NVIDIA Jetson Orin Nano 2 brings physical AI to drones and robots
ainews ·
NVIDIA has unveiled the Jetson Orin Nano 2, an entry-level edge robotics computer designed to run generative AI directly on drones, robots, and vision systems. The board delivers 78 trillion operations per second, 8GB of memory, and an eight-core Arm CPU in the same compact form factor as its predecessor. NVIDIA says it provides twice the inference performance of the Jetson Orin Nano Super, while its 15-watt mode uses 40% less power than that model at equivalent performance. It supports NVIDIA’s open software stack and Jetson ecosystem, including memory-efficient large language and vision-language models such as Cosmos, Nemotron, Gemma 4, and Qwen 3. Companies including Cognex, Doosan Bobcat, and Matic are exploring applications ranging from home robots and inspection systems to delivery drones, while Matic plans to use the board in cleaning robots with conversational AI, gesture detection, mapping, and semantic understanding. Alphabet’s Wing is evaluating the hardware for more responsive and energy-efficient delivery drones, but has not announced a production deployment timeline. NVIDIA also identified numerous partners developing carrier boards, customized software, and reference designs for the platform.
ainews