Haozhan Tang

Papers

Total Citations

H-Index

About

Haozhan Tang is pioneering the integration of 3D foundation models into robotics, with a focus on enabling robots to perceive, interact with, and learn from their environments more intuitively. His research spans three key areas: unified 3D representation and calibration, object geometry and pose estimation, and intuitive motion generation. Tang’s most cited work, “Unifying Representation and Calibration With 3D Foundation Models” (2024, 4 citations), addresses a fundamental robotics challenge by eliminating the need for external calibration markers, allowing manipulator-mounted cameras to autonomously calibrate and represent their environment. In “Simultaneous Geometry and Pose Estimation of Held Objects Via 3D Foundation Models” (2024, 2 citations), he tackles the complex problem of enabling robots to jointly estimate an object’s shape and movement as it is held and manipulated—a capability critical for tool use. His work “Teaching Periodic Stable Robot Motion Generation via Sketch” (2024, 2 citations) simplifies robot programming by allowing users to generate stable, periodic motions through simple sketches, democratizing access to advanced robotic control. Though early in his career, Tang’s contributions are already shaping how robots perceive and interact with the physical world, laying the groundwork for more autonomous and user-friendly robotic systems.