NVIDIA has announced the release of JetPack™ 7.0, the latest and most advanced software stack for the Jetson™ platform. Built to enable cutting-edge robotics and generative AI applications at the edge, JetPack 7 delivers an unprecedented foundation for developers building machines that interact with and understand the physical world.

JetPack 7.0 redefines what’s possible with Jetson by providing ultra-low latency, deterministic performance, and scalable deployment. From humanoid robots to AI systems tackling the most demanding generative workloads, JetPack 7 ensures developers have the right tools and libraries to bring ideas to life.

Key to this release is full support for the NVIDIA Jetson Thor™ platform, featuring groundbreaking performance and next-generation AI capabilities. JetPack 7.0 also introduces:

• A preemptable real-time kernel for predictable system responsiveness.
• Multi-Instance GPU (MIG) support, maximizing GPU utilization across workloads.
• An integrated Holoscan Sensor Bridge, enabling seamless sensor-to-AI pipelines.

At its core, JetPack 7 is built on Linux Kernel 6.8 and Ubuntu 24.04 LTS, ensuring long-term stability and compatibility. Its modular, cloud-native architecture integrates the latest NVIDIA AI compute stack, making it easier than ever to align Jetson development with NVIDIA’s broader AI workflows.

For developers, this means seamless interoperability, whether building robotics systems in the lab or deploying generative AI at the edge

JetPack 7 also marks a major milestone in aligning Jetson with industry standards through the Server Base System Architecture (SBSA). By adopting SBSA:

• Jetson Thor is now positioned alongside ARM server-class systems.
• Developers benefit from stronger OS support, simplified software portability, and smoother enterprise integration.
• CUDA 13.0 is now unified across all ARM targets, streamlining development and reducing fragmentation.

This alignment ensures consistency from server-class systems to Jetson Thor, bridging the gap between edge and enterprise AI.

JetPack 7.0 is powered by Jetson Linux 38.2, which brings a host of enhancements:

• Based on Ubuntu 24.04 LTS and Linux Kernel v6.8 LTS.
• Support for the Jetson AGX Thor Developer Kit and Jetson T5000 module.
• OpenRM-based stack architecture.
• Updated AI compute libraries: CUDA 13, cuDNN 9.12, and TensorRT 10.13.
• CoE (CSI over Ethernet) support via the Holoscan Sensor Bridge, enabling plug-and-play with the Eagle Camera Sensor Module LI-VB1940.
• Optimized support for CSI/GMSL via Argus and CoE via SIPL Camera API.
• NVIDIA-optimized preemptable real-time kernel for deterministic performance.

NVIDIA JetPack 7.0 launches with support for the latest Jetson platforms:

• Jetson AGX Thor Developer Kit
• Jetson T5000

Developers using these devices can immediately take advantage of JetPack 7’s new capabilities for robotics, AI, and sensor-driven applications.

• Manual flashing instructions have been updated due to SBSA architecture adoption—developers should carefully follow the updated guide.
• For reinstallation using an ISO, refer to the Getting Started Guide to avoid issues.

With JetPack 7.0, NVIDIA is setting a new standard for AI-powered edge computing. By combining next-generation hardware support, industry-standard architectures, and an updated AI stack, JetPack 7 delivers everything developers need to push the boundaries of robotics and generative AI.

For full technical details, developers should review the Jetson Linux 38.2 release notes.

The NVIDIA Jetson platform is a family of compact, high-performance computer modules built to bring AI to the edge, enabling everything from robotics and autonomous vehicles to industrial automation. Each Jetson module integrates powerful GPUs with ARM-based processors, allowing autonomous machines—such as robots, unmanned vehicles, and intelligent sensors—to operate with speed and precision directly where the data is generated.

In robotics and other autonomous systems, milliseconds can determine success or failure—whether it’s avoiding an obstacle, making a precision movement, or responding to a critical safety event. Edge AI addresses this by processing data locally, reducing latency for real-time decision-making and ensuring systems keep running even without internet connectivity. This local processing also protects privacy by keeping sensitive information on-device and reduces network load, saving both bandwidth and operating costs.

