Max Robotics — Global Service Robot Directory + US Certification

About

Yetong Zhang is a roboticist whose research lies at the intersection of simultaneous localization and mapping (SLAM), multi-robot coordination, and constrained optimization for robotic systems. Zhang’s most impactful contribution is the development of MR-iSAM2, an incremental smoothing and mapping algorithm that introduces the multi-root Bayes tree (MRBT) to efficiently solve multi-robot SLAM inference problems. This work, with 16 citations, addresses a critical challenge in deploying teams of robots in unknown environments. Zhang also proposed a distributed client-server optimization framework for SLAM, enabling devices with limited computational resources—such as VR/AR headsets—to perform full SLAM tasks without sacrificing accuracy. Beyond perception, Zhang has contributed to trajectory optimization for pneumatically-actuated jumping robots, leveraging factor graphs to model compliance and agility. More recently, Zhang introduced a manifold optimization approach for robotic inference and planning, transforming constrained problems into unconstrained ones to simplify complex planning tasks. With a portfolio spanning SLAM, resource-constrained robotics, and optimization theory, Yetong Zhang is shaping the future of autonomous systems that must perceive, plan, and cooperate in real-world environments.