Max Robotics — Global Service Robot Directory + US Certification

About

Sharath Maddineni is at the forefront of embodied AI and robotics, pioneering the integration of large multimodal models into physical agents. His research centers on enabling robots to perform complex, long-horizon reasoning by bridging the gap between internet-scale digital knowledge and real-world physical action. Maddineni’s major contributions include the development of RoboVQA, a scalable data collection framework that achieves 2.2x higher throughput than traditional methods, allowing robots to reason over extended tasks using diverse, bottom-up data. He also co-authored AutoRT, which leverages foundation models for orchestrating robotic agents at scale, addressing the critical challenge of grounding language and vision in physical environments. Most recently, his work on Gemini Robotics introduces a new family of AI models purpose-built for robotics, aiming to translate generalist digital capabilities into robust physical performance. With over 50 citations across his key papers, Maddineni’s research is shaping the future of autonomous systems, making him a notable figure in the quest to bring AI into the physical world.