Allan Zhou

Stanford Medicine, University of California, Berkeley

Papers

Total Citations

H-Index

About

Allan Zhou is a robotics researcher whose work lies at the intersection of computer vision, imitation learning, and human-robot interaction. His major contributions include pioneering methods to make robotic learning more data-efficient and expressive. In his highly cited 2023 work, "NeRF in the Palm of Your Hand," Zhou introduced SP (Synthetic Perturbations), a corrective augmentation technique that leverages novel-view synthesis to dramatically reduce the number of expert demonstrations needed for training visual manipulation policies—a key bottleneck in imitation learning. This paper has already garnered 39 citations, reflecting its immediate impact on the field. Earlier, in his 2018 paper "Cost Functions for Robot Motion Style" (18 citations), Zhou tackled the underexplored challenge of generating emotionally expressive robot motion. By proposing style-encoding cost functions that augment nominal task objectives, he demonstrated how robots can perform physical tasks with distinct, human-like styles—a foundational step toward more natural human-robot collaboration. Zhou’s work bridges the gap between data-hungry deep learning and the practical need for efficient, expressive robotic systems, making him a rising voice in modern robotics research.