Max Robotics — Global Service Robot Directory + US Certification

About

Qiming Yuan is a leading researcher in robotics and reinforcement learning, best known for groundbreaking work in sim-to-real transfer and autonomous skill acquisition. His most celebrated contribution is the 2019 paper "Solving Rubik's Cube with a Robot Hand," which demonstrated for the first time that a policy trained entirely in simulation could solve a complex, real-world manipulation task—the Rubik’s cube—using a dexterous robot hand. This work, which has garnered over 630 citations, introduced **automatic domain randomization (ADR)** , a now-foundational technique that systematically varies simulation parameters to bridge the reality gap. Yuan further advanced robotic autonomy with his 2021 work on "Asymmetric self-play for automatic goal discovery," where two agents (Alice and Bob) engage in a game to automatically generate and solve challenging manipulation goals, enabling a single policy to handle novel objects and tasks without human engineering. His research sits at the intersection of deep reinforcement learning, robotics, and goal-conditioned policies, with a focus on creating scalable, generalist robotic systems. Yuan’s innovations have profoundly influenced how robots learn complex physical skills, making him a pivotal figure in modern robotics.