🧪 Technology⚡· Impact 7/10
NVIDIA and Google DeepMind Advance Humanoid Robot Foundation Models
Source: blog.robozaps.com · Jun 18, 2026
Summary
NVIDIA's Project GR00T and Google DeepMind's RT-2 represent foundational models that enable humanoid robots to understand natural language and generalize to unseen tasks, marking a significant step toward versatile real-world robotics. This combines large-scale AI with physical embodiment, potentially accelerating the development of general-purpose robots.
Related research
All papers →Recent papers matching 4 keywords from this headline
PERCEPTION
Open access📊 9,777 cites
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Martı́n Abadi, Ashish Agarwal, Paul Barham +17 more
2016
LEARNING
📊 7,678 cites
Fractional Brownian Motions, Fractional Noises and Applications
Benoît B. Mandelbrot, John W. Van Ness
1968
MANIPULATION
📊 6,720 cites
A Mathematical Introduction to Robotic Manipulation
Richard M. Murray, Zexiang Li, Shankar Sastry
2017
PERCEPTION
📊 6,456 cites
Probabilistic graphical models : principles and techniques
Daniel L. Koller, Nir Friedman
2009