\n
![](\"https:\/\/cdn.flipboard.com\/techcrunch.com\/fd89fdc267eceb9d1d8fadad4ce7ed559330e5ef\/original.jpg\")
<\/p>\n [ad_1]
\n<\/p>\n
Today at TechCrunch\u2019s TC Sessions: Robotics + AI event at UC Berkeley, Nvidia VP of Engineering Claire Delaunay <\/a> announced that the company\u2019s Isaac SDK<\/a> is available for download. Announced last month<\/a>, the software development kit is part of the chipmaker\u2019s ongoing push to help make robotics development more accessible for a wider range of users.<\/p>\n 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.<\/p>\n According to the company:<\/p>\n 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.<\/p>\n<\/blockquote>\n And, of course, the system will play nicely with NVIDIA\u2019s <\/a> own robotics hardware components like the Jetson Nano and Jetson AGX Xavier. Delaunay demonstrated some of the system\u2019s functionality onstage at today\u2019s event, using Nvidia\u2019s dual in-house reference platforms, the two-wheeled Carter and four-wheeled Kaya.<\/p>\n<\/p><\/div>\n\n