<p><em>This is the fifth article of an&nbsp;</em><a href="https://www.wevolver.com/article/what-is-a-collaborative-robot" rel="noopener noreferrer" target="_blank"><em>eight-part series</em></a><em>&nbsp;that explores how collaborative robots or cobots are transforming industrial workspaces. It will survey the technologies that have converged to make robotic influence possible, unpack the unique engineering challenges robotics pose, and describe the solutions that are leading the way to the influential robots of the future.</em></p><p><em>The articles were originally published in an e-magazine, and have been substantially edited by Wevolver to update them and make them available on the Wevolver platform. This series is sponsored by Mouser, an online distributor of electronic components. Through their sponsorship,&nbsp;</em><a href="https://www.mouser.com/" rel="nofollow" target="_blank"><em>Mouser Electronics</em></a><em>&nbsp;supports spreading knowledge about collaborative robots.</em></p><h1>Introduction</h1><p>A new generation of robots, termed &ldquo;collaborative robots&rdquo; or &ldquo;cobots,&rdquo; is now being integrated into manufacturing environments. Rather than being used to replace human labor, these robots are being used to work together with humans in a common workspace. These cobots are typically used on tasks that require improved process control and/or greater flexibility, scalability, and agility. To enable cobots to work together with the human workforce, numerous improvements have been incorporated to enhance worker safety. The result is increased productivity and better labor utilization at lower overall costs. Consequently, these cobots are affordable for small- and medium-sized companies to support lower-speed, lower-volume production runs. This article examines some of the technological advancements that enable collaborative robotics and provides some examples of how these cobots are being used in a<a href="https://www.wevolver.com/article/industrie.40.deep.dive.part.5.flexible.manufacturing" rel="noopener noreferrer" target="_blank">&nbsp;manufacturing environment.</a></p><h1>Enabling Technologies</h1><p>Collaborative robotic platforms incorporate numerous enabling technologies that differentiate them from traditional robots and enhance human/robotic interaction, improve worker safety, and reduce costs. Improvements in sensor, actuator, control, and computation technologies empower the<a href="https://www.wevolver.com/article/the-complexities-of-mimicking-humans-is-just-the-beginning" rel="noopener noreferrer" target="_blank">&nbsp;cobot&rsquo;s perception</a>, data fusion and processing, artificial intelligence, and actuation. Other technologies promote ease of use, adaptability, and lower costs. A brief overview of some of these technologies follows:</p><h2>Perception</h2><p>Technologies that improve perception include sensors that can detect and measure any physical property, such as distance, proximity, force, torque, velocity, sound, vibration, volume, weight, surface finish, texture, chemical composition, temperature, electrical current, and magnetism. Other technologies, such as machine vision, allow the cobot to detect and identify objects, spaces, scenes, orientations, and locations of objects in the visible, infrared, and ultraviolet wavelengths. Together, these perception technologies allow improved accuracy, higher throughput, collision avoidance, and situational awareness. Voice recognition and motion tracking technologies may also allow operators to control the cobot through voice commands and hand gestures.</p><p><span class="fr-img-caption fr-fic fr-dib" style="width: 788px;"><span class="fr-img-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiAid2V2b2x2ZXItcHJvamVjdC1pbWFnZXMiLCAia2V5IjogImZyb2FsYS8xNTk5MDM0MTY5Mjk4LXNpY2suanBnIiwgImVkaXRzIjogeyJyZXNpemUiOiB7IndpZHRoIjogOTUwLCAiZml0IjogImNvdmVyIn19fQ=="><span class="fr-inner" spellcheck="false">Cobots can be equipped with a variety of sensors. Image:&nbsp;<a href="https://www.sick.com/at/en/the-new-mobility-how-sensors-control-the-cobots-of-the-future/w/blog-sensors-cobots/" rel="noopener noreferrer" target="_blank">Sick</a></span></span></span></p><h2>Data Fusion and Processing</h2><p>Raw data from numerous sensors must be integrated, processed, and interpreted to enable the cobot to make informed and accurate deductions about the environment so that appropriate actions can be taken. This must be rapidly accomplished to avoid undue delays in the robot&rsquo;s operation, especially if the robot needs to interrupt its operation to avoid a collision with an object or human. Sensor-fusion algorithms must effectively integrate data from different types of sensors, which may come from different locations within the workspace or may be sensed at different times to make informed and accurate deductions about the environment and situation.