Embedded World 2019 Flashbacks

If you want to keep in touch with the newest trends in embedded systems, Nuremberg Embedded World is the right place for you. In order to heighten your expectations, we want to share our impressions on the latest event.

More and More Chips

This year the embedded market has undergone a serious segmentation of chip manufacturers. One of the main event threads was producing chips for the deep learning and their implementation.

For instance, Nvidia’s video chipsets and their end devices for video cameras. Qualcomm in cooperation with NXP, which is famous for the achievements in vehicle automation, also follow this trend.

Companies that specialize in producing power efficient chipsets also participated in the event. A large variety of solutions with up-to-date FPGA and DSP onboard were introduced as an alternative to the standard CPU. For example, one company, produces chips with long life period for voice recognition that are as small as a pencil point, respond to certain activation words and word phrases, and has extensive battery life.

Foggy Calculations

Teradek attracted a lot of attention with the solutions based on peripheral calculations (also known as fog computing) that make the system more stable and independent from network environment and its quality. The main principle of this approach is making all the calculations on edge devices, excluding any cloud interference, that accelerates the process as there is no delay in receiving and processing the information. This approach reduces price and improves the data transfer security. Developers are now presented with a wider range of opportunities. For instance, such type of solutions can be used for elderly care without the need to install IP cameras that send the video stream to the external end user, as all the necessary information is processed and distributed to the assigned person right here and now.

Another company that uses such type of approach is Elite Vision that produces cameras with high accuracy for manufacturing facilities. They introduced camera with in-built computation module that processes the signal and provides the user with an end result of its computation. The device can be used for counting objects, scanning QR-codes, analyzing road traffic information or in any classification processes.

Such events encourage companies working in the same sphere to start new cooperation and partnerships. In that spirit, DSR is looking for camera and server station manufacturers for joint solution development.

Weapon Detection System in Public

DSR demoed a system for detecting any weapon or another predefined object (for example, products in a store) in the hands of people in a crowd. This system recognizes people and focuses on their hands. That is its peculiar feature. This product can be used for searching for people with a weapon in their hands in a small crowd. The small, power efficient chipset guarantees a long battery life period of the device and allows it to transfer the computed data and video via different types of wireless networks. This implementation of the fogging is unique because it removes the necessity of transferring data using expensive traffic. The algorithm consists of 2 neural networks: first one is responsible for identifying the wrist; the second is in charge of recognizing the object it is holding. We created a new set of data for machine learning, taught the system to accurately analyze the data, optimized the architecture and chose the right framework.

What’s Inside

In the core of the solution is the goal to make devices with such analytical power more power efficient and available to a larger number of customers without dependency on expensive hardware. That’s why our choice for a cheap machine learning device is dragonboard 410 powered by Quad-core ARM® Cortex® A53 CPU and Qualcomm Adreno 306 GPU with WiFi, Bluetooth and 3G/4G modules. Due to differentiated Quadcore CPU and GPU the development board is capable of processing several parallel tasks locally.

In addition, the system contains an Ethernet video camera, a switch, and a display. We also utilized a high performance VGA adapter produced by Nvidia and AMD for deep machine learning. Although this hardware set up meets the system requirements, its cost is still not optimal. Similar solutions are rumored to use hardware that can heat a small apartment, especially once the price of cryptocurrency falls.

This development is deep in the middle of Computer Vision – a self-learning system that is capable of learning on examples of types of weapons and human movement patterns. We are working on evolving the solution to utilize it in the area of video surveillance and public safety.

World Ruled by Robots?

“What’s New in the World of Artificial Intelligence?” asked me Alexa….

Some people believe that artificial intelligence does not exist, while others watch Sci-Fi movies and devise survival plans for when robots rise against us. Artificial intelligence today is weak, meaning many of the tasks and operations being performed now are limited in scope, but that is continuing to change every day. The development of AI is building at a rapid pace and is poised to change how we interact with the world around us on a daily basis.

Recently, with the help of artificial intelligence, companies are beginning to solve individual niche issues.  For example, emails and responses can be automated in the workplace, reducing the need for human attention. Self-driving cars are operating independently and more safely, reducing the number of accidents on roads. Experts have even predicted that in 10 years self-driving cars will be a normal reality in the US, along with radical organizational and cost structure changes for transportation companies like taxi and bus services.

