Synaptics has introduced its new 461x family of wireless connectivity modules, which support the Matter standard, as demonstrated at Embedded World 2025. The demonstration was led by Anand Roy, Senior Product Line Manager for Wireless Connectivity, showcasing the Astra development kit. The kit includes Synaptics’ compact 461x module, designed for controlling smart home devices like smart bulbs. The full range of Synaptics’ products and capabilities can be explored further on their official website: https://www.synaptics.com.

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

The showcased device utilizes the Matter connectivity standard, allowing seamless interoperability across various ecosystems. Matter compliance ensures compatibility between smart home devices from different manufacturers, streamlining user experience and device management. The Astra dev kit controls a smart light bulb, demonstrating real-time interactions and responsiveness via an intuitive application running on a Wi-Fi-connected tablet.

Synaptics’ 461x module supports both Zigbee and Thread protocols, which operate within the IEEE 802.15.4 standard. These low-power wireless technologies are essential for reliable connectivity and efficient device communication in home automation networks. By combining Matter with Zigbee and Thread support, the module ensures versatile deployment scenarios for developers and manufacturers of IoT products.

During the demonstration, the application controlled the connected smart bulb effortlessly. Actions included toggling the bulb’s power, adjusting brightness levels, and altering colors from orange to yellow and blue. The intuitive controls provided by the smart app highlight the usability enhancements enabled by Synaptics’ wireless connectivity modules.

Moreover, Synaptics emphasizes the importance of multimodal control options, demonstrating the 461x module’s capability in handling voice recognition and audio events. This feature expands user interactions beyond conventional apps, enabling voice-based commands for greater convenience in smart home environments. Such capabilities underline Synaptics’ commitment to enhancing smart home automation through versatile and accessible technologies.

The Astra development kit not only illustrates practical use-cases but also provides developers with essential tools for rapid prototyping and development of Matter-compatible IoT devices. The comprehensive functionality embedded in the 461x series processors accelerates the integration of voice-controlled applications into consumer electronics, significantly reducing time-to-market.

Synaptics’ demonstration at Embedded World 2025 underscores the growing industry focus on interoperability and ease-of-use in smart home environments. As consumer adoption of IoT devices continues to grow, Synaptics’ Matter-compatible modules offer significant potential for developers and device manufacturers seeking reliable, scalable connectivity.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

Synaptics has developed an innovative approach to integrating large language models (LLMs) into household appliances, demonstrated through a prototype dishwasher interface. By extracting common user inquiries from a dishwasher manufacturer’s user guide, they created a system capable of understanding and responding to voice commands without requiring internet connectivity. This offline functionality ensures user privacy and reliability.

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

The core of this system is the Synaptics SL1680 processor, a highly integrated AI-native system-on-chip (SoC) optimized for multi-modal consumer, enterprise, and industrial IoT workloads. The SL1680 features a quad-core Arm® Cortex®-A73 64-bit CPU subsystem, a multi-TOPS neural processing unit (NPU), and a high-efficiency GPU for advanced graphics and AI acceleration. These components enable efficient on-device processing of complex AI tasks, such as natural language understanding and speech recognition. citeturn0search1

In the prototype, the system performs speech-to-text conversion to interpret user queries. It then vectorizes these queries and matches them against a pre-processed set of frequently asked questions using the NPU’s capabilities. Once the best match is identified, the system generates a voice response through text-to-speech synthesis, providing users with immediate assistance. For example, when asked, “How can I put plastic on my dishwasher?” the system responds with guidance on placing dishwasher-safe plastics on the top rack to avoid melting.

This integration of LLMs into appliances like dishwashers offers potential benefits beyond user convenience. Manufacturers could reduce the volume of calls to customer service centers by enabling appliances to address common user issues directly. Additionally, this technology could be applied to other devices, such as set-top boxes, to assist users in troubleshooting without external support.

The SL1680’s architecture supports running multiple AI models in parallel, allowing for a range of functionalities within a single device. This flexibility means that while the current implementation focuses on specific use cases, future developments could expand the system’s capabilities without significant hardware changes. For instance, users might issue commands like “Do it in a quick mode” without pressing any buttons, streamlining appliance operation.

Localization is another advantage of this technology. The system can be programmed to support multiple languages and understand various accents, making it adaptable to diverse markets. This adaptability ensures that users worldwide can interact naturally with their appliances, enhancing the overall user experience.

Updating the system with new information or responses is straightforward. Manufacturers can deploy updates over the internet or via mobile devices, ensuring that appliances remain current with the latest user guides and troubleshooting procedures. This ease of update allows for continuous improvement of the system’s responsiveness and accuracy.

The cost implications of integrating such advanced AI capabilities into appliances are manageable. Since the SL1680 SoC is designed for efficiency and performance, manufacturers can incorporate these features without substantial increases in production costs. This balance ensures that consumers receive enhanced functionality without a significant price hike.

Incorporating LLMs into household appliances represents a significant step toward more intuitive and user-friendly home environments. By leveraging Synaptics’ SL1680 processor, manufacturers can deliver smart appliances that not only perform their primary functions but also assist users through natural language interactions, setting the stage for a new era of intelligent home devices.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

Synaptics showcased its Astra Machina Foundation Series developer kit at Embedded World 2025, part of the Dev Kit Zone organized by Embedded Computing Design. Dave Garrett, VP of Technology and Innovation at Synaptics, presented the Astra Machina, highlighting its substantial potential for developers working with edge computing, IoT, and neural networks. The Astra Machina kits include high-performance SL-Series processors featuring ARM Cortex A-class CPUs, GPUs, and integrated Neural Processing Units (NPUs), delivering up to eight TOPS of neural acceleration for advanced machine learning tasks.

