Max Robotics — Global Service Robot Directory + US Certification

About

Peiyuan Zhi is a robotics researcher advancing the frontier of intelligent manipulation and human-robot collaboration. His work centers on three key areas: 6-DoF grasp pose detection, closed-loop mobile manipulation, and assistive robotic systems. Zhi’s most cited paper, “Hybrid Physical Metric For 6-DoF Grasp Pose Detection” (2022, 27 citations), tackles the challenge of multi-grasp, multi-object detection by introducing data-driven physical metrics that mimic human reasoning. In 2025, he achieved a breakthrough with “Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V” (10 citations), presenting COME-robot—the first system to leverage GPT-4V for real-time, open-ended reasoning and adaptive planning in dynamic environments. This work demonstrates how vision-language models can enable robots to navigate and manipulate with unprecedented flexibility. Zhi also contributed to assistive technology with a multimodal automatic feeding robotic device (2022), addressing self-feeding challenges for disabled individuals. His recent exploration of perception alignment in human-robot collaboration (SYNERGAI, 2025) further underscores his commitment to bridging human intent and robotic action. With a growing citation impact and a focus on integrating large foundation models into physical systems, Zhi is shaping the future of autonomous, context-aware robotics.