Social networks, neural networks, and learning algorithms… Russian search engine Yandex is currently conducting closed testing of a new social network using AI and neural networks. Access is only available by invitation of someone who already exists on the network. By tapping into AI and neural networks, you are able to find completely new friends solely on the information you have provided to the system. The algorithms are configured so that you see people based along your selected features. Interestingly, the development with the use of artificial intelligence began to appear in areas such as beauty, cosmetology, and health.

Other large companies continue to use artificial intelligence to help predict events. Mobile operators can analyze the behavior of subscribers in order to offer services that will help improve the user experience, while other applications of modern development are aimed at helping users make decisions.

Google, Siri, Alexa, Cortana, Alice, how many virtual assistants can you remember?  There are many others, but these are some of the most popular we see today. Each of these assistants can allow you to do basic searches, analyze or processes information, but the fact remains that each assistant relates back to weak AI. Just think about how many times you’ve tried to talk humanly and gotten a response that didn’t quite seem to make any sense.

So why don’t we see strong artificial intelligence?  Well, why grow an artificial tree, if you can grow the present faster and cheaper?  Perhaps humanity doesn’t need strong AI just yet.

We are going to continue to dive deeper into this subject in our next issue. In the meantime, please remember that not all robots can be correlated with artificial intelligence. If you have a floor cleaning robot at home, this does not mean that it can study neural networks, collect or process your personal data.

Nordic Chooses DSR & Wins

Nordic Chooses DSR & Wins

DSR Corporation announces its partnership with Nordic Semiconductor. DSR’s ZBOSS 3.0 Zigbee 3.0 software stack is part of the Nordic offering for the multiprotocol nRF53840 SoC.  ZBOSS software was formally certificated by the Zigbee Alliance in September of 2018 as a Zigbee 3.0 compliant platform.

Satisfied Clients

“We are very satisfied with the choice of the Zigbee 3.0 solution vendor for our nRF52840 multiprotocol System-on-Chip (SoC),” says Nordic’s Pär Håkansson, Strategic Marketing Manager. “DSR Corporation has proven itself as a highly reliable partner, working closely with Nordic to make joint production quality software. We appreciate DSR’s professionalism, teamwork and extensive experience in software engineering and Zigbee to help us deliver a new solution to the market that will broaden Zigbee reach around the world.”

What`s Inside

nRF52840 is designed around an Arm® Cortex-M4 CPU with floating Point unit (FPU) and provides the ability to support complex and demanding applications as a single chip solution. Implementation of Zigbee in the nRF52840 SoC expands Nordic’s already broad portfolio of mesh networking solutions for smart home, industrial, and enterprise industry.

DSR’s ZBOSS 3.0 is a cross-platform, high-performance Zigbee 3.0 software protocol stack implementing Zigbee 3.0. ZBOSS 3.0 is highly interoperable and has been used as a Zigbee Pro compliant platform for several chipset solutions. ZBOSS 3.0 is a market-proven product that is used to provide interoperability between 200+ products at more than 40 companies.  ZBOSS 3.0 allows all devices roles and provides extensive support for various cluster libraries.  User-friendly, high-level APIs support fast creation of applications on a predictable budget.  Built with a fixed memory footprint, ZBOSS does not use dynamic memory allocation, which leads to predictable memory budgeting.  Lastly, an important stack feature is optimized power consumption: ZBOSS interrupt-driven I/O improves battery consumption and excludes polling. Additionally, ZBOSS utilizes low RAM capacity on the target device with a special technique in handling data structures.

Worldwide Acceptance

Following the launch of this product, we are happy to announce that Nordic’s advanced Bluetooth® 5/Thread 1.1/Zigbee PRO solution won “2018 Product of the Year”. The nRF52840 chip was named winner of the “RF/Microwave” category by Electronic Products Magazine, which has been an industry icon for more than 40 years. We are both excited for Nordic and honored that they selected us as a trusted technology partner.

