Phillip Richter
Papers
2
Total Citations
6
H-Index
1
About
Phillip Richter is a rising researcher at the forefront of Human-Robot Interaction (HRI) and explainable AI (XAI). His work focuses on the critical challenge of bridging the gap between human intuition and robotic behavior, particularly in learning and error scenarios. Richter’s major contribution is the introduction of the **Mental Model Mismatch (MMM) Score**, a novel feedback mechanism that uses Large Language Models to quantify and correct discrepancies between a human teacher’s expectations and a robot’s actual learning capabilities. This work, detailed in his 2024 paper on intention-based feedback, aims to reduce user misconceptions that often lead to technology misuse or rejection. His complementary research on "learning robots" identifies the enabling architectures needed to make complex autonomous systems more transparent to lay users. While still early in his career, Richter’s foundational papers have already garnered attention for tackling a core problem in HRI: ensuring that as robots become more prevalent in everyday life, their behavior remains interpretable and trustworthy to non-experts.
Research Focus
Key Achievements
Top Papers
- 1
- 2