As robots and intelligent machines take on more complex tasks, from multi-sensor fusion to running large AI models, their need for computing power grows rapidly. Next-generation edge platforms must not only deliver ultra-low latency and high throughput but also support advanced AI workloads like generative AI, vision-language understanding, and autonomous navigation—all in compact, energy-efficient form factors.

The latest member of the Jetson family, Jetson Thor, was developed to meet the growing demand for greater computing power to support next-generation humanoid robots, autonomous systems and large AI models running directly on-device.

Built for demanding workloads such as generative AI and multi-sensor fusion, Jetson Thor delivers up to 7.5× higher AI performance and 3.5× better energy efficiency than AGX Orin. While AGX Orin offered ~275 TOPS, Jetson Thor surpassed it dramatically, reaching 2,070 TFLOPS (FP4). This leap in performance allows developers to run larger deep learning models, process more sensors in parallel, and achieve faster real-time control—making Jetson Thor a better choice for edge AI.

Jetson AGX Thor redefines robotic intelligence, delivering the power and efficiency needed to bring next-generation humanoid robots to life. It supports a wide range of generative AI models—from Cosmos Reason, DeepSeek, Llama, Gemini, and Qwen to domain-specific robotics models like NVIDIA Isaac™ GR00T N1.5—enabling any developer to easily experiment and run inference locally, whether with Vision Language Action (VLA) models, popular LLMs, or VLMs.

To deliver a seamless cloud-to-edge experience, Jetson AGX Thor runs the NVIDIA AI software stack for physical AI applications, including:

• NVIDIA Isaac for robotics,
• NVIDIA Metropolis for visual agentic AI, and
• NVIDIA Holoscan for sensor processing.

It also enables the creation of AI agents directly at the edge using NVIDIA agentic AI workflows such as Video Search and Summarization (VSS).

Video has become one of the most valuable sources of information in today’s connected world, powering everything from security monitoring to industrial inspection, retail analytics, and healthcare diagnostics. However, the sheer volume of video data is overwhelming—hours of footage must often be reviewed just to find a few seconds of relevant events. Without automation, this process is slow, expensive, and prone to human error.

This is where Video Search and Summarization (VSS) comes in. VSS is a powerful generative AI application designed to streamline the development of intelligent video analytics agents. Built on the NVIDIA AI Blueprint for video search and summarization, it combines vision-language models (VLMs), large language models (LLMs), and advanced computer vision to:

• Search across multiple live streams and recorded files instantly.
• Summarize video content with contextualized insights.
• Provide interactive Q&A about video footage.
• Deliver real-time alerts and notifications for critical events.
• Support audio-based cues for more comprehensive situational understanding.
• Offer REST APIs for easy integration into existing systems.

Previously, workloads of this scale were only practical in cloud environments. Now, thanks to Jetson Thor’s AI compute capacity, VSS can run at the edge. This means organizations can perform real-time, privacy-preserving video analytics without relying on internet connectivity—ideal for mission-critical applications in security, manufacturing, smart cities, and more.

Jetson Thor sits at the top of the Jetson family in terms of hardware capabilities.

• CPU: 14-core Arm Neoverse-V3AE processor for high-performance multitasking and real-time operations.
• GPU: NVIDIA’s next-generation Blackwell architecture GPU with 2,560 CUDA cores and 96 Tensor Cores, delivering massive AI compute performance.
• MIG (Multi-Instance GPU): Enables secure, isolated execution of multiple AI workloads by partitioning GPU resources in hardware.
• Specialized Accelerators: Includes a 3rd-gen Programmable Vision Accelerator (PVA), dual video encoders/decoders, and an optical flow accelerator to offload processing from CPU/GPU.
• Memory: 128 GB LPDDR5X RAM with a 256-bit interface and ~273 GB/s bandwidth—ideal for large AI models and high-resolution sensor data.
• Power: Configurable from 40 W to 130 W, supporting both low-power embedded use cases and full-performance operation.
• Connectivity:
  • QSFP slot with 4× 25 GbE high-bandwidth Ethernet for streaming data from multiple cameras or lidars.
  • Additional Multi-Gigabit Ethernet (RJ-45), multiple USB 3.2 ports, DisplayPort/HDMI outputs, and industrial interfaces like CAN/UART.

