This edition of NVIDIA Robotics Research and Development Digest (R2D2) explores several contact-rich manipulation workflows for robotic assembly tasks from NVIDIA Research and how they can address key challenges with fixed automation, such as robustness, adaptability, and scalability. Contact-rich manipulation refers to robotic tasks that involve continuous or repeated physical contact��
]]>
Programming robots for real-world success requires a training process that accounts for unpredictable conditions, different surfaces, variations in object size, shape, texture, and more. Consequently, physically accurate simulations are vital for training AI-enabled robots before deployment. Crafting physically accurate simulation requires advanced programming skills to fine-tune algorithms��
]]>
From humanoids to policy, explore the work NVIDIA is bringing to the robotics community.
]]>
Large-scale, use�Ccase-specific synthetic data has become increasingly important in real-world computer vision and AI workflows. That��s because digital twins are a powerful way to create physics-based virtual replicas of factories, retail spaces, and other assets, enabling precise simulations of real-world environments. NVIDIA Isaac Sim, built on NVIDIA Omniverse, is a fully extensible��
]]>
The era of AI robots powered by physical AI has arrived. Physical AI models understand their environments and autonomously complete complex tasks in the physical world. Many of the complex tasks��like dexterous manipulation and humanoid locomotion across rough terrain��are too difficult to program and rely on generative physical AI models trained using reinforcement learning (RL) in simulation.
]]>
This post is the first in a series on building multi-camera tracking vision AI applications. In this part, we introduce the overall end-to-end workflow, focusing on building and deploying the multi-camera tracking system. The second part covers fine-tuning AI models with synthetic data to enhance system accuracy. Large areas like warehouses, factories, stadiums, and airports are typically��
]]>
Autonomous machine development is an iterative process of data generation and gathering, model training, and deployment characterized by complex multi-stage, multi-container workflows across heterogeneous compute resources. Multiple teams are involved, each requiring shared and heterogeneous compute. Furthermore, teams want to scale certain workloads into the cloud��
]]>
Robots are typically equipped with cameras. When designing a digital twin simulation, it��s important to replicate its performance in a simulated environment accurately. However, to make sure the simulation runs smoothly, it��s crucial to check the performance of the workstation that is running the simulation. In this blog post, we explore the steps to setting up and running a camera benchmark��
]]>