Nvidia launches its Isaac SDK to help democratize AI-powered robot development


Today at TechCrunch’s TC Sessions: Robotics + AI event at UC Berkeley, Nvidia VP of Engineering Claire Delaunay announced that the company’s Isaac SDK is available for download. Announced last month, the software development kit is part of the chipmaker’s ongoing push to help make robotics development more accessible for a wider range of users.

The system is designed to improve accessibility to key features of robotics AI and ML, including obstacle detection, speech recognition and stereo depth estimation, each of which will prove key components to even basic robotic systems, going forward.

According to the company:

Using computational graphs and an entity component system, the Isaac Robot Engine allows developers to break down complex robotic tasks into a network of smaller, simpler steps. Developing a complex system is made easy using Gems, which are modular capabilities for sensing, planning, and actuation that can be easily plugged into a robotics application.

And, of course, the system will play nicely with NVIDIA’s own robotics hardware components like the Jetson Nano and Jetson AGX Xavier. Delaunay demonstrated some of the system’s functionality onstage at today’s event, using Nvidia’s dual in-house reference platforms, the two-wheeled Carter and four-wheeled Kaya.