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

The Astra Machina development kits showcased at Embedded World 2025 run a Linux-based platform built on Yocto, accessible via Synaptics’ Embedded Software SDK (ESSDK) on GitHub. This allows developers quick integration with Python, HuggingFace models, and popular ML frameworks, significantly speeding up the prototyping process. The kits come ready with USB peripherals, GPIO, USB, I²C, I2S, HDMI, and display interfaces, making it easy to connect sensors, cameras, microphones, and other external peripherals essential for comprehensive edge applications.

Dave Garrett emphasized the importance of practical, hands-on experience, encouraging developers to experiment broadly with these kits to maximize their potential. At the Dev Kit Zone, hosted by Embedded Computing Design, Synaptics demonstrated real-world applications, including industrial-grade computer vision for automated pill sorting on conveyor systems. The demonstration showed Astra Machina’s capability to perform real-time, accurate image recognition and object classification directly at the edge, underscoring its suitability for various smart industrial and consumer applications.

Wireless connectivity is another key component of Astra Machina kits. Synaptics integrates their proprietary Wi-Fi and Bluetooth modules, enabling seamless IoT connectivity essential for diverse applications from smart homes to industrial automation. This integrated wireless capability helps developers easily deploy comprehensive IoT ecosystems without the need for additional complex hardware configurations.

Synaptics maintains a strong commitment to open-source software and has collaborated with Google Research on open-source compilers for machine learning networks. This partnership supports extensive compatibility with popular neural network frameworks, enabling developers to rapidly deploy sophisticated ML models across Synaptics’ diverse hardware platforms. The intent is clear: facilitating interoperability and simplifying developer experiences by avoiding proprietary lock-ins.

Developers interested in the Astra Machina Foundation Series can purchase kits immediately from authorized distributors like Mouser or directly via Synaptics’ developer portal (https://www.synaptics.com). Garrett emphasized the ease of setup, claiming developers can begin running neural networks within an hour of unboxing. He encouraged users to actively experiment, tweak, and innovate, pointing out that such iterative, hands-on approaches often lead to the most successful and impactful IoT products.

Beyond Astra Machina, Synaptics also previewed upcoming Reference Design Kits (RDKs), targeting ultra-low-power applications, capable of performing visual inference tasks in the milli-amp range. These kits, suitable for battery-powered applications, complement the higher-end performance seen in Astra Machina, offering flexible options to cater to varying edge-computing needs.

Overall, Synaptics’ participation in Embedded World 2025 highlighted its strategic push into powerful, open, and accessible development kits, designed explicitly to accelerate real-world innovation in IoT and edge computing technologies.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

Jamie from 42 Technology (https://www.42technology.com) showcases their application for automated line clearance at Embedded World 2025. Utilizing embedded edge AI technology, this demonstration addresses real-time quality control and anomaly detection specifically designed for pharmaceutical manufacturing processes. The system employs industrial-grade cameras and Synaptics’ Astra SL1680 edge AI processor to monitor pill production lines, accurately detecting contaminants and process irregularities.

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

The demonstration specifically captures images of pills moving on a conveyor belt, analyzing these visuals instantly to identify anomalies based on color differentiation. Though color is the demonstrated differentiator here, the system’s AI capabilities are flexible, capable of identifying various anomalies or contaminants that pose significant risks in pharmaceutical production and other industrial applications.

42 Technology has spearheaded the design and conceptualization of this demonstration. Leveraging their expertise in manufacturing processes, instrumentation, and systems engineering, they collaborated closely with Synaptics, using the Astra SL1680 processor at the system’s core. The Astra platform, recognized for its edge AI performance, integrates seamlessly with Bala industrial camera systems to deliver precise imaging data for analysis.

A critical partner in this collaboration is Arcturus Networks, part of Synaptics’ ecosystem. Arcturus provided essential support in developing the machine learning aspects of the project, enabling accurate anomaly detection and enhancing the overall reliability and responsiveness of the embedded AI solution.

The showcased conveyor system replicates real-world pharmaceutical manufacturing environments. Pills are automatically ejected onto a production line, where real-time image analysis is conducted. The edge AI technology quickly counts pills, identifies irregularities, and logs any contaminants, providing immediate visual feedback and timestamped records. This capability allows operators to review anomalies rapidly and take prompt corrective action.

This solution addresses a common challenge in industrial manufacturing: ensuring line clearance and eliminating safety risks associated with contaminants or leftover packaging materials. The demonstration specifically illustrates detection of anomalies such as residual pill bottles or cartons that could otherwise remain unnoticed. Timely identification of these irregularities helps maintain safety standards, regulatory compliance, and operational efficiency.

This project highlights the effectiveness of collaborative development. It combines 42 Technology’s industrial expertise and integration skills, Synaptics’ specialized edge AI hardware, Bala’s robust vision systems, and Arcturus Networks’ sophisticated machine learning algorithms. Such multidisciplinary collaboration ensures that the final system is both reliable and versatile, suitable for diverse manufacturing contexts beyond pharmaceuticals.

As showcased at Embedded World 2025, this technology represents an effective use of edge AI in enhancing industrial safety and quality assurance. Its flexibility and adaptability to various anomaly detection scenarios illustrate a practical implementation of machine learning in manufacturing, marking a notable development in embedded industrial automation.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

At Embedded World 2025, Synaptics showcases its Veros brand, emphasizing reliability in wireless communication tailored for the Internet of Things (IoT). The Veros lineup integrates AI-native compute capabilities within connectivity solutions, aiming to enhance performance and efficiency across IoT applications.

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

A notable addition to the Veros series is the 461x family, a triple-combo system-on-chip (SoC) that consolidates Wi-Fi, Bluetooth, and Zigbee/Thread functionalities into a single chip. This integration reduces design complexity and power consumption while maintaining robust performance across various ranges. Demonstrations showcased the chip’s capability to sustain approximately 40 megabits per second throughput even in congested environments, highlighting its efficiency and reliability.

The convergence of these three wireless technologies—traditionally implemented as separate components—into a unified SoC represents a significant advancement in IoT device design. By streamlining these functionalities, Synaptics addresses the growing demand for compact, energy-efficient, and high-performance solutions in the IoT landscape.