Jetson Thor runs on Ubuntu 24.04 LTS with the new JetPack 7.0 SDK, ensuring compatibility with NVIDIA’s latest AI software stack, including CUDA and TensorRT.

1. Autonomous Systems (Vehicles & Robots)
Processes LIDAR, camera, and radar data simultaneously to enable precise perception and safe decision-making. Humanoid robots and drones can perform real-time localization, SLAM, and obstacle detection with greater speed and accuracy.

2. Smart Cities & Security
Analyzes 24/7 video streams from city surveillance systems locally—without sending data to the cloud—for instant traffic management, crowd control, and threat detection. Supports real-time analysis of 4K/8K video feeds.

3. Industrial Automation
Enhances factory robotics, production line cameras, and inspection systems for defect detection, quality control, and predictive maintenance. Built for reliability in demanding industrial environments.

4. Healthcare Technologies
It powers AI-driven medical devices such as portable MRI and ultrasound systems to process images directly on-device for instant diagnostics. Surgical robots can benefit from real-time imaging and enhanced precision, while patient monitoring systems can safeguard privacy by keeping all data processing local.

Beyond these, Jetson Thor can power AI research labs, smart retail systems, agricultural automation, and much more—accelerating the shift toward smarter, faster, and more autonomous edge systems.

In summary: Jetson Thor brings supercomputer-class AI performance to the edge, making it possible to run previously cloud-only applications like Video Search and Summarization locally, in real time, and with full data privacy. This opens the door to faster, smarter, and more autonomous machines across every industry.

i2cdetect is a command-line tool used on Linux-based systems to scan for I2C devices. It’s especially useful on embedded platforms like Jetson to identify which I2C devices are connected to which bus. While some Jetson carrier boards include pinout diagrams, these diagrams don’t always clearly indicate the corresponding I2C bus numbers. With i2cdetect, you can easily discover the active buses and determine where your I2C device is connected.

Required Materials:

• Jetson Kits
• Any sensor that works with i2c
• Jumper Cables

Identify the SCL, SDA, and GND pins on your Jetson kits. You will use jumper wires to connect this i2c sensor to your Jetson device.

You can install it by entering the following command in your computer’s terminal:

UART (Universal Asynchronous Receiver/Transmitter) is a widely used communication method that allows electronic devices to talk to each other by sending data one bit at a time. Developers often use UART to help debug their systems. By connecting a UART module to their device, they can send messages from the device to an external terminal or debugger. This makes it easier to watch what’s happening inside the system in real time — such as checking variables or seeing how the program is running. Because UART works asynchronously, it doesn’t need a shared clock signal between devices, which makes it relatively simple to use for debugging tasks.

Required Materials:

• NVIDIA Jetson Kits
• Jumper Cables
• FTDI or USB TTL Converter
• Native Ubuntu host computer

Identify the RXD, TXD, and GND pins on your FTDI or USB-TTL converter. You will use jumper wires to connect this module to your Jetson device. However, one important thing to note: the connections must be crossed. This means the TX pin from Jetson goes to the RX pin on the converter, and vice versa. You can follow the table below to correctly connect Jetson’s UART pins to the converter’s pins.

Next, connect the USB end of the converter to your computer. While making these connections, do not power on the Jetson yet. You will connect the power supply in Step 8.

1. To perform debugging, we need an application called Minicom. You can install it by entering the following command in your computer’s terminal:

2. Another command we will use is dmesg, which stands for diagnostic messages. It shows system messages from the Linux kernel, such as those from device drivers.

After running this command, plug in your USB converter to your computer. You will see a log appear in the terminal, similar to the image below.

In that log, the line that mentions FTDI refers to our USB converter, and ttyUSB0 is the port it is using. We will use this port name when setting up Minicom.

3. In this step, we will configure the Minicom application. Without closing the terminal window from the previous step, open a new terminal and enter the following command:

4. After starting Minicom, go to the “Serial Port Setup” option.

5. There are three important settings to check here; Serial Device, Bps/Par/Bits, and Hardware Flow Control.

6. First, in the Serial Device section, enter the ttyUSB0 address you saw earlier in the dmesg –follow terminal.

Second, make sure the Bps/Par/Bits value is set to 115200 8N1. In our test, this value was set automatically, but if you see something different, change it to 115200 8N1.