</p><h2>Artificial Intelligence</h2><p>A traditional robot operates according to preprogramed instructions that are repeated without regard to changes in its operational environment. A cobot, on the other hand, incorporates <a href="https://www.wevolver.com/article/industrie.40.deep.dive.part.1.introducing.smart.manufacturing" rel="noopener noreferrer" target="_blank">artificial intelligence (AI)</a>, which encompasses its ability to perceive its environment; reason and solve problems; recognize, learn, and adapt to new situations and environments; autonomously make decisions; and interact with humans. The &ldquo;programming&rdquo; of a cobot to operate in a new environment is not necessarily complicated and can simply involve a human operator manually walking through the desired motion by moving the cobot&rsquo;s arms through the desired trajectory. AI is enabled through high-speed computer processors and software that may incorporate a variety of technologies such as fuzzy logic, probabilistic methods, neural networks, and expert systems. These technologies provide cobots with human-like qualities that promote human-robot interaction and collaboration.</p><h2>Actuators</h2><p>While traditional robots have very stiff joints with high force, high torque actuation devices, cobots have compliant joints that can provide smooth or soft motions and forces, so they may seamlessly interact with their human counterparts. Compliant actuators do not require expensive, high-precision drive mechanisms or motion sensors, as they rely on force or current feedback to compensate for potential errors in position accuracy. Furthermore, since cobots are lighter and designed to work with humans in a shared workspace, they do not need the expensive high-force actuation devices or motor drives that are commonly used in traditional robots.</p><h1>Applications</h1><p>New applications for collaborative robotics within manufacturing continue to develop and expand. Because cobots are affordable, highly adaptable, and almost plug-and-play capable, small- and medium-sized manufacturers are eager to take on this technology. Some of these notable applications include the following:</p><h2>Machine Tending</h2><p>A typical production machine, such as the kind used for computer numerical control (CNC) machining, must continuously be tended by an operator who will load raw material, start the machine, ensure its proper operation, and unload finished parts. Machine tending is one of the most common industrial jobs. Often monotonous and boring, it does not require a high skill level, and operators are prone to injury due to the repetitive lifting of heavy materials and parts. Other examples of machine tending operations include traditional machining operations (e.g., stamping, grinding, trimming, and welding), injection molding, printed circuit board (PCB) testing, part inspecting, and coordinate measuring.</p><p><span class="fr-img-caption fr-fic fr-dib" style="width: 788px;"><span class="fr-img-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiAid2V2b2x2ZXItcHJvamVjdC1pbWFnZXMiLCAia2V5IjogImZyb2FsYS8xNTk5MDM0MzM5MTU5LTA0MDIgKDEpLnBuZyIsICJlZGl0cyI6IHsicmVzaXplIjogeyJ3aWR0aCI6IDk1MCwgImZpdCI6ICJjb3ZlciJ9fX0="><span class="fr-inner" spellcheck="true">A cobot tending a CNC machine. Image:&nbsp;<a href="http://www.robotiq.com" target="_blank">Robotiq</a></span></span></span></p><p>Cobots may be an ideal fit for machine tending applications. They can be placed in front of a traditional manufacturing machine and easily programmed to perform the required loading and unloading tasks. Periodically, skilled technicians can examine the machine and tools and perform regular maintenance. This can lead to better workforce utilization, where the cobots are used for the lower-skill-level manual operations and technicians are used for the higher-skill-level tasks such as inspecting, repairing, and changing tools, performing quality control tests, and taking appropriate corrective actions. This, in turn, can result in significant labor savings, lower injury rates, less production downtime, a more motivated and skilled workforce, and higher productivity.</p><h2>Packaging and Palletizing</h2><p>Packaging and palletizing tasks typically involve the removal of products from an assembly line or conveyor belt, counting and wrapping them appropriately, applying labels, placing them into cartons, and sealing the cartons. High-speed, high-volume manufacturers can create specialized robotic machines and equipment for packaging. On the other hand, small to medium companies may still require manual packaging operations since automated equipment may not be cost-effective due to limited production runs or variations in product form factors.</p><p>Cobots may be an ideal fit for such packaging and palletizing applications. They can be easily programmed to recognize and count items on a conveyor belt, apply packaging materials and labels, and place them into the appropriate cartons. Human workers can still work with the cobots while performing higher-skill-level tasks such as quality-control inspections. Programming for the cobot can be easily modified to adapt to changes in the product configuration or packaging requirements.</p><p><span class="fr-img-caption fr-fic fr-dib" style="width: 788px;"><span class="fr-img-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiAid2V2b2x2ZXItcHJvamVjdC1pbWFnZXMiLCAia2V5IjogImZyb2FsYS8xNTk5MDM0NDAwNDM3LTA0MDMgKDEpLmpwZyIsICJlZGl0cyI6IHsicmVzaXplIjogeyJ3aWR0aCI6IDk1MCwgImZpdCI6ICJjb3ZlciJ9fX0="><span class="fr-inner" spellcheck="true">Cobot in packaging application. Image:&nbsp;<a href="http://www.robotiq.com" target="_blank">Robotiq</a></span></span></span></p><h2>Collaborative or Adaptive Assembly</h2><p>Traditional (pick and place) robots require the precise location of the unfinished assemblies and parts. Cobots, on the other hand, are adaptable to non-precise placement, as they might incorporate vision systems that facilitate position feedback. A collaborative or adaptive assembly operation may involve use of a human operator to first inspect, sort, and select a particular part then roughly align the part onto an unfinished assembly (that is, a work-in-progress). In a subsequent assembly step, a cobot would complete the assembly by fastening the part to the unfinished assembly. An operation such as this might be advantageous in situations where parts are too small to align with unaided human vision; or where the final alignment and attachment of the part requires a great deal of dexterity or strength; or where final assembly must be performed at high temperatures, in a difficult environment, or with hazardous chemicals or adhesives. A cobot would, therefore, be useful if the location, orientation, or placement of parts onto an unfinished assembly is not accurate or repeatable.</p><h2>Human Augmentation</h2><p>Collaborative robots can be used to augment human capabilities during manufacturing and assembly operations by assisting in the performance of menial (repetitive) tasks or tasks that require strength or extended reach. For example, certain manufacturing operations might require lifting and positioning a heavy part, like an automobile door, onto an unfinished assembly, like an automobile body. Such a process might not lend itself to a completely automated operation if it requires fine adjustments to the part position to ensure the part properly fits onto the unfinished assembly. For example, in an automobile assembly operation, different vehicle styles might require varying amounts and styles of doors for installation, which may not be a suitable situation for a completely automated process. However, a cobot can be useful in this situation to lift the heavy part. It could then carry out &ldquo;instructions&rdquo; from the human operator by responding to the operator&rsquo;s touch and move to position the part on the desired location of the unfinished assembly.</p><h1>Conclusion</h1><p>These are only a few examples that illustrate the role of collaborative robotics in manufacturing. As enabling robotic technologies in the areas of sensors, actuators, controls, and computation continue to evolve, we expect that more and more manufacturers will continue to adopt collaborative robotic systems into their workplaces. What might the eventual role of cobots be in manufacturing environments? The advancement in its technology and applications continue to unfold.</p><p><em>This article was originally written by Phi Hipol for Mouser and substantially edited by the Wevolver team. It&#39;s the fifth article of a series exploring collaborative robots.&nbsp;</em></p><p id="isPasted"><em>Article One</em><em>&nbsp;</em><a href="https://www.wevolver.com/article/what-is-a-collaborative-robot" rel="noopener noreferrer" target="_blank"><em>introduces collaborative robots.</em></a></p><p><em>Article Two</em><em>&nbsp;describes&nbsp;</em><a href="https://www.wevolver.com/article/a-history-of-industrial-robots" rel="noopener noreferrer" target="_blank"><em>the history of Industrial Robots.</em></a></p><p><em>Article Three</em><em>&nbsp;gives an&nbsp;</em><a href="https://www.wevolver.com/article/the-complexities-of-mimicking-humans-is-just-the-beginning" rel="noopener noreferrer" target="_blank"><em>overview of collaborative robots sensor technologies.</em></a></p><p><em>Article Four</em><em>&nbsp;</em><a href="https://www.wevolver.com/article/designing-collaborative-robots-maximizing-productivity-and-safety" rel="noopener noreferrer" target="_blank"><em>examines the balance between cobot safety and productivity.</em></a></p><p><em>Article Six</em><em>&nbsp;explores the&nbsp;</em><a href="https://www.wevolver.com/article/programmable-versus-fixed-function-controllers-alternatives-for-complex-robotic-motion" rel="noopener noreferrer" target="_blank"><em>challenges of motion control of robotic arms.</em></a></p><p><em>Article Seven l</em><a href="https://www.wevolver.com/article/cobots-are-collaborators-ai-will-make-them-partners" rel="noopener noreferrer" target="_blank"><em>ooks at the potential of AI in cobots.</em></a></p><p><em>Article Eight&nbsp;</em><a href="https://www.wevolver.com/article/social-impact-of-robotics-in-the-workplace-the-arrival-of-the-perfect-coworker" rel="noopener noreferrer" target="_blank"><em>discusses the social impact of cobots.</em></a></p><hr><h1><em>About the sponsor: Mouser Electronics</em></h1><p><a href="https://www.mouser.com/" rel="nofollow" target="_blank"><em>Mouser Electronics</em></a><em>&nbsp;is a worldwide leading authorized distributor of semiconductors and electronic components for over 800 industry-leading manufacturers. They specialize in the rapid introduction of new products and technologies for design engineers and buyers. Their extensive product offering includes semiconductors, interconnects, passives, and electromechanical components.</em></p><p><em><em><img class="fr-fic fr-dii" src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1685445472729-1685445472729.png"></em></em></p><p><br></p><p><br></p>

Article 5 of our Cobot Series: Traditionally, robotics have served limited roles in manufacturing environments; however, various technologies have converged to make robots work well as collaborators with humans and to succeed in various applications.

