Nicholas Conlon
Papers
5
Total Citations
38
H-Index
4
About
Nicholas Conlon is a leading researcher in human-autonomy teaming, focusing on the critical challenge of enabling autonomous systems to understand and communicate their own capabilities. His work centers on developing algorithmic methods for competency self-assessment, allowing robots and AI agents to evaluate their proficiency in real-time and adjust their behavior accordingly. Conlon's major contributions include pioneering deep reinforcement learning approaches for autonomous vehicle self-assessment and event-triggered frameworks that dynamically adjust levels of autonomy based on the robot's confidence in its performance. His 2023 survey on algorithmic methods for competency self-assessments has garnered 13 citations, establishing foundational knowledge in the field. Notably, his 2022 work on robot proficiency self-assessment in human-robot teaming, with 9 citations, directly addresses the trust calibration problem—ensuring humans appropriately rely on autonomous systems in high-risk environments like space exploration and search & rescue. Conlon's research is instrumental in creating transparent, trustworthy AI teammates that can honestly communicate their limitations, a crucial step toward safe and effective human-machine collaboration.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Event-triggered robot self-assessment to aid in autonomy adjustment5 citations · 2024
- 5