Finally, the Hardware Flow Control option should be set to Yes.

Your final configuration should look like the example shown below.

7. After completing Step 6, press the ESC key, then select “Save setup as dfl” to save your settings. After that, exit Minicom.

Now, open a new terminal and enter the command below. This time, you will see Minicom’s main interface.

8. Now it’s time to power on your Jetson board. Once you connect the power, you will start to see messages appearing in Minicom.

When the boot process finishes, you can review the logs to check for any errors or important messages.

When diving into edge AI development with NVIDIA Jetson modules, it’s easy to focus on the powerful compute modules like Jetson Nano, Xavier NX, Orin or Thor. But it is also very important to have the right carrier board for your project.

In this post, we’ll unpack what a Jetson carrier board is, its functions, components, and how to choose the right one for your project. Whether you’re a hobbyist, engineer, or product designer, understanding carrier boards is critical to building scalable and reliable edge AI solutions.

At its core, a carrier board is a printed circuit board (PCB) that breaks out the functionality of a Jetson module and provides the necessary interfaces, power rails, and connectivity for the module to operate in the real world.

Think of the Jetson module as the “brain” — it houses the CPU, GPU, memory, and storage — while the carrier board is the “body” that connects it to the outside world.

Jetson modules are designed as System on Modules (SoMs), meaning they’re compact, self-contained compute units that require a carrier board to connect peripherals like cameras, displays, USB devices, and networking interfaces.

A Jetson carrier board performs several key roles:

• Power Rails: Regulates and distributes the correct voltage and current to the module and peripherals.
• Interface Expansion: Provides connectors for USB, Ethernet, HDMI/DisplayPort, CSI (camera), PCIe, UART, I2C, SPI, and more.
• Peripheral Support: Enables connectivity for devices like cameras, SSDs, Wi-Fi/Bluetooth modules, and sensors.
• Debugging and Development: Offers serial console access, recovery mode toggles, boot switches, and sometimes JTAG headers.
• Cooling Integration: Many boards support fan control and thermal management to keep the module within safe operating temperatures.

Here are some of the essential components you’ll find on a typical Jetson carrier board:

• Power Management ICs: Ensure proper power sequencing and conversion for the module and peripherals.
• USB/Ethernet PHYs: Handle data link-level communication for USB and network interfaces.
• Video Output Interfaces: HDMI, DisplayPort, or eDP output components for connecting external displays.
• MIPI CSI Connectors: For camera input — often with multiple lanes for high-bandwidth sensors.
• Connectors and Expansion Headers: Such as GPIO, I2C, SPI, CAN, and UART headers for integrating custom electronics.
• ESD Protection and Level Shifters: For signal integrity and protection against electrostatic discharge.
• Clock Generators: Provide stable timing signals required by some interfaces or modules.
• Microcontrollers (on some boards): Used for fan control, power sequencing, or even watchdog functionality.

A carrier board is only as good as its software support, and that’s where the Board Support Package (BSP) comes in.

The BSP is a collection of software that includes:

• Bootloader
• Linux Kernel
• Device Trees
• Drivers
• User-space utilities

It tells the Jetson module how to communicate with the hardware on the carrier board. Each board may need a custom device tree and sometimes even kernel patches to support specific peripherals or configurations.

NVIDIA provides a BSP through its L4T (Linux for Tegra) platform, but third-party carrier board vendors often release their own BSPs or overlays to ensure full compatibility.

When selecting a carrier board, several key factors come into play:

1. Module Compatibility: Not all carrier boards support all Jetson modules. The Orin NX, AGX Orin and Thor have different form factors and power consumptions.

2. Form Factor: Consider the size and layout of the board — compact boards are ideal for drones and robots, while full-sized options are better for industrial deployments.

3. I/O Requirements: Define your needs for USB ports, video outputs, CSI camera lanes, Ethernet (1GbE vs 10GbE), CAN bus, and other interfaces.

4. Thermal Design: Will your application operate in a sealed enclosure? Does it require active cooling? Make sure the carrier board supports appropriate thermal solutions.