The Veros 461x’s AI-native compute capabilities enable contextually aware processing, allowing devices to make intelligent decisions at the edge without relying heavily on cloud services. This feature is particularly beneficial for applications requiring real-time responsiveness and enhanced security.

Synaptics’ commitment to advancing edge AI and wireless connectivity is evident in the Veros 461x family. By integrating multiple wireless protocols and AI processing into a single chip, Synaptics provides a versatile solution for developers aiming to create innovative and efficient IoT products.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

Renesas Electronics, a leader in embedded semiconductor solutions, showcased its GreenPAK™ programmable mixed-signal products at Embedded World 2025. GreenPAK devices enable engineers to integrate analog and digital functions into a single design, optimizing component count, board space, and power consumption. These cost-effective, non-volatile memory (NVM) programmable devices are ideal for applications ranging from handheld devices to automotive systems.

A key feature of GreenPAK is its integrated development environment, which allows designers to combine digital and analog blocks seamlessly. Using the GreenPAK Designer Software and development kits, custom circuits can be created and programmed in minutes, facilitating rapid prototyping and iterative design processes.

Renesas also introduced the SLG47105, a GreenPAK device equipped with digital resources and one-time programmable memory. This component is tailored for applications requiring precise digital control, such as segment displays and digital alarm clocks. Additionally, the SLG47105 features an H-bridge output, enabling efficient DC motor control with capabilities like overcurrent protection and constant speed maintenance, even under varying voltage conditions.

The versatility of GreenPAK extends to analog applications as well. For instance, the AN-O-PACK family integrates rich analog features, allowing for functions like light intensity tracking using simple sensor arrays. Other applications include DC-DC boost converters and buzzer drivers, demonstrating GreenPAK’s capability to manage power efficiently while maintaining a compact form factor.

Renesas provides comprehensive development tools to support GreenPAK designers. The GreenPAK Advanced Development Board (SLG4DVKADV) enables the development of custom designs using GreenPAK Mixed Signal ICs, allowing for rapid prototyping and testing. citeturn0search12 This platform supports a wide range of GreenPAK ICs, offering flexibility to designers working on diverse applications.

At Embedded World 2025, Renesas also announced Renesas 365, powered by Altium, a cloud-based platform designed to unify silicon, software, and hardware development. This solution aims to streamline electronics system development from silicon selection to system lifecycle management, enhancing collaboration and efficiency across engineering teams. citeturn0search1

In summary, Renesas’ GreenPAK programmable mixed-signal products and the introduction of Renesas 365 represent significant advancements in embedded system design. These innovations provide engineers with the tools to create efficient, compact, and versatile solutions across a wide range of applications, from consumer electronics to industrial automation.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

At Embedded World 2025, CODICO, a prominent European distributor for Synaptics, showcased a range of advanced products at their booth. Among the highlights were Synaptics’ Astra Machina development kits, the SL1680 processor, and the newly introduced SR110 microcontroller unit (MCU). These offerings underscore CODICO’s commitment to delivering cutting-edge solutions in the embedded systems market.

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

The Astra Machina development kits are designed to facilitate rapid prototyping and development for IoT applications. Featuring modular designs, these kits incorporate swappable core compute modules, a common I/O board, and support for various daughter cards, offering flexibility and scalability for developers.

Central to these kits is the SL1680 processor, a high-performance system-on-chip (SoC) optimized for multimodal consumer, enterprise, and industrial IoT workloads. It boasts a quad-core Arm Cortex-A73 CPU, a multi-TOPS neural processing unit (NPU), and a high-efficiency GPU, enabling advanced graphics and AI acceleration. The SL1680 also integrates multimedia accelerators for image signal processing, 4K video encode/decode, and audio processing, making it a versatile solution for complex IoT applications.

The newly launched SR110 MCU extends Synaptics’ Astra platform by delivering high-performance, AI-native, multimodal compute capabilities. Based on the Arm Cortex-M55 core with Helium technology and the Arm Ethos-U55 NPU, the SR110 supports multiple tiers of operation—performance, efficiency, low-power sensing, and always-on modes. This architecture allows for intelligent processing at varying power levels, making it suitable for applications requiring context-aware computing.

A notable demonstration at the CODICO booth showcased the SR110’s capability to measure heart rate via a video stream. By capturing skin variations with each heartbeat, the system calculates the heart rate through frame-by-frame analysis. This innovative application exemplifies the potential of Synaptics’ processors in health monitoring and similar fields.

CODICO’s role extends beyond distribution; they provide comprehensive support to customers from the initial idea through to mass production. Their support engineers, experienced in hardware development, collaborate with a network of software companies to assist clients in bringing products to market efficiently.

For developers interested in these technologies, CODICO offers the Astra Machina kits and the SR110 micro kits through their sample shop. The Astra Machina kit is currently available from stock, while the SR110 micro kit is expected to be available starting in May.

By partnering with Synaptics, CODICO continues to provide state-of-the-art components that empower developers to create innovative IoT solutions. Their presence at Embedded World 2025 highlights their dedication to advancing embedded technologies and supporting the evolving needs of the industry.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

At Embedded World 2025, Toradex presented a comprehensive suite of embedded computing solutions, emphasizing their dedication to simplifying product development across various industries. A notable demonstration featured a customer’s innovative wheelchair capable of navigating stairs, underscoring Toradex’s role in providing robust Linux-based computing platforms that power intricate mechatronic systems.

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

In their AI segment, Toradex showcased the capabilities of the Aquila AM69 System on Module (SoM), equipped with four Neural Processing Units (NPUs). This configuration efficiently processed inputs from eight simultaneous camera feeds, highlighting the platform’s robust AI processing capabilities suitable for demanding applications.