Thoughts After CES 2019

CES 2019 at a Glance

Every year we make our way to CES (Consumer Electronics Show) in Las Vegas for the annual consumer electronics exhibition. Imagine over 4,500 vendors presenting new ideas and technological developments spread across an entire week — it really does give a whole new meaning to the city of lights. CES presents a great opportunity to meet like-minded individuals in similar fields, or different, helping catch new ideas, contacts, and ideas – it’s wonderful here.

The history of CES began over 52 years ago with organizers showing more progress each and every year. With the main theme being innovation and information technology, the width of coverage is vast:

  • Robotics,
  • Artificial Intelligence,
  • Three-dimensional Printing,
  • Design,
  • Drones,
  • Sport Technologies,
  • Smart Home,
  • Family & Lifestyle,
  • Virtual Reality (VR),
  • Games,
  • Unmanned Vehicles,
  • Music,
  • Entertainment & Content,
  • Cryptocurrency,
  • Internet of Things (IoT),
  • and Machine Intelligence.

 

All About IoT

The beginning of the year confirmed that IoT is coming to the mass market.  Focus has shifted from smartphones to other smart devices — and manufactures are taking notice.  Improved air quality sensors, door positions, windows, just to provide a few quick examples.  There are even smart window systems being developed that can inform the home when a window is opened wider than an indicated gap, for example.

Consumers can now choose between a wide variety of smart devices and systems, putting real pressure on manufactures and companies to advance smart home ecosystems. But the problem doesn’t just end there. Consumers need a way to connect many different smart devices to a single system – easy management.  This is where Zigbee and other wireless technologies flex their strength; gateways with multiantenna and customization service suggestions come to the rescue.

Hi Computer, Talk to Me

Voice automation control becomes more the norm than the rarity.  It falls into many devices and almost everyone has them now. People want to have a voice assistant in their home, in the office, and in the car, like Jarvis from Iron Man. Project recipes from the Internet to the kitchen door by voice request?  Yes, please!  Yet, even Alexa from Amazon or Google-assistant do not always suit as a compromising option.  Artificial intelligence is poised to grow wiser and communicate with people better and faster.  Companies that once winced at the idea of software in their products are now flocking to CES.  For example, Procter and Gamble – L’Oreal, are developing mirrors that can look at your face to determine if your skin needs support or treatment.  Maybe just a care cream?  Cameras take pictures of the users face and follow changes of the face in real time.  Maybe they’ll even notice skin cancer in due time.

It is interesting that companies that are seemingly far from “software” come into the sphere of technology.  These companies expand the development zone to such wide branches like automation for pets, children, sleep, and beauty.  There are even smart leashes and collars!  People even get interested in buying devices that can distribute pleasant smells throughout their homes.  And what if you could connect a device that could command three-dimensional TV? Cars? Batteries? Spotify on your steering wheel?  The ideas and possibilities are endless.

Robotics help businesses change their models.  It is especially gratifying that companies competing in the past are starting to cooperate.  To denote such activity, the new term ‘coopetition’ has appeared.  ‘Coopetition’ should bring even greater breakthroughs in overall development.  Teamwork gives rise to new achievements.  SDKs help bring the product to market.  Quick starts are real.

Meet & Talk

DSR had a lot of productive meetings with existing and prospective clients and it was the most successful CES to date. DSR was also a proud  sponsor of the Zigbee Alliance Social – an invitation only event that was a great opportunity to bring all of the members together in one location and celebrate Zigbee successes from 2018. During this event, Zigbee Alliance announced several of the new developments and expansions of the standard and also unveil the location of the next member meeting. The atmosphere for the event was very warm and inviting and perfect for conversations and celebration.

In Closing

Here are seven key CES 2019 takeaways that caught our attention:

  • IoT is finally an emerging mass market (and the data it gathers has lots of financial implications)
  • Amazon and Google are in “hand-to-hand combat” driving voice technology into the Smart Home and beyond
  • 5G, NB-IOT and Cat-M1 are expanding battery-powered WAN connectivity in amazing ways
  • Drones—from airborne to underwater to John Deere—are becoming platforms
  • Robotics are creating business change
  • Artificial Intelligence is getting smarter
  • “Coopetition” is happening in lots of places

IoT is moving capabilities out of smart phones and into different smart things. People want their homes, cars and offices to have a voice like Jarvis (see the Ironman movie franchise). And not everyone wants Amazon Alexa or Google Assistant as the go-between. Battery-powered WAN connectivity in a variety of speeds is making the cloud easier by “losing the gateway.” Drones and robotics platforms are giving new capabilities to businesses and consumers. Artificial Intelligence (“AI”) is changing the way products and services interact with humans. And if Apple and Samsung are teaming up, is it time to evaluate how “coopetition” might help your 2019 business goals?

