Ifrah Idrees

Brown University

Papers

4

Total Citations

35

H-Index

3

About

Ifrah Idrees is a rising researcher at the intersection of robotics, natural language processing, and formal methods, whose work focuses on enabling robots to intelligently recover from failures and understand complex human commands. Her most significant contribution is the CAPE framework (Corrective Actions from Precondition Errors), which leverages large language models (LLMs) to diagnose why a robot’s action failed and generate corrective plans—moving beyond simple retries to address the root cause. This work, published in 2022 and 2024, has already garnered over 22 citations, signaling its impact on the field of robot task planning. Idrees also tackles the challenge of grounding natural language commands into linear temporal logic (LTL) for long-horizon tasks, demonstrating how robots can follow complex, temporally constrained instructions in unseen environments without requiring environment-specific training data. Additionally, she developed a framework for realistic simulation of daily human activity to support the development of social robots like Astro. With a growing publication record and a clear focus on making robots more robust and intuitive, Idrees is establishing herself as a key voice in the next generation of autonomous systems research.

Research Focus

Key Achievements

3
H-Index
4
Papers
35
Total Citations
9
Avg Citations/Paper
🏆 Most Cited Paper
CAPE: Corrective Actions from Precondition Errors using Large Language Models
13 citations · 2024
📈 Most Prolific Year: 2023 (2 Papers)
🤝 Key Collaborators: 15
🏛 Institutions: Brown University

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago