Industrial robotics focus of new Nvidia AI platform
Autonomous machines will use AI to transform manufacturing, logistics, agriculture and other verticals
At the ongoing Computex event in Taipei, Taiwan, Nvidia announced a new artificial intelligence (AI) system designed to power autonomous machines and industrial robotics. The chipmaker specifically called out manufacturing, logistics, agriculture, construction and home delivery as potential use cases for its new Nvidia Isaac platform.
Isaac uses Nvidia’s Jetson Xavier robotics computer, which features more than 9 billion transistors to perform more than 30 trillion operations per second. Jetson Xavier comprises a Volta Tensor Core GPU, eight-core ARM CPU, deep learning accelerators and image, vision and video processors. The company says the system uses “a third the energy of a lightbulb.”
Nvidia CEO Jensen Huang called AI “the most powerful technology force of our time. Its first phase will enable new levels of software automation that boost productivity in many industries. Next, AI, in combination with sensors and actuators, will be the brain of a new generation of autonomous machines. Someday, there will be billions of intelligent machines in manufacturing, home delivery, warehouse logistics and more.”
The company expects early access to the developer kit for distributors in August; the Isaac platform carriers a $1,299 price tag.
Nvidia is going all in on AI. In addition to the robotics-focused product, the company has also developed Drive Isaac to enable autonomous vehicle development. Given the application, Nvidia has stressed the rigorous safety architecture and testing that went into the system on a chip. According to SVP of Automotive Hardware and Systems Gary Hicock, Drive serves as “an open platform so that the experts in the world’s best car companies can engage our platform to make it industrial strength.”
To support the level of safety required by autonomous vehicles, Hicock said a system on a chip “must have an architecture that doesn’t just detect hardware failures during operation. It also needs to be developed in a process that mitigates
SoC must have an architecture that doesn’t just detect hardware failures during operation. It also needs to be developed in a process that mitigates potential systematic faults. That is, the SoC must avoid failures whenever possible, but detect and respond to them if they cannot be avoided.