Max Robotics — Global Service Robot Directory + US Certification

About

Gaoyue Zhou is a leading researcher at the intersection of robotics, reinforcement learning, and embodied AI, with a focus on building generalist robotic systems that can learn from diverse, real-world data. Her most impactful contribution is co-leading the **Open X-Embodiment** collaboration, a landmark project that aggregated robotic datasets from over 20 institutions to train the RT-X models. This work, cited over 220 times, demonstrated that large-scale, cross-embodiment data can produce policies capable of zero-shot generalization across different robots—a significant step toward foundational models in robotics. Zhou also pioneered **Parrot**, a framework for learning data-driven behavioral priors that accelerate reinforcement learning by pretraining on offline datasets, analogous to pre-training in NLP and vision. Her **Navigation World Model (NWM)** extends these ideas to controllable video prediction for visual navigation. Additionally, she developed the **Train Offline, Test Online** benchmark and **RoboHive** platform to standardize real-world robot learning evaluation. With a publication record spanning top venues like RSS, CoRL, and ICRA, Zhou’s work is shaping how the field approaches scalable, data-driven robot learning.