Max Robotics — Global Service Robot Directory + US Certification

About

Brianna Zitkovich is a leading researcher in robotics and machine learning, best known for pioneering the Robotics Transformer (RT) series that bridges large-scale pretrained models with real-world robotic control. Her landmark work on RT-1 (512 citations) established a scalable framework for transferring knowledge from diverse, task-agnostic datasets to enable robots to perform complex manipulation tasks with minimal fine-tuning. She extended this paradigm with RT-2 (267 citations), a vision-language-action model that directly incorporates web-scale knowledge into end-to-end robotic control, unlocking emergent semantic reasoning and unprecedented generalization in physical robots. Zitkovich also contributed to open-world object manipulation using pretrained vision-language models, enabling robots to follow nuanced human instructions like retrieving specific objects. Her work on Q-Transformer advanced offline reinforcement learning by combining Transformers with autoregressive Q-functions for scalable multi-task policy learning from large datasets. Collectively, her research has redefined how robots can leverage internet-scale data for real-world control, achieving over 850 citations and establishing new benchmarks for generalization and semantic understanding in robotics.