Another real-world application demonstrated was the deployment of the Verdin iMX8M Plus in marine environments. This system performed semantic segmentation to detect and map oceanic debris, illustrating the adaptability of Toradex’s solutions to rugged and mission-critical scenarios.

A standout exhibit was the T-Bot, a robot exemplifying heterogeneous multicore processing. It utilized a Cortex-A core running Linux alongside an M core responsible for real-time balancing tasks. This architecture ensured continuous operation even in the event of a Linux system crash, emphasizing system reliability.

Toradex also addressed the forthcoming EU Cyber Resilience Act, highlighting their proactive measures to assist clients in achieving compliance. Their offerings include secure boot processes and continuous vulnerability monitoring, ensuring products meet stringent security standards.

The company’s collaboration with Texas Instruments was evident in their support for various TI starter kits, such as the AM62 and AM62P. This partnership facilitates secure over-the-air updates and subsystem enhancements, streamlining development processes for clients.

An overview of Toradex’s product lineup revealed a focus on scalability and compatibility. The Verdin family, for instance, offers pin-compatible modules, allowing seamless transitions between different processors and performance levels. This flexibility enables tailored solutions without extensive redesigns.

Additionally, Toradex’s commitment to open-source principles was showcased through their provision of design files for carrier boards. Clients can download, modify, and manufacture these designs, accelerating development cycles and reducing time-to-market.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

At Embedded World 2025, MiTAC unveiled a suite of advanced embedded solutions tailored for diverse industrial applications. Central to their showcase was an AI training model and deployment software kit, built on an Intel platform integrated with the Intel GT tool kit. This configuration facilitates efficient AI model deployment and device management, streamlining edge AI implementation.

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

MiTAC also demonstrated a compact AI edge device featuring a Hailo-8 AI processor, delivering up to 26 tera operations per second (TOPS). This integration offers substantial AI acceleration capabilities within a small form factor, making it suitable for applications requiring high-performance AI inference at the edge.

In the realm of fleet management, MiTAC presented a comprehensive system equipped with dual cameras—one monitoring the road and the other the driver. Leveraging algorithms for driver monitoring, the system detects behaviors such as phone usage, distraction, or drowsiness. Data is transmitted to a web platform, enabling fleet managers to oversee driver behavior and vehicle status in real-time.

MiTAC’s booth also featured various embedded boards, including ARM-based solutions like the NXP i.MX 8M and Intel platforms such as Tiger Lake UP3 and Alder Lake. Notably, the Alder Lake generation incorporates a dedicated neural processing unit (NPU), enhancing AI inference capabilities up to 22 TOPS, thereby addressing the growing demand for AI at the edge.

Additionally, MiTAC showcased self-service kiosks equipped with dual screens—one for advertisements and another for interactive ordering. Integrated cameras analyze customer demographics, such as age and gender, to deliver targeted advertising. These kiosks also feature thermal printers, barcode scanners, and payment modules, providing a comprehensive solution for retail environments.

Based in Taiwan, MiTAC continues to leverage its extensive manufacturing experience to deliver innovative embedded solutions. Their participation in Embedded World 2025 underscores their commitment to advancing technologies in AI, edge computing, and industrial automation.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

At Embedded World 2025, David Steele from Arcturus presented a line inspection demonstration developed in collaboration with 42 Technology (42T). The system operates on Synaptics’ SL1680 processor, integrating advanced object detection and color analysis to identify pills and detect contaminants on a conveyor belt. The SL1680’s architecture includes a quad-core Arm® Cortex®-A73 CPU and a multi-TOPS Neural Processing Unit (NPU), facilitating efficient edge AI processing.

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

The demonstration utilizes a YOLOv8 model for object detection, specifically trained on a custom dataset to recognize pills. By leveraging Synaptics’ toolkit, the model’s preprocessing is executed directly on the NPU, reducing CPU load and optimizing system performance. This allocation allows the CPU to handle visualization and presentation tasks more effectively.

Integrating natural language processing (NLP) capabilities, such as ChatGPT, into such systems could enhance user interaction by enabling queries about anomaly correlations or failure statistics. This would involve adding another model to the existing ensemble, a feasible extension given the system’s modular design.

Arcturus employs an MLOps framework that facilitates continuous model improvement directly at the edge. This process involves collecting data from the operational device, building new datasets, training updated models, and comparing their performance against existing ones. Successful models can then be deployed in real-time, ensuring the system adapts to evolving operational conditions.

The application of AI in industrial inspection is poised to enhance analysis capabilities significantly. By deploying cost-effective models on efficient hardware like the SL1680, industries can achieve substantial improvements in inspection accuracy and speed. This advancement represents a shift from legacy algorithms to more sophisticated AI-driven solutions.

Arcturus is actively engaged in multiple AI projects, with approximately six initiatives currently underway. The rapid pace of AI innovation presents both challenges and opportunities, and the team is enthusiastic about exploring new use cases, particularly in edge computing environments.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

At Embedded World 2025, Forlinx Embedded presented their extensive portfolio of system-on-modules (SoMs) and single board computers (SBCs), designed to streamline client projects across various industries, including industrial automation, electronics, and medical equipment. Their range includes solutions based on prominent architectures like RISC-V, ARM, and products powered by key semiconductor partners such as NXP, Texas Instruments, and Rockchip. More details on their portfolio are available at [https://www.forlinx.net].

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

One of the highlights from Forlinx Embedded at the show was the introduction of their RISC-V-based System-on-Module, reflecting a growing industry trend toward open-source hardware architectures. By leveraging RISC-V, Forlinx provides developers flexibility and efficient integration paths for applications demanding customization and low-power performance.

A major spotlight at their booth was the FET-MX9352-C SoM, powered by NXP’s latest i.MX93 processor. This module incorporates a dual-core ARM Cortex-A55 processor alongside a Cortex-M33 coprocessor, effectively targeting real-time processing tasks and energy-sensitive applications. The module is optimized for diverse sectors including medical, industrial automation, and smart electronics, showcasing versatility and broad application scope.