Technologies Converge to Help Drive Manufacturing Applications

<p dir="ltr">SamacSys, a Supplyframe Company, is the world&rsquo;s leading provider of 2D and 3D CAD models for the electronics industry. &nbsp;The company, driven by founder and CEO Alex MacDougall, has a singular vision to free up electronic engineers&#39; design process to ensure there is more time on innovation and less time on drawing CAD models. We sat down with MacDougall and asked him to reflect on the experiences that helped him launch a global company that offers a free service to engineers and gathered his thoughts on future trends and predictions for the electronics industry.</p><h2>Introducing Alex MacDougall</h2><p dir="ltr">MacDougall grew up in the rural area of Hertfordshire, North of London, and received his initial engineering education with the UK military, he went on to study electronics and circuit board design. After leaving the Royal Marines he completed the IPC CID certification, becoming the youngest person in Europe with the certification.</p><p dir="ltr">His first job in the electronics industry was in an applications Engineer (AE) role at the UK branch of PADS software, the global leader in PCB design software at the time. His love for engineering pulled him into an additional role in a design bureau in the same building as PADS Software. &ldquo;I would go to the design bureau, from 5 or 6am and would work with them, designing circuits&rdquo; recalls MacDougall. &ldquo;Then I would do my nine to five as an AE. Then I&#39;d go back to do more design work from five until late. So I was, for a number of years learning two different professions, one as the designer and one as the guy supporting other people using design software. I was grinding hard for a few years to give my career path various options.&rdquo;</p><p dir="ltr">MacDougall found this combination of intimately understanding both electrical engineering design and software development would provide the confidence and knowledge for starting SamacSys many years later.</p><h1><strong>SamacSys Origin Story</strong></h1><h2><strong>Who is SamacSys?</strong></h2><p dir="ltr">The idea for SamacSys developed over many years as the issue of the lack of available CAD models for electronic engineers kept coming up again and again. &ldquo;I&#39;d be speaking with engineers from different companies and was listening to what they were saying, and this subject just kept coming up - and I couldn&#39;t believe that it hadn&#39;t been fixed yet,&rdquo; says MacDougall. &ldquo;I was also feeling my own frustrations from designing products and then hearing that it was more of a widespread issue and I just wanted to solve this for the industry.&rdquo;</p><p dir="ltr">Every modern piece of technology contains a printed circuit board or PCB packed full of electronic components. Before a PCB gets made, it is designed in software (CAD) by an engineer with exact models of every single component within it. There are currently millions of components available for engineers to choose from for inclusion in their designs and thousands more are brought to market every year as technology advances. Correctly modelling the components, including their functions, their connections, and their physical dimensions is essential to ensure the PCB design is suitable for its application both in size and function. So engineers must painstakingly model each component themselves or spend hours finding and obtaining these models online.</p><p><img class="fr-fic fr-dib" src="https://images.wevolver.com/eyJidWNrZXQiOiAid2V2b2x2ZXItcHJvamVjdC1pbWFnZXMiLCAia2V5IjogImZyb2FsYS8xNTk3MzI4MjIzNjM4LWZvb3RwcmludHMgc2FtYWNzeXMucG5nIiwgImVkaXRzIjogeyJyZXNpemUiOiB7IndpZHRoIjogOTUwLCAiZml0IjogImNvdmVyIn19fQ==" style="width: 788px;"></p><p dir="ltr">SamacSys goes a long way to solve this problem by providing high-quality CAD models of components for free. The SamacSys model library contains millions of models that allow engineers to streamline the design process, reduce error rate, and innovate quickly.