Daniel Jun Xian Ng

Papers

Total Citations

H-Index

About

Daniel Jun Xian Ng is a leading researcher at the intersection of machine learning and safety-critical cyber-physical systems (CPS). His work focuses on ensuring the reliability of autonomous systems by addressing a fundamental vulnerability: when ML models encounter data outside their training distribution, they can produce catastrophic failures. Ng’s key contributions center on out-of-distribution (OOD) detection, developing both embedded and real-time solutions. His seminal 2021 paper, "Embedded out-of-distribution detection on an autonomous robot platform," has garnered 13 citations and demonstrated how OOD detectors can be deployed directly on resource-constrained robotic hardware. Building on this, his 2022 work, "Design Methodology for Deep Out-of-Distribution Detectors in Real-Time Cyber-Physical Systems," with 7 citations, provides a systematic framework for integrating OOD detection into time-sensitive CPS, preventing inaccurate predictions before they lead to system failure. Ng’s research is pivotal for the safe deployment of autonomous vehicles, drones, and industrial robots, bridging the gap between theoretical ML robustness and practical real-time constraints. His work has established a design methodology that is becoming essential for engineers building trustworthy AI in the physical world.