What is Dotdot?

What is Dotdot?

A bit of history — the creation of Zigbee standard required a lot of effort, time and knowledge to construct. Dotdot is an alias for ZCLIP, which stands for Zigbee Cluster Library (ZCL) over IP. It is about exposing ZCL functionality to the IP world, in contrast to classic Zigbee that is always isolated from IP networks and requires a Zigbee gateway to connect Zigbee mesh with the outer world. This would become a bridge between IoT and other networks. Different manufacturers have Zigbee Gateway solutions mostly for connectivity of Zigbee network with cloud.

In classic Zigbee there are all instruments for organization, self-organization, restoring and stability of the network. Above all of this sits the Cluster Library, which calls functions allowing the clusters to communicate. Although, there is one short fall with this system – it cannot get online. With ZCL exposed to IP, it becomes possible to establish a direct communication channel between Internet/Intranet application and Dotdot device when border device remains transparent for and unaffected by the details of communication. The same way communication between Dotdot devices located on different networks is also possible under condition that device services are properly advertised across network borders or devices appear bound by means of a third-party application.

New Language: Old Terms, New Sense

Dotdot is a standard that allows you to put ZCL on any “rails” other than Zigbee – WiFi, Thread, and so on.  This is an add-on for Zigbee.  An application level protocol that allows smart devices from closed networks (with addresses) to communicate more openly through the address space that is on the Internet and other networks.  It is important to not just reach the device itself, but also to address the command to a specific cluster within, and do so securely.

 

Figuratively, Dotdot receives commands in one language and translates them into a language understandable for smart devices.  This makes smart devices ecosystem more open.  Dotdot uses the Zigbee approach in ZCL and has extended it to other types of transports as well. The mesh built for some Dotdot solution deployments is not mandated to contain only Dotdot-compatible devices.

The Commissioning Application

The Dotdot commissioning application was developed next to and based on Thread that was taken from the official Thread Commissioning App mostly as is, courtesy of the Thread Group. The application allows managing the expansion process of the Dotdot network. Seamless integration of the parts and stabilization of Thread for both mobile platforms was also performed.

This application allows third-party devices to enter, which is critical for maintaining network security.  The top layer works with Dotdot enabled devices over Thread. Thread is responsible for commissioning new Thread enabled devices to the home network and discovering devices that are already there. Dotdot makes use of device lists from Thread and as a result uncovers Dotdot enabled devices and their services. The system interrogates the device, finds what services and clusters are running, on which endpoint, and which commands support the device, allowing for a complete picture of the device’s capabilities.  Once this is completed, you are able to change the attributes and send commands from the application itself.  There are clusters, attributes, bindings and reporting.

Why Should Companies Implement Dotdot?

Speed. Abstraction. Interoperability. Dotdot provides the opportunity to create applications in a more flexible way. This is because Dotdot solutions use “generic” border routers that are standard, easy replaceable even at run time, and are not a “single point of failure.” The same data model is provided for different IoT technologies, despite what protocols are used to send data (WiFi, BLE, Zigbee, Thread, and so on), this means there is a wider market for solution spread. You can create a wider IoT system where all the devices understand each other. This creates an easier entry point for companies to develop solutions and allows application developers to focus on the application and functionality, without delving into the underlying specifics of a particular wireless network.

How to Get Started

  1. Download an SDK from a company that provides the solution.
  2. Study the provided API and Zigbee clusters description. Find the needed clusters and start own device (certified by Zigbee Alliance) implementation.
  3. Gain access to the Dotdot Commissioning Application.
  4. To accelerate your development, engage a company with experience in Dotdot and wireless technologies.
  5. Lastly, consider becoming a member of the Zigbee Alliance (if you are not already) to get access to even more tools and become involved in the development of IoT standards.