David Guttendorf

Papers

Total Citations

H-Index

About

David Guttendorf is a leading researcher at the intersection of robotics, autonomous systems, and software engineering, with a primary focus on ensuring the safety and reliability of intelligent machines. His most impactful work, "Robustness testing of autonomy software" (2018, 52 citations), established a foundational framework for stress-testing robotic systems against unexpected inputs—a critical need as these technologies enter industrial and human-interactive domains. This contribution directly addresses the gap between traditional software robustness testing and the unique challenges posed by autonomous systems. More recently, Guttendorf has pioneered novel approaches to fault diagnosis, as demonstrated in his 2024 paper on "Active Learning Omnivariate Decision Trees for Fault Diagnosis in Robotic Systems." This work introduces a powerful technique that leverages multivariate decision trees and active learning to generate human-interpretable descriptions of failure conditions, enabling engineers to rapidly debug complex robotic behaviors. By combining rigorous testing methodologies with interpretable machine learning, Guttendorf is shaping the future of dependable autonomy, making his research essential reading for anyone working on safe and trustworthy robotic systems.