NVIDIA introduces Jetson Orin Nano 2 for entry-level Edge AI and robotics
NVIDIA has announced the Jetson Orin Nano 2, a compact robotics computer designed for Edge AI applications including robots, delivery and inspection drones, and computer vision systems.
The new platform delivers up to 78 trillion operations per second (TOPS) of AI compute, with 8GB of memory and an eight-core Arm CPU. NVIDIA says it provides twice the inference performance of the previous Jetson Orin Nano Super in the same form factor, while consuming 40% less power at equivalent performance in 15W mode.
The system is designed to run AI models locally, allowing devices to process sensor data, images and language without relying entirely on cloud computing. Applications include real-time perception, navigation, object recognition and interaction with users.
Jetson Orin Nano 2 supports NVIDIA’s Jetson software ecosystem and is compatible with a range of large language and vision-language models, including NVIDIA Cosmos and Nemotron, as well as open models such as Gemma 4 and Qwen 3.
Applications across robotics
NVIDIA says more than three million developers are already working with its robotics software ecosystem. Early companies exploring the new platform include Cognex, Doosan Bobcat, Matic and Wing.
Matic Robotics is using the platform for home-cleaning robots, with applications including conversational AI, gesture recognition, mapping and autonomous navigation.
Drone delivery company Wing is also evaluating the platform for real-time AI perception and processing in its delivery drones, with the aim of improving responsiveness and energy efficiency.
A wider ecosystem of companies, including AAEON, ADLINK, Advantech, Aetina, Antmicro, Auvidea, Seeed Studio and Connect Tech, is developing carrier boards, hardware platforms and software solutions based on Jetson technology.
Availability
The NVIDIA Jetson Orin Nano 2 module and developer kit are expected to be available in the first half of 2027