Forlinx highlighted their long-standing relationship with NXP Semiconductors, noting their position as China’s largest distributor of NXP’s ARM-based solutions. This partnership has enabled them to develop widely adopted products, with extensive deployments in sectors that require reliability and performance, such as industrial automation, healthcare, and automotive markets.

Additionally, Forlinx presented modules based on Rockchip processors, notably featuring the RK3588 SoM. This SoM integrates an octa-core CPU comprising four Cortex-A76 and four Cortex-A55 cores, providing robust performance capabilities suitable for AI-driven applications and multimedia processing. With up to 16GB LPDDR4x RAM and comprehensive support for Linux and Android, it meets the needs of sophisticated edge computing scenarios.

The company also discussed their involvement with Texas Instruments, highlighting the enduring popularity of TI’s platforms within the electronics sector. By integrating TI’s robust and proven technologies, Forlinx ensures that their SoMs can be readily adopted in critical embedded solutions, particularly in the industrial and electronics markets, benefiting from TI’s established ecosystem and broad compatibility.

Forlinx employs a modular approach in their products, aiming to significantly reduce development complexity for their customers. Their commitment to providing compact form-factor solutions was evident in the demonstration of smaller, highly integrated boards, allowing developers greater versatility in design and deployment for compact embedded systems.

Forlinx Embedded’s presence at Embedded World 2025 demonstrated their strategic focus on collaboration, robust technology platforms, and the importance of adaptability in the embedded technology landscape. Through consistent partnerships and technical expertise, they continue to facilitate efficient and scalable development across numerous industrial applications.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

Renesas presented its latest developments in industrial automation at Embedded World 2025, highlighting the capabilities of its new PROFINET SDK tailored for RZ/T2M and RZ/N2L microprocessors. The PROFINET SDK, now available for download on Renesas’ official website https://www.renesas.com enables both PROFINET RT and IRT communication, vital for real-time industrial automation tasks. This demo prominently featured the integration of Renesas’ hardware with Siemens PLC controllers, demonstrating high-performance, deterministic industrial networking capabilities.

The RZ/T2M, specifically designed for industrial Ethernet applications, features a dual-core architecture, where one core manages communication, and the second oversees real-time operations, such as motor control. In contrast, the RZ/N2L serves as a compact single-core alternative optimized for applications requiring efficient I/O integration and master-device communication. It excels as an IO-Link master, seamlessly communicating with sensors and actuators and managing data flow within industrial networks.

In this Embedded World demonstration, Renesas exhibited the combined functionality of the RZ/N2L as an IO-Link master, connecting sensors and actuators efficiently to the central PLC via IO-Link and PROFINET protocols. The showcased quad-channel IO-Link master solution was complemented by software solutions from partner TMG, emphasizing seamless integration with existing industrial systems.

Renesas also demonstrated real-time Linux capabilities on the RZ/T2M device, highlighting its ability to run CODESYS PLC software on a Linux RT environment. This setup showcased practical use in industrial network applications, emphasizing flexibility and compatibility with real-world automation scenarios.

The demo featured various sensor-related applications, including sensor signal conditioning ICs and MCU-based solutions communicating over IO-Link. These sensors facilitated analog signal processing, digital IO, and real-time transmission of data to the central control unit, providing a comprehensive representation of the end-to-end capabilities in Renesas’ portfolio.

Additionally, Renesas displayed several practical applications, such as a real-time sensor evaluation setup that counted sensor events, visibly displayed on an integrated HMI interface. The hardware and software ecosystem presented ensured accurate signal conditioning and robust performance, which are essential requirements in industrial automation environments.

A significant advantage highlighted at Embedded World 2025 was Renesas’ capability to deliver the lowest cycle times within PROFINET’s IRT communication, positioning their solutions competitively for demanding industrial environments like servo drives and automated control systems.

Overall, the Renesas demonstration at Embedded World 2025 underscored their comprehensive ecosystem approach, providing tailored software, robust hardware, and partner-supported integrations essential for modern industrial automation projects.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

At Embedded World 2025, NXP Semiconductors showcased a diverse array of technologies, emphasizing advancements in automotive, industrial, and smart home domains. A prominent feature of their booth was the NXP Partner Wall, displaying 28 ecosystem partners’ application-specific demonstrations across sectors like automotive and industrial. Notably, some demos integrated multiple partners, highlighting collaborative solutions in wireless connectivity and sensor integration.​

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

In the ‘Brighter Places’ section, NXP presented innovations targeting building automation. A key demonstration featured building control systems managing valve operations within commercial infrastructures, underscoring NXP’s commitment to enhancing energy efficiency and operational control in modern buildings.​

The ‘Brighter Journeys’ area focused on automotive technologies. Central to this was the introduction of the S32K5 microcontroller unit (MCU), designed to support scalable vehicle architectures. The S32K5, built on a 16nm FinFET process, features Arm Cortex CPU cores running up to 800 MHz and offers power-efficient application performance. It includes optimized accelerators for network translation, security, and digital signal processing, along with an integrated Ethernet switch core, enhancing networking solutions and software reuse. ​

Another automotive highlight was the ultra-wideband (UWB) technology demonstration. Beyond enabling keyless car access, UWB facilitates applications like presence detection, child occupancy sensing, and replacing traditional kick sensors for trunk access. Its capability to detect breathing patterns also addresses safety concerns, such as identifying unattended animals in vehicles.​

NXP also showcased a digital connected cluster tailored for two-wheelers, emphasizing the evolution of motorcycle dashboards into comprehensive information centers. Collaborating with the Fraunhofer Institute, NXP introduced an infotainment system capable of 360-degree sound detection. This system alerts drivers to specific sounds, like bicycle bells, enhancing situational awareness and safety.​

In the ‘Brighter Lives’ segment, NXP addressed smart home innovations. A notable exhibit was the AI-enhanced healthcare demo, featuring a home controller interfacing with smart devices to monitor health metrics. Capabilities include fall detection and vital sign monitoring through wearable technology, enabling real-time alerts to authorities and healthcare providers in emergencies.​
nxp.com

Additionally, NXP highlighted a monitoring dashboard designed for home environments, providing users with comprehensive insights into their household systems. This aligns with the growing trend of integrating intelligent monitoring solutions to enhance home safety and efficiency.​

Overall, NXP’s presence at Embedded World 2025 underscored their dedication to advancing technologies across various sectors, focusing on safety, efficiency, and enhanced user experiences.​

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

At Embedded World 2025 in Nürnberg, Hailo presented its latest advancements in AI processing, focusing on the Hailo-15 AI Vision Processors. citeturn0search0 These processors are designed to enhance edge devices with robust AI capabilities, enabling real-time data processing directly on the device.

