Srinath Sridhar

John Brown University, Robotics Research (United States)

Papers

Total Citations

H-Index

About

Srinath Sridhar is a leading researcher at the intersection of computer vision, robotics, and human-computer interaction, with a core focus on understanding and modeling dexterous human manipulation. His work is pivotal in bridging the gap between how humans physically interact with objects and how machines can replicate that understanding. Sridhar’s major contributions include pioneering markerless grasp capture, as demonstrated in his highly influential work "MANUS: Markerless Grasp Capture Using Articulated 3D Gaussians" (2024, 17 citations). This research tackles the challenging problem of accurately modeling hand-object contact without physical markers, using articulated 3D Gaussians to capture the subtle geometry of grasps—a critical step for advancing robotic manipulation and mixed reality. He also pushes the boundaries of robotic perception with "ViTa-Zero: Zero-shot Visuotactile Object 6D Pose Estimation" (2025, 5 citations), which addresses the generalization limitations of visuotactile sensing by enabling robots to estimate object poses without task-specific training data. By combining visual and tactile information, Sridhar’s work is laying the foundation for more intuitive and capable robotic systems, making him a key figure in the future of embodied AI and human-robot interaction.