Max Robotics — Global Service Robot Directory + US Certification

About

Sichun Xu is a leading researcher at the intersection of robotics and artificial intelligence, whose work has fundamentally reshaped how robots understand and execute human language. Xu’s primary contributions lie in grounding large language models (LLMs) in real-world robotic control, bridging the gap between semantic knowledge and physical action. Their seminal paper, “Do As I Can, Not As I Say” (516 citations), introduced the concept of grounding LLMs in robotic affordances, enabling robots to act on high-level instructions rather than merely processing text. This work laid the foundation for the groundbreaking Robotics Transformer (RT-1) series, with over 550 combined citations, which demonstrated how large, diverse datasets could be leveraged for scalable, real-world robot control. Xu further advanced the field with RT-2 (267 citations), a vision-language-action model that transfers web-scale knowledge directly into robotic control, enabling emergent semantic reasoning and unprecedented generalization. Most recently, Xu contributed to ALOHA 2, an enhanced low-cost bimanual teleoperation system, democratizing access to dexterous robotic data collection. With over 1,300 total citations and a consistent focus on scalable, data-driven solutions, Xu stands as a pivotal figure in the quest for robots that can truly understand and act in the human world.