Alexander Unnervik
Papers
1
Total Citations
18
H-Index
1
About
Alexander Unnervik is a researcher at the forefront of trustworthy autonomous systems, with a primary focus on high-level fusion perception and fault detection for self-driving vehicles and intelligent robots. His most-cited work, “A Plausibility-Based Fault Detection Method for High-Level Fusion Perception Systems” (2020, 18 citations), tackles a critical challenge in safe automation: guaranteeing trust in perception systems plagued by non-traceable, systematic errors. Unnervik’s key contribution lies in developing a plausibility-based framework that identifies faults otherwise invisible to standard validation methods, directly enhancing the reliability of autonomous agents in real-world environments. This work has become a foundational reference for researchers addressing safety in perception fusion, influencing subsequent studies on fault-tolerant AI. By bridging the gap between theoretical reliability and practical deployment, Unnervik’s research offers a vital tool for engineers and scientists striving to make autonomous systems robust against hidden failures. His achievements underscore a commitment to operational safety, positioning him as a notable voice in the ongoing effort to build trustworthy automation for critical applications.
Research Focus
Key Achievements
Top Papers
- 1