William Ljungbergh
Papers
2
Total Citations
30
H-Index
2
About
William Ljungbergh is a rising researcher at the intersection of autonomous systems, sensor fusion, and intelligent control. His work primarily addresses the critical challenge of **multitarget tracking (MTT)** and **mobile robot navigation** in complex, dynamic environments. Ljungbergh’s most significant contribution is his pioneering comparison of classical model-based Bayesian methods with modern deep learning for MTT. In his highly cited 2021 paper (24 citations), he systematically evaluated **Random Finite Set (RFS) methods** against **Transformer-based neural networks**, providing a crucial roadmap for the next generation of trackers used in autonomous driving, surveillance, and robotics. This work is notable for bridging the gap between theoretical conjugate priors and practical, data-driven solutions. Complementing this, Ljungbergh has advanced practical robotics through **Nonlinear Model Predictive Control (NMPC)** for trajectory generation. His 2021 paper (6 citations) demonstrates a robust framework combining visibility graphs and A* search to enable collision-free, long-range navigation for mobile robots amidst both static and dynamic obstacles. By blending rigorous Bayesian theory with cutting-edge deep learning and control, Ljungbergh is shaping how autonomous systems perceive and move through the world.
Research Focus
Key Achievements
Top Papers
- 1
- 2