A naukri.com initiative
The Robot Report
3w
13
Image Credit: The Robot Report
AWS offers accelerated robotics simulation with NVIDIA
- NVIDIA and AWS are offering tools to accelerate the development of robotics, quantitative computing and AI.
- NVIDIA Isaac Sim, a reference application built on NVIDIA Omniverse, is now available on NVIDIA L40S GPUs in Amazon Elastic Cloud Computing (EC2) G6e instances.
- This enables developers to simulate and test AI-driven robots in physically based virtual environments, allowing roboticists to use these instances to train many computer vision models that power AI-driven robots.
- The same instances can also be used for data generation and simulation of model training, and teams can orchestrate complex robotics development workflows.
- Developers may use simulation to verify, validate and optimise robot design as well as systems and algorithms before deployment, the company said.
- Simulation reduces costly manufacturing and construction change orders by optimising facility and system designs.
- NVIDIA said Isaac Sim can help generate synthetic data for perception model training, easing the synthetic data generation process by reducing many tedious and manual steps.
- The NVIDIA DGX Cloud is now available on Amazon for training AI models, while NVIDIA BioNeMo has been integrated into AWS HealthOmics.
- Other NVIDIA announcements include integrating AI blueprints and the RAPIDS quick start notebooks on Amazon EMR.
- Developers could also use Isaac Lab, an open-source robot learning framework built on Isaac Sim, to build robot policy for AWS Batch that will be repeated and easily troubleshooted.
Read Full Article
Like
For uninterrupted reading, download the app