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

One notable demonstration featured the integration of the Hailo-15 processor into drones developed in collaboration with System Electronics. These drones showcased advanced object and face detection capabilities, emphasizing the processor’s high performance and low power consumption—critical factors for extending battery life in aerial applications.

Another highlight was the NG Cam smart camera, equipped with the Hailo-15 processor. This device demonstrated the ability to perform zero-shot learning using the CLIP model, allowing it to recognize and describe objects without prior specific training. For instance, the camera could identify a person wearing glasses by processing the input text “man with glasses,” showcasing the versatility of AI applications in real-world scenarios.

In partnership with SolidRun, Hailo introduced a System on Module (SoM) featuring the Hailo-15H processor. This compact module delivers up to 20 TOPS (Tera Operations Per Second) and supports high-resolution imaging, including 4K video at 60 frames per second. Its robust design ensures reliable operation across various industrial environments, making it suitable for applications in security, industrial automation, and smart cities.

The Hailo-15 processor also enhances image quality through AI-driven features such as low-light denoising and high dynamic range (HDR) processing. Demonstrations highlighted the processor’s ability to improve image clarity in low-light conditions and manage high-contrast scenes effectively, ensuring that subsequent analytics, like optical character recognition (OCR), yield more accurate results.

Hailo’s commitment to edge AI extends to the automotive sector. At CES 2025, they showcased integrations of their processors in advanced driver-assistance systems (ADAS), utilizing multiple sensor modalities, including cameras, LiDAR, and radar. These integrations aim to enhance vehicle safety and autonomy by enabling real-time perception and decision-making on the edge.

Furthermore, Hailo’s processors are facilitating the deployment of large language models (LLMs) on edge devices. The upcoming Hailo-10 accelerator, expected to be available later this year, is designed to run models like GPT and Stable Diffusion directly on devices, ensuring low-latency performance and enhanced privacy by keeping data processing local.

Through collaborations with various partners, Hailo continues to push the boundaries of AI at the edge, offering scalable and efficient solutions across multiple industries. Their participation in events like Embedded World 2025 underscores their dedication to advancing edge AI technologies.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

Octavo Systems, a leader in System-in-Package (SiP) technology, presented its latest high-density integration solutions at Embedded World 2025 in Nuremberg. Their SiP approach integrates microprocessors, DDR memory, power management, and passive components into a compact BGA package, simplifying PCB design while enhancing performance. By eliminating complex DDR routing and power sequencing, Octavo enables engineers to focus on application innovation. Their products span industries from real-time audio processing to robotics and industrial automation. https://octavosystems.com

One standout demo featured Chaos Audio’s digital multi-effects pedal, leveraging Octavo’s SiP for real-time, ultra-low-latency audio processing. The pedal replaces traditional analog effect chains with a software-driven system, controlled via Bluetooth. Octavo’s integration allowed Chaos Audio to focus on DSP algorithms rather than complex hardware, solving long-standing latency issues in digital audio processing.

Olive Robotics showcased a modular robotics kit powered by Octavo’s OSD32MP1, built around the STMicroelectronics STM32MP1 microprocessor. Running the Robot Operating System (ROS) on Linux, the kit distributes processing across multiple compute nodes, optimizing AI-driven motion tracking. Octavo’s SiP enabled Olive Robotics to cut development time from 18 months to three, drastically accelerating time-to-market.

Octavo introduced the OSD62, integrating the Texas Instruments AM62 quad-core ARM Cortex-A53 with 2GB DDR4 into a single SiP. The result is a 70% PCB space reduction, enabling four-layer designs without complex routing. Similarly, the OSDZU3, based on the AMD (formerly Xilinx) Zynq UltraScale+ MPSoC, consolidates 15 power rails into a single 5V input, simplifying FPGA-based system design. Both SiPs reduce cost and complexity while enabling high-performance computing.

Their commitment to accessibility extends to open-source hardware designs, providing full schematics and PCB layouts. Engineers can integrate SiP technology without dealing with DDR complexity or power sequencing. Octavo’s solutions support everything from rapid prototyping to full-scale production, optimizing thermal performance through advanced die stacking and substrate-level heat dissipation.

One demo highlighted an STMicroelectronics-based SiP running Linux on a zero-layer PCB setup, demonstrating how Octavo’s SiP solutions enable ultra-compact embedded systems with minimal external components. Another featured the integration of Octavo’s SiP in an industrial torque wrench, tracking torque application for manufacturing quality control via IoT connectivity.

Octavo’s roots in Texas Instruments are evident in its leadership, including co-founder Gene Frantz, a pioneer in DSP development. His vision for SiP democratization has positioned Octavo as a key enabler of compact, high-performance embedded computing, making previously impractical form factors achievable.

Their SiP solutions transform embedded design, from AI-driven robotics to real-time audio and industrial automation. Octavo’s presence at Embedded World 2025 underscored the growing demand for compact, high-performance, rapidly deployable systems, further cementing SiP as a crucial technology for next-generation computing.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

At Embedded World 2025 in Nuremberg, Germany, embedUR Systems, a trusted software partner of Synaptics, showcased their expertise in embedded software and Edge AI solutions. citeturn0search4 They presented multiple AI models operating on Synaptics’ AI-native hardware, demonstrating their capability to optimize and deploy AI applications effectively.

