Meghan Booker
Papers
2
Total Citations
4
H-Index
2
About
Meghan Booker is an early-career robotics researcher whose work sits at the intersection of autonomous planning, perception, and adaptive decision-making. Her research addresses one of the field's most persistent challenges: enabling robots to operate reliably in complex, uncertain, and dynamic real-world environments. In her 2025 work, *ConceptAgent*, Booker and her collaborators tackle open-world task planning by combining Large Language Models with precondition grounding and tree search strategies, pushing the boundaries of how robots can reason about and execute multi-step tasks in highly variable settings. Complementing this, her 2023 paper on Bayesian attention-switching explores how robots can intelligently determine *what* to focus on and *when* — inferring changes in environmental abstractions to maintain reliable operation amid time-varying conditions. Though both papers are in the early stages of accumulating citations — each garnering 2 citations to date — they reflect a research vision that bridges classical probabilistic reasoning with modern language-driven AI. Booker's contributions are particularly relevant as the robotics community grapples with deploying autonomous agents beyond controlled laboratory settings. Students interested in robot cognition, adaptive planning, or human-robot interaction will find her work an compelling entry point into these rapidly evolving questions.
Research Focus
Key Achievements
Top Papers
- 1
- 2