Sruthi Soorian

Rutgers, The State University of New Jersey

Papers

Total Citations

H-Index

About

Sruthi Soorian’s research lies at the intersection of robotic manipulation and computer vision, with a focus on enabling robots to interact with objects in unstructured, real-world environments. Her most-cited work, “Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands” (2020, 5 citations), addresses a critical challenge in manipulation: accurately estimating an object’s pose relative to a robot hand when the hand itself obscures the view. This problem is particularly acute for adaptive hands, whose variable finger configurations complicate detection. Soorian’s contribution is a robust, occlusion-aware approach that leverages geometric reasoning and sensor data to maintain pose estimation even under heavy occlusion—a key enabler for tasks like precise placement or within-hand manipulation. While her citation count is modest, her work tackles a foundational bottleneck in dexterous robotics, offering practical solutions for systems that must operate reliably despite visual clutter. Her research is especially relevant for students and engineers working on grasping, in-hand manipulation, or sensorimotor control, as it bridges the gap between theoretical pose estimation and the messy realities of physical interaction. Soorian’s focus on adaptive hands, which are increasingly common in research and industry, positions her as a contributor to the next generation of more capable, perceptive robotic systems.