Jonathan Gough
Papers
2
Total Citations
7
H-Index
2
About
Jonathan Gough’s research lies at the intersection of automated planning, action model learning, and robust execution monitoring in artificial intelligence. His work addresses a critical gap in intelligent systems: the mismatch between abstract planning models and the unpredictable realities of physical execution. Gough’s major contribution is pioneering methods to detect and manage execution failures by leveraging learned action models—enabling planners to anticipate discrepancies between planned behaviors and real-world outcomes. His most cited paper, “Detecting execution failures using learned action models” (2007, 5 citations), introduces techniques that allow autonomous systems to recognize when environmental uncertainties cause plan deviations, thereby improving reliability. A related study, “Using learned action models in execution monitoring” (2006, 2 citations), further develops these ideas by integrating learned models directly into monitoring loops. Though his citation counts are modest, Gough’s work is foundational for researchers tackling the challenge of bridging symbolic planning with grounded, resilient execution—a key step toward truly autonomous robots and agents operating in dynamic, uncertain environments. His contributions remain relevant for advancing robust AI systems.
Research Focus
Key Achievements
Top Papers
- 1Detecting execution failures using learned action models5 citations · 2007
- 2Using learned action models in execution monitoring2 citations · 2006