Nvidia Jetson Orin Nano

The NVIDIA Jetson Orin Nano is a next-generation AI computing module that delivers up to 40 TOPS of AI performance in a compact and energy-efficient form factor. It is built for applications requiring high-performance edge AI, such as autonomous robots, drones, and embedded vision systems.

Powered by an 8-core Arm Cortex-A78AE CPU and an Ampere GPU with 1024 CUDA cores and 32 Tensor Cores, the Orin Nano can handle demanding AI models for perception, navigation, and real-time decision-making. It supports a wide range of AI frameworks, including TensorFlow, PyTorch, and ROS, and runs on the JetPack SDK, providing tools and libraries for accelerated computing.

In mobile robotics, the Jetson Orin Nano enables advanced features like real-time object detection, SLAM, path planning, and sensor fusion, significantly enhancing robot autonomy and performance while maintaining low power consumption.

Key Specifications:

• CPU: 6-core or 8-core Arm Cortex-A78AE (depending on variant)
• GPU: NVIDIA Ampere architecture with 1024 CUDA cores + 32 Tensor Cores
• AI Performance: Up to 40 TOPS
• Memory: 8 GB or 4 GB LPDDR5
• Storage Interface: microSD, NVMe (via carrier board)
• Connectivity: Gigabit Ethernet, USB 3.2 (via carrier board)
• Power Consumption: 7W to 15W configurable
• Software: JetPack SDK, supports TensorRT, cuDNN, CUDA, ROS 1/2
• Form Factor: 70 x 45 mm module

The Jetson Orin Nano is an ideal AI accelerator for mobile robots like Leo Rover, enabling complex AI workloads directly on the robot without cloud dependency.

Check the integration manual here:

https://docs.fictionlab.pl/integrations/noetic/computing-devices/nvidia-jetson