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

One notable demonstration was the “crowd sensor,” utilizing Synaptics’ privacy sensor and a camera to count individuals in real-time. This setup highlights the potential of integrating AI with sensor technology to achieve accurate crowd monitoring while maintaining privacy.

Adjacent to this, embedUR introduced a contextual language model named the “map guide assistant.” This AI-driven system, running on Synaptics’ SL series board, provided attendees with precise booth locations and event information, showcasing the practical application of natural language processing in navigation and information retrieval.

Further emphasizing their AI capabilities, embedUR demonstrated a personalized experience through Synaptics’ privacy sensor. This system recognizes individuals and adjusts settings, such as preparing a preferred coffee, illustrating the fusion of facial recognition technology with user-centric services.

A significant highlight was embedUR’s early implementation of Synaptics’ SR series MCUs. citeturn0search4 This collaboration underscores embedUR’s commitment to harnessing advanced AI-native platforms to deliver efficient and scalable Edge AI solutions.

Additionally, embedUR presented a secure lockbox demo, employing facial recognition to restrict access. This application demonstrates the potential of integrating AI for enhanced security in everyday devices, ensuring that only authorized users can access sensitive items.

With over two decades in embedded software solutions, embedUR Systems has established itself as a leader in the field. Their participation in Embedded World 2025 reflects their dedication to advancing AI integration in embedded systems, offering services like model fine-tuning, optimization, and sensor integration to accelerate product development.

For more information about embedUR Systems and their offerings, visit their official website: https://embedur.ai

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

Synaptics showcased its latest automotive technologies at Embedded World 2025, focusing on driver identification and dual-display processing. Their touch and display driver ICs, along with discrete touch solutions, integrate capacitive sensing to distinguish between driver and passenger interactions. A waveform generator embedded beneath the driver’s seat emits a signal that propagates through the body. When the driver touches the screen, the system recognizes their ID, enabling access to critical functions while restricting distractions like video playback.

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

This technology is designed to enhance road safety by preventing drivers from engaging in activities that could cause distractions. For example, while driving, the system disables texting and entertainment apps, ensuring that only essential navigation or vehicle controls remain accessible. Meanwhile, passengers who lack the waveform generator signal can freely interact with the infotainment system without restrictions. This feature offers OEMs and Tier 1 suppliers a streamlined way to comply with safety regulations and improve user experience.

The integration process is straightforward, as the waveform generator operates within a ±5% frequency tolerance, making it adaptable across different vehicle designs. It remains functional regardless of a person’s clothing or body size, ensuring consistent identification accuracy. Synaptics promotes this technology for next-generation vehicle models, collaborating with leading car manufacturers to implement it in upcoming designs.

Beyond driver detection, Synaptics introduced its SmartBridge technology, which enables efficient multi-display management in vehicles. The SmartBridge chip supports DisplayPort MST (Multi-Stream Transport), allowing a single video cable to drive two independent displays. This reduces complexity and cost by eliminating extra video cables, control units, and additional processing hardware.

SmartBridge’s integrated local dimming enhances display contrast, bringing LCD screens closer to OLED-level black performance. By dynamically adjusting backlight zones, this feature improves visibility in bright conditions, reducing eye strain and keeping drivers more focused on the road. The resulting sharpness and clarity contribute to a safer and more immersive driving experience.

Energy efficiency is another key advantage of Synaptics’ local dimming technology. By selectively reducing backlight intensity in dark areas, it significantly lowers power consumption. Tests demonstrate that enabling local dimming can cut display power usage by up to 50%, which is especially beneficial for electric vehicles, helping to extend driving range by conserving battery energy.

Synaptics is actively working with automotive display manufacturers across Europe, Asia, and North America to integrate these solutions into future vehicles. Given the typical automotive development cycle, it takes approximately two to three years from initial integration to commercial deployment. With the increasing demand for advanced cockpit features in electric and self-driving cars, such innovations are becoming essential.

By combining driver identification, multi-display efficiency, and power-saving enhancements, Synaptics is positioning itself at the forefront of automotive HMI (Human-Machine Interface) development. These technologies will shape the next generation of smart vehicles, ensuring both safety and a high-performance user experience.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

At Embedded World 2025, NXP showcased the integration of the DeepSeek R1 8B model with its i.MX 8M Plus application processor, augmented by Kinara’s Ara-2 neural processing unit (NPU). This configuration exemplifies the synergy between NXP’s processing capabilities and Kinara’s specialized AI acceleration.

—
Synaptics is my Embedded World 2025 video coverage sponsor, check out my Synaptics videos here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvhAbQoe9YN4c84SqXxIY3fQ
—

DeepSeek R1 is an open-source reasoning model designed to emulate human-like cognitive processes. Before providing responses, it undergoes iterative self-assessment to ensure accuracy and reliability. When queried about appropriate actions following a car accident, DeepSeek R1 generated a comprehensive, step-by-step guide, reflecting its advanced reasoning capabilities.

The integration of Kinara’s Ara-2 NPU, capable of delivering up to 40 TOPS (Tera Operations Per Second), significantly enhances the system’s AI performance. This hardware acceleration facilitates efficient processing of complex models like DeepSeek R1, enabling rapid and accurate responses to intricate queries.

In another demonstration, NXP presented a multimodal application utilizing the Large Language and Vision Assistant (LAVA) model. This model combines a vision encoder with a large language model (LLM) to analyze and interpret visual data. Operating entirely at the edge, this setup ensures data privacy, low latency, and reduced power consumption.

When tasked with describing a challenging image, the system processed the visual input and, within approximately seven seconds, provided a detailed description. This rapid analysis underscores the efficacy of edge computing in handling complex AI workloads without relying on cloud-based resources.

