Xiao Zang

Rutgers Sexual and Reproductive Health and Rights, Rutgers, The State University of New Jersey

Papers

Total Citations

H-Index

About

Xiao Zang is a researcher advancing the frontier of robot motion planning through the innovative integration of deep learning and hardware-aware design. His primary research areas span neural network-based motion planning, spatio-temporal reasoning for robotics, and efficient hardware architectures for autonomous systems. Zang’s major contribution is the development of novel frameworks that reframe motion planning as a video prediction problem, enabling robots to anticipate and navigate complex environments with greater foresight. His work on the Spatio-Temporal Neural Network-based Motion Planner, which has garnered 15 citations, demonstrates how deep learning can replace traditional, computationally expensive planning algorithms with parallelizable, learning-driven approaches. Additionally, his MOPED engine (4 citations) introduces flexible dimension support, tackling the scalability challenges that plague sampling-based planners in high-dimensional spaces. Zang has also contributed to the hardware side with a Graph Neural Network-enabled motion planner architecture, bridging the gap between algorithmic innovation and real-time deployment. His research is particularly notable for its dual focus on algorithmic efficiency and practical hardware implementation, making autonomous navigation more accessible for 2-D/3-D applications.