Papers
6
Total Citations
152
H-Index
4
About
Amine Elhafsi is a robotics and artificial intelligence researcher whose work sits at the intersection of foundation models, autonomous systems, and robot safety. He is best known for pioneering the application of large language models (LLMs) to semantic anomaly detection in robotics — work that has garnered over 85 citations and established him as a leading voice in leveraging internet-scale AI to identify and mitigate out-of-distribution failures in autonomous systems. His 2024 follow-up on real-time anomaly detection and reactive planning with LLMs further demonstrates his commitment to translating zero-shot generalization capabilities into practical safety mechanisms for deployed robots. Beyond anomaly detection, Elhafsi has made meaningful contributions to trajectory forecasting through MATS, an interpretable representation designed to bridge behavior prediction and motion planning — a critical challenge in human-robot interaction. His earlier work on cloud robotics explored intelligent network offloading policies for resource-constrained platforms like drones, reflecting a broad systems-level perspective. Across his portfolio, Elhafsi consistently addresses the gap between powerful AI models and their reliable deployment in real-world robotic settings, making his research particularly relevant to students working on safe and scalable autonomy.
Research Focus
Key Achievements
Top Papers
- 1Semantic anomaly detection with large language models85 citations · 2023
- 2Real-Time Anomaly Detection and Reactive Planning with Large Language Models28 citations · 2024
- 3
- 4Network Offloading Policies for Cloud Robotics: A Learning-Based Approach15 citations · 2019
- 5Map-Predictive Motion Planning in Unknown Environments2 citations · 2020
- 6Semantic Anomaly Detection with Large Language Models2 citations · 2023