Max Robotics — Global Service Robot Directory + US Certification

About

Jaspiar Singh is at the forefront of scaling robot learning through the integration of large-scale machine learning models and real-world control. His primary research areas include robotics, vision-language-action models, and data-efficient generalization for manipulation tasks. Singh’s most influential contribution is the development of the Robotics Transformer (RT-1) series, which demonstrates how knowledge from diverse, task-agnostic datasets can be transferred to enable robots to solve specific tasks with minimal fine-tuning. His landmark 2023 paper, “RT-1,” has garnered over 512 citations, establishing a new paradigm for real-world robotic control at scale. Building on this, his work on RT-2 (267 citations) pioneers the direct incorporation of Internet-scale vision-language models into end-to-end robotic control, unlocking emergent semantic reasoning and unprecedented generalization. Singh also explores methods for scaling robot learning through semantically imagined experiences, generating synthetic training data to boost performance in novel scenarios. His research has profound implications for creating robots that can adapt to open-world environments, bridging the gap between simulated training and real-world deployment.