The system also demonstrated real-time video analysis capabilities. By capturing frames from a live video stream and processing them through the LAVA model, it generated accurate descriptions of dynamic scenes. This functionality has potential applications in security monitoring, event summarization, and automated content generation.

NXP’s recent agreement to acquire Kinara for $307 million underscores its commitment to advancing edge AI technologies. This strategic move aims to enhance NXP’s processing portfolio with Kinara’s high-performance, energy-efficient NPUs, thereby expanding the possibilities for intelligent edge applications across industrial and automotive sectors.

The combination of NXP’s processors and Kinara’s AI acceleration hardware offers a scalable platform for deploying sophisticated AI models at the edge. This integration facilitates the development of intelligent systems capable of real-time data processing, decision-making, and autonomous operation, marking a significant step forward in edge computing.

Industry observers speculate that NXP’s acquisition of Kinara could lead to the development of more energy-efficient and high-performance AI solutions, particularly in the realms of autonomous vehicles and smart industrial applications. This move positions NXP to better compete with other semiconductor companies investing in edge AI capabilities.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

Geniatech’s latest AI-powered industrial ARM box PC integrates the NXP i.MX 8M Plus processor with Kinara’s Ara-2 AI accelerator, offering up to 40 TOPS of AI computing power. This fanless, industrial-grade solution is designed for edge AI applications, providing an alternative to high-cost desktop AI workstations. It supports large AI models with billions of parameters, making it a powerful tool for on-device inference and processing without relying on cloud-based APIs. The device is showcased at Embedded World 2025, emphasizing its capability to run models like DeepSeek and LLaMA while maintaining data privacy. For more details, visit: https://www.geniatech.com/embedded

The system-on-chip (SoC) combines a quad-core ARM Cortex-A53 processor with an additional Cortex-M7 core, ensuring efficient processing for AI workloads. The integrated neural processing unit (NPU) within the i.MX 8M Plus delivers 2.3 TOPS of AI acceleration, while Kinara’s Ara-2 extends this capability to 40 TOPS, significantly boosting inference speed. This setup allows developers to deploy AI applications directly at the edge, reducing latency and operational costs.

With up to 16GB of LPDDR4X RAM for the Kinara Ara-2 AI accelerator and 8GB to 16GB LPDDR4 for the i.MX 8M Plus, the system supports memory-intensive AI tasks. Storage options include 32GB eMMC, expandable to 256GB, ensuring ample space for large AI models and datasets. Video processing capabilities include 1080p60 HEVC, H.265, and VP9 decoding, alongside HDR ISP support for high-quality imaging applications.

The device’s connectivity features include dual Gigabit Ethernet, Wi-Fi, 4G LTE, and GPS support, making it adaptable to various industrial and AI-driven IoT environments. Video output is handled through HDMI and LVDS, with additional interfaces including USB 3.0, RS232, CAN, and MIPI CSI for camera integration. This wide range of I/O options enables deployment in smart surveillance, industrial automation, and other AI-driven edge computing applications.

Unlike traditional AI computing solutions requiring high-end GPUs, Geniatech’s embedded system provides a cost-effective and energy-efficient alternative. With its easy-to-install software and over-the-air update capabilities, the system ensures continuous improvements and access to the latest AI models. The focus on local processing enhances privacy by keeping data on the device rather than relying on cloud services.

As AI adoption continues to grow, Geniatech is actively exploring future developments, including support for larger AI models, potentially reaching 32 billion parameters. This commitment to scalability positions the company as a key player in industrial AI, addressing the increasing demand for edge AI computing solutions.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!

At Embedded World 2025, Geniatech unveiled a groundbreaking 31.5-inch ePaper display, marking a significant advancement in ePaper technology. This large-format display integrates a specialized algorithm to enable smooth motion and fast refresh rates, making it one of the first ePaper screens capable of displaying video content. The development of this technology has been highly anticipated for decades, as traditional ePaper has struggled with slow refresh rates. Now, with Geniatech’s innovation, dynamic content can be displayed with impressive clarity and fluidity. https://www.geniatech.com/epaper-digital-signage/

One of the standout features of this display is its ability to render partial refreshes, allowing for rapid content updates without requiring a full-screen refresh. This makes it ideal for applications such as digital signage, public information displays, and outdoor advertising, where frequent updates are needed. The technology behind this display leverages FPGA-based processing to optimize refresh performance, overcoming the limitations of conventional ePaper solutions.

The reflective nature of ePaper ensures excellent visibility in various lighting conditions, including direct sunlight, making it particularly suitable for outdoor applications. Unlike traditional LCD or OLED screens, which rely on backlighting, this display utilizes ambient light to create high-contrast images, ensuring readability while reducing power consumption. This ultra-low power requirement makes it a strong candidate for energy-efficient digital signage solutions.

Geniatech’s approach to ePaper also focuses on sustainability. With minimal energy use and a display design engineered for longevity, it aligns with industry efforts to reduce electronic waste and power consumption. Businesses looking to implement digital signage with lower environmental impact will find this solution appealing, as it offers both performance and efficiency without compromising on readability.

The sharpness and responsiveness of this display make it particularly effective in scenarios where static and motion content need to coexist. For example, retail environments can use it for dynamic pricing updates, real-time promotional content, and interactive wayfinding displays. Similarly, transportation hubs could deploy it for up-to-date scheduling and route information.

Geniatech anticipates that this 31.2-inch ePaper display will enter mass production within the next two months. The combination of video playback capability, energy efficiency, and outdoor readability positions it as a transformative solution for businesses and organizations seeking innovative display technologies. As more industries explore ePaper for dynamic content, this breakthrough could reshape the landscape of digital signage.

Check out all my Embedded World 2025 videos in this playlist: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga

This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK

Join https://www.youtube.com/charbax/join for Early Access to my videos and to support my work, or you can Click the “Super Thanks” button below the video to send a highlighted comment!