Liila Torabi

Papers

Total Citations

H-Index

About

Liila Torabi is a robotics researcher whose work spans autonomous mobile manipulation, 3D object modeling, and machine learning for robot navigation. Her research addresses some of the most challenging problems in field robotics: enabling robots to perceive, model, and navigate complex, unknown environments with minimal human intervention. Among her most notable contributions is the development of a fully autonomous 9-DOF mobile-manipulator system capable of building detailed 3D models of objects in situ, requiring no prior knowledge of the object beyond a rough bounding box estimate. This work, combining a PowerBot mobile base with a six-DOF arm and a line-scan range sensor, demonstrated sophisticated integrated view and path planning in unstructured environments. Her 2016 work on fast incremental learning for off-road robot navigation tackled a critical practical limitation in autonomous driving systems — the computational and data burden of large training datasets — proposing more efficient learning strategies suited to real-world deployment. While Torabi's citation counts remain modest (ranging from 3 to 4 citations per paper), her contributions represent meaningful advances in autonomous systems research, particularly in bridging perception, planning, and learning for robots operating in challenging, real-world conditions. Her work offers a strong foundation for researchers pursuing robust field robotics and adaptive autonomous navigation.