5. Power Supply: Check input voltage ranges and power requirements. Some boards support wide input ranges or even PoE (Power over Ethernet).

6. Environmental Constraints: Industrial-grade boards may offer extended temperature ranges, shock/vibration resistance, and conformal coating.

7. Software and Community Support: Well-documented boards with an active support community or vendor-provided BSPs reduce development time and risk.

A common point of confusion is the interchangeability of Jetson modules and carrier boards. While some boards claim compatibility across multiple modules, real-world deployment can be tricky.

Key areas to check:

Pin Compatibility: Xavier NX and Orin NX share the same 260-pin connector, but Orin Nano has some functional limitations.

Mechanical Fit: Ensure the heatsink and connector layout aligns between module and carrier.

Power Delivery: Orin modules can demand more power than earlier modules. Ensure the board supports this.

BSP Compatibility: Using an Orin NX module on an older Xavier board may require BSP patches or kernel updates.

Jetson carrier boards are more than just breakout boards — they are critical enablers for deploying edge AI solutions. Whether you’re building a smart camera, autonomous robot, or industrial AI gateway, choosing the right carrier board impacts performance, reliability, scalability, and time-to-market.

Understand your project’s requirements, verify compatibility, evaluate software support, and choose a board that can grow with your system’s needs.

In this guide, I’ll walk you through the steps to prepare and flash NVIDIA Jetson Xavier NX using Auvidea’s custom carrier boards (JNX30D). This tutorial is written for users who may not be experts but want to get their Jetson up and running.

Required Materials:

• JNX30D Kit
• Micro USB Cable
• Native Ubuntu host computer

1. Download Required Files

First, download the following two archives provided by NVIDIA. These contain the Jetson Linux BSP and the root filesystem:

Jetson Linux BSP: jetson_linux_r35.6.0_aarch64.tbz2
Sample Root Filesystem: tegra_linux_sample-root-filesystem_r35.6.0_aarch64.tbz2
Auvidea BSP: JNXxxx

In this guide, I’ll walk you through the steps to prepare and flash NVIDIA Jetson Nano using Auvidea’s custom carrier boards (JNX30D / JN30D). This tutorial is written for users who may not be experts but want to get their Jetson up and running.

Required Materials:

• JNX30D / JN30D Kit
• Micro USB Cable
• Native Ubuntu host computer

1. Download Required Files

First, download the following two archives provided by NVIDIA. These contain the Jetson Linux BSP and the root filesystem:

• Jetson Linux BSP: jetson-210_linux_r32.7.1_aarch64.tbz2
• Sample Root Filesystem: tegra_linux_sample-root-filesystem_r32.7.1_aarch64.tbz2
• Auvidea BSP: JN30B/JN31/JN32/JN34/JNX30/JNX30D/JN30D

kernel_out should contain files like Image, device tree blobs, and kernel modules provided by Auvidea.

5. Recovery mode

Before flash, you must enter recovery mode. For that Connect the device to the host computer with a micro USB cable, then power up the device. If you see the Nvidia Corp. logo when you type lsusb into the terminal on your host computer, it’s in recovery mode.

In many situations, you may not have direct access to a monitor to use with your Jetson device. This can be a problem, especially when you’re working in the field or on embedded systems without a dedicated display.

This guide shows how to mirror your Jetson’s screen to a host computer (Ubuntu or Windows) using a USB HDMI capture card and OBS Studio. It’s a simple and practical way to interact with Jetson remotely using your regular PC monitor.

Required Materials:

• Nvidia Jetson Kit
• USB Hdmi Capture Card
• Native Ubuntu host computer

1. Download Required Files

First, install OBS studio app on your host computer with following instructions:

2. Capture Card Connection

Connect your usb hdmi capture card to your host computer. You will plug the Jetson’s HDMI cable into the USB-HDMI capture card’s HDMI connector and the capture card’s USB connector into your host computer.

3. Open OBS Studio APP

4. Adding Video Capture Device

Click on + button and choose video capture device

5. Video format

After adding the device, you can configure the settings as shown in the image below. After this step, you’ll see the Jetson screen on your host computer.