NVIDIA has announced a significant breakthrough in humanoid robotics, offering manufacturers, AI developers and global software developers a new set of services, models and computational platforms. This effort is aimed at facilitating the development, training and building of the next generation of humanoid robots.
New tools include innovative microservices and frameworks such as NVIDIA NIM™ for robotic simulation and learning, and the NVIDIA OSMO orchestration service, which optimizes the handling of complex robotic workflows.
NVIDIA demonstrates new tools for humanoid robotics
NIM microservices enable developers to reduce implementation times dramatically, from weeks to minutes. They include the MimicGen microservice, which creates synthetic motion data based on teleoperation recordings, and Robocasa, which generates tasks and environments for OpenUSD simulations. In addition, NVIDIA OSMO, now available, is a cloud-native solution that facilitates the management and scalability of robotic workflows, reducing development time to less than a week.
Likewise, NVIDIA demonstrated a new teleoperation workflow at the SIGGRAPH conference that enables developers to generate large volumes of synthetic data from a few human demonstrations. Using devices such as Apple Vision Pro and tools such as NVIDIA Isaac Sim and MimicGen, developers can train robotic models more efficiently and economically. This process reduces the time and costs associated with capturing human demonstration data.
NVIDIA builds three computers so manufacturers can create AI-enabled robots. Source: NVIDIA.
Exclusive access to NVIDIA robotics technology
To support humanoid robotics developers, NVIDIA has launched a new Developer Program that offers early access to its latest technologies. Initial participants include Boston Dynamics and other industry leaders. This program provides access to key platforms such as NVIDIA Isaac Sim, NVIDIA Isaac Lab, and Jetson™ Thor computers, enabling developers to customize and optimize their robotic solutions.
Follow us on social networks and don’t miss any of our publications!
YouTube LinkedIn Facebook Instagram X
Source and photo: nvidianews
Loading...
