Zitong Zhan

University at Buffalo, State University of New York

Papers

Total Citations

H-Index

About

Zitong Zhan is an emerging researcher at the forefront of robot autonomy and autonomous systems, with a particular focus on self-supervised learning, neuro-symbolic frameworks, and kinematics-aware trajectory planning. His most notable contribution, "Imperative Learning," introduces a groundbreaking self-supervised neuro-symbolic learning framework designed to overcome a fundamental limitation in modern robotics: the over-reliance on large, expensive labeled datasets. By bridging data-driven methods with symbolic reasoning, Zhan's framework enables robots to generalize more robustly to dynamic, ever-changing environments — a challenge that has long constrained reinforcement and imitation learning approaches. Building on this foundation, his work on iKap extends these principles into practical trajectory planning, developing kinematics-aware systems that integrate vision-to-planning pipelines with greater efficiency and environmental adaptability. Though early in his research career, Zhan's publications have already begun attracting scholarly attention, accumulating citations that signal growing interest from the robotics and machine learning communities. His work represents a promising step toward more autonomous, adaptable, and data-efficient robotic systems, positioning him as a researcher to watch in the rapidly evolving field of robot intelligence.