&nbsp;</p><p dir="ltr"><strong id="isPasted">Recommended reading:&nbsp;</strong><span style="background-color: transparent;"><a href="https://www.wevolver.com/article/samacsys-power-user-case-study-icarus-design" rel="noopener noreferrer" target="_blank">SamacSys Power User Case Study: Icarus-Design</a></span></p><p dir="ltr">The urgency to solve this industry-wide issue has always been the driver for Alex. From the very inception of SamacSys to today. The need to solve this issue is behind every decision the company makes.</p><h2><strong>The early days</strong></h2><p dir="ltr">SamacSys was started in 2010, while the world was still in recovery mode of the 2008 financial crisis. There was a degree of uncertainty in the market, but MacDougall had a certainty about the product. By observing other similar ventures at the time, he decided not to pursue a heavy VC investment, but rather try to go bootstrapped and in doing so avoid the risk of VC taking over significant equity-based on risk in the business model. &ldquo;Despite the risks, in a way building the business was secondary,&rdquo; explains MacDougall. &ldquo;The first goal for us really was to solve a market challenge.&rdquo;</p><p dir="ltr">This drive for an industry-wide solution restrained the company from scaling too early and instead focussed them on perfecting their product and testing their theory that this would become an essential service for all electronic engineers.</p><p dir="ltr">What worked for the company was that they had a product that made sense to potential customers and that they could get immediate validation of its value. Even on very early sales calls, MacDougall was able to make some initial sales which provided some cash but even more importantly the energy to continue the project buoyed by the reception their idea was receiving.</p><p dir="ltr">One of the best rewards from that early success was the genuine appreciation from engineers which they could express very clearly, not only with words of gratitude but with case studies where they could describe exactly how SamacSys was helping improve their design process.</p><p><img class="fr-fic fr-dib" src="https://images.wevolver.com/eyJidWNrZXQiOiAid2V2b2x2ZXItcHJvamVjdC1pbWFnZXMiLCAia2V5IjogImZyb2FsYS8xNTk3MzI4MzI1NDM2LWNhZCBtb2RlbC5wbmciLCAiZWRpdHMiOiB7InJlc2l6ZSI6IHsid2lkdGgiOiA5NTAsICJmaXQiOiAiY292ZXIifX19" style="width: 788px;"></p><p dir="ltr">Despite this initial success, there were still big hurdles in the early days of the company, one of the more difficult to overcome was getting taken seriously by larger companies in the industry. MacDougall remembers it was an easier task to be understood by the Electronic Design Automation players, but much harder to establish a reputation within the components business. &ldquo;Imagine walking through the door of a leading component manufacturer or distributor, with a new world changing concept. I just looked like some crazy young guy with unrealistic dreams! Getting taken seriously by company execs was a nightmare early on. I&rsquo;m pleased to say they have now become our customers. &rdquo; MacDougall remembers.</p><h1><strong>SamacSys in 2020 and beyond</strong></h1><p dir="ltr">SamacSys was recently acquired by Supplyframe, an intelligence platform for the global electronics value chain. Supplyframe&rsquo;s solutions align electronics demand with supply and by delivering insights at key decision points throughout the entire design-to-source product lifecycle with the goal of ensuring a resilient and agile supply chain. &nbsp;</p><p dir="ltr">SamacSys had received other acquisition offers in the past, but they were not a good fit for MacDougall. &ldquo;Supplyframe&rsquo;s position in the industry allows us to stay neutral so that we can do what&#39;s right for the industry and not be steered towards one particular area in the market,&rdquo; says MacDougall about the decision. &ldquo;I have a vision match with Supplyframe CEO Steve Flagg, he understands what we are doing and gave me confidence that together we would be able to keep evolving our solution in a way that&rsquo;s best for Engineers &amp; our customers.&rdquo;</p><p dir="ltr">The acquisition of Samacys by Supplyframe was based on a shared vision of expanding the intelligence that can be provided to engineers at the point of design. &nbsp;The combined entities have a belief that new forms of digital engagement drive innovation in electronics manufacturing, from initial idea to design-driven part selection to procurement-driven purchasing activities, all optimized alignment with supply chain capacity and market response.