Papers
8
Total Citations
85
H-Index
4
About
Bo Wahlberg is a researcher whose work spans autonomous systems, decision-making under uncertainty, and computational neuroscience, with particular strengths in robotics, control theory, and machine learning. His most influential contribution, "Teaching Robots to Perceive Time" (2020, 38 citations), bridges neuroscience and artificial intelligence by drawing on dopaminergic reward prediction mechanisms to model time perception in robotic systems — a novel interdisciplinary approach that has attracted significant attention. This thread continues in his biologically inspired computational framework for time perception (2021), which models neural timing mechanisms underlying planning and decision-making. Wahlberg has also made meaningful contributions to probabilistic decision-making, notably through his value iteration algorithm for Partially Observed Markov Decision Process (POMDP) multi-armed bandits (2004, 15 citations), addressing the complex challenge of resource allocation under uncertainty. His work on the WARA-PS public safety research arena (2021, 13 citations) demonstrates a commitment to translating theoretical advances into real-world collaborative autonomous systems for aerial and surface vehicles. Additional contributions to fault detection in navigation systems and Hidden Markov Model identification reflect a researcher whose career consistently integrates rigorous mathematical foundations with practical, high-impact applications in autonomous systems and intelligent control.
Research Focus
Key Achievements
Top Papers
- 1Teaching Robots to Perceive Time: A Twofold Learning Approach38 citations · 2020
- 2
- 3
- 4FAULT DETECTION USING REDUNDANT NAVIGATION MODULES7 citations · 2006
- 5Observers Data Only Fault Detectio4 citations · 2009
- 6A Biologically Inspired Computational Model of Time Perception3 citations · 2021
- 7
- 8Fault Detection Using Redundant Navigation Modules2 citations · 2007