneous localization and mapping (SLAM) using DSmT (2013, 5 citations). His research on generic object recognition through multi-feature fusion (2016, 3 citations) and evidential data association (2022, 3 citations) continues to shape modern robot perception systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3A FUSION MACHINE BASED ON DSMT AND PCR5 FOR ROBOT'S MAP RECONSTRUCTION10 citations · 2006
- 4Sequential Adaptive Combination Of Unreliable Sources Of Evidence6 citations · 2015
- 5SLAM and Path Planning of Mobile Robot Using DSmT5 citations · 2013
- 6GENERIC OBJECT RECOGNITION BASED ON FEATURE FUSION IN ROBOT PERCEPTION3 citations · 2016
- 7Evidential data association based on Dezert–Smarandache Theory3 citations · 2022