Hanieh Shojaei

Papers

Total Citations

H-Index

About

Hanieh Shojaei is a researcher at the forefront of autonomous perception systems, specializing in LiDAR-based scene understanding, uncertainty estimation, and out-of-distribution (OOD) detection for semantic segmentation. Her work addresses a critical challenge in safe autonomous driving: ensuring that deep learning models can reliably identify and flag unfamiliar or ambiguous scenarios in real-world LiDAR point clouds. In her most-cited paper, "Uncertainty Estimation and Out-of-Distribution Detection for LiDAR Scene Semantic Segmentation" (2025), Shojaei introduces novel methods to quantify model confidence and detect anomalous objects or environments that fall outside the training distribution—a key step toward robust, trustworthy perception. This contribution has already garnered early attention with 2 citations, underscoring its relevance to the growing field of safety-critical AI. Shojaei’s research bridges the gap between theoretical uncertainty quantification and practical deployment in autonomous vehicles, offering tools that enhance both model interpretability and operational safety. Her work is particularly notable for its focus on real-time, point-cloud-specific techniques, making it directly applicable to industry-grade LiDAR systems. As the demand for reliable autonomous navigation intensifies, Shojaei’s contributions are poised to influence next-generation perception pipelines and safety standards.