NVIDIA's new Jetson Orin Nano 2 chip aims to put frontier AI inside drones and home robots
The tiny computer uses 40% less power than its predecessor while doubling AI processing speed, and NVIDIA says it will let developers run the same kind of intelligence found in today's best chatbots directly inside physical machines.
Key points
- NVIDIA announced the Jetson Orin Nano 2, a compact AI computer for physical machines, in mid-2025.
- The module delivers 78 trillion AI operations per second and uses 40% less power than its predecessor at equivalent performance.
- It doubles the AI inference speed (the rate at which a model produces answers) of the previous Jetson Orin Nano Super.
- Wing, the Alphabet drone-delivery subsidiary, and home-robot maker Matic Robots are among the first partners evaluating the hardware.
- The Jetson Orin Nano 2 module and developer kit will be available in the first half of 2027.
A computer roughly the size of a credit-card reader could soon give a delivery drone the reasoning ability of a top-tier AI chatbot. That is the pitch behind the Jetson Orin Nano 2, NVIDIA's latest entry-level edge AI module, where "edge AI" means artificial intelligence that runs on a device itself rather than sending data back to a distant server.
What exactly did NVIDIA announce?
The Jetson Orin Nano 2 is a small, self-contained computing module designed to sit inside robots, drones and smart cameras. NVIDIA says it performs 78 trillion AI operations per second, packs 8 gigabytes of memory, and draws just 15 watts of power in its most efficient mode. At that power level, it matches the peak performance of the previous model while using 40% less electricity, NVIDIA vice-president Deepu Talla told The Robot Report.
The headline number is doubled inference speed. Inference, in plain terms, is the moment an AI model takes in information and produces an answer or decision. Faster inference means a drone can spot an obstacle and react sooner, or a cleaning robot can identify a chair leg and steer around it in real time.
Why does the power saving matter?
Battery life is everything for a flying drone or a cordless floor robot. Cutting power consumption by 40% for the same workload could meaningfully extend how long a device operates between charges, or let engineers shrink the battery and reduce weight.
The new chip can also run large language models, the technology behind text-based AI assistants like ChatGPT, and vision language models, which let machines describe or reason about what a camera sees. A year ago, models that capable needed a rack of server hardware. Now, NVIDIA says, they fit in a palm-sized module.
| Specification | Jetson Orin Nano Super | Jetson Orin Nano 2 |
|---|---|---|
| AI performance (TOPS) | ~40 | 78 |
| Memory | 8 GB | 8 GB |
| Power (efficient mode) | ~15 W | 15 W |
| Inference speed vs. predecessor | baseline | 2x faster |
| Availability | now | H1 2027 |
Who is already building with it?
Wing, the drone-delivery arm of Google's parent company Alphabet, is testing the chip for faster, safer package drops to residential addresses. Matic Robots plans to use it in home cleaning machines so the robots can hold simple conversations, recognise gestures and build a precise map of a living room.
NVIDIA says more than 10,000 companies are currently shipping or developing products on its Jetson family of modules, and over 3 million developers use its robotics software stack.
The module fits the same physical slot as previous Jetson Orin hardware, meaning companies that already designed products around the older chip can swap in the new one without redesigning their circuit boards.
What does this mean for ordinary people?
Not immediately much: the hardware arrives in early 2027 at the soonest, and consumer products using it will follow later still. But the direction is clear. Smarter drones could make same-day delivery more reliable. Home robots could become genuinely useful rather than frustrating. Factory machines could catch defects they previously missed.
For now, the tangible step is that AI capable of real conversation and visual understanding is moving off server farms and into the physical world, one small module at a time.
Common questions
Will this affect the price of robots or drones for consumers?
NVIDIA has not released a retail price for the Orin Nano 2 module. Entry-level Jetson hardware has historically sold in the low hundreds of dollars, but the cost of a finished consumer product depends heavily on the manufacturer.
Does the robot need an internet connection to use this AI?
No. That is the whole point of edge AI: the model runs on the device itself. A drone using Orin Nano 2 can reason about its surroundings even without a mobile signal, which matters for reliability and privacy.
When can developers actually get one?
NVIDIA has confirmed availability in the first half of 2027 for both the bare module and the developer kit, a board that lets engineers prototype new products.