&nbsp;</p><p dir="ltr">This &ldquo;Design-to-Source&rdquo; lifecycle requires that organizations effectively manage direct materials sourcing and procurement across numerous siloed workflows and applications. &nbsp;By connecting engineering design and sourcing and augmenting decision-making capabilities with real-time market intelligence, Supplyframe and Samacsys offer resiliency, agility, and profitability to the electronics value chain. &nbsp;</p><p dir="ltr"><img class="fr-fic fr-dib" src="https://images.wevolver.com/eyJidWNrZXQiOiAid2V2b2x2ZXItcHJvamVjdC1pbWFnZXMiLCAia2V5IjogImZyb2FsYS8xNTk3MzI4MzUwODQ4LXNjcmVlbiBzaG90IHNhbWFjc3lzLnBuZyIsICJlZGl0cyI6IHsicmVzaXplIjogeyJ3aWR0aCI6IDk1MCwgImZpdCI6ICJjb3ZlciJ9fX0=" style="width: 788px;"></p><h2><strong>What is next for SamacSys?</strong><strong>&nbsp;</strong></h2><p dir="ltr">When asked about the future for SamacSys, MacDougall&rsquo;s answer is clear: &ldquo;Engineers of the future will not believe their senior colleagues used to waste their valuable time building CAD models. With our solution engineers can now experience ubiquitous CAD model availability, embedded at the point of design.&rdquo;</p><p dir="ltr">The downstream impact of this vision is significant. Streamlining a design process means products are getting to market faster, while engineering teams are overall reducing costs and errors which again, enables more time for innovation and development.</p><h2><strong>Predictions for the industry</strong></h2><p dir="ltr">&nbsp;MacDougall is motivated by the advances occurring in the electronics industry including a move towards more modular design processes. &nbsp;&ldquo;If you have a modular approach, it is easier to engage. &nbsp;We provide the building blocks, we have done the hard work already. Electrical engineering is a high barrier profession, you can&rsquo;t just watch one YouTube video and be qualified, but modular design will help open access - and that will drive more people to innovate.&rdquo;</p><p dir="ltr">Another exciting development for MacDougall is the continued connection to Artificial Intelligence (AI). &ldquo;It&rsquo;s reasonable to expect that some of the design can be done via a platform where the designer selects functionality, such as this device &lsquo;has a screen&rsquo;, &lsquo;is USB powered&rsquo;, etc. and the algorithm will be able to generate the specific product, essentially ready for manufacture.&rdquo;</p><h2><strong>Final thoughts</strong></h2><p dir="ltr">SamacSys is a company with a singular vision to help an industry. Alex MacDougall and SamacSys are increasing the potential for innovation by freeing up electronic engineers from the tyranny of the CAD model. As MacDougall states: &ldquo;If engineers can spend the time they used to waste building cad models thinking and building life-changing technology for humanity, - that has got to be a good thing right?&rdquo;</p><hr><h1><strong><em>About the Sponsor: Supplyframe</em></strong></h1><p><em>This article is sponsored by Supplyframe. Supplyframe aligns electronics demand with supply and brings new levels of resiliency to the global electronics value chain, with transformative, intelligence-based solutions to deliver insights at key decision points throughout the entire design-to-source product lifecycle. Leveraging billions of continuous signals of design intent, demand, supply, and risk factors, Supplyframe&rsquo;s Design-to-Source Intelligence (DSI) Platform is the world&rsquo;s richest intelligence resource for the electronics industry. Over 10 million engineering and supply chain professionals worldwide engage with our SaaS solutions, search engines, and media properties to power rapid innovation and optimize in excess of $120 billion in annual direct materials spend. Supplyframe is headquartered in Pasadena, Calif., with offices in Austin, Belgrade, Grenoble, Oxford, San Francisco, Shanghai, and Shenzhen.&nbsp;</em></p><p><img class="fr-fic fr-dib" src="https://images.wevolver.com/eyJidWNrZXQiOiAid2V2b2x2ZXItcHJvamVjdC1pbWFnZXMiLCAia2V5IjogImZyb2FsYS8xNTk3MjIzNjQzNjU0LVN1cHBseWZyYW1lLUxvY2t1cC1CbGFjay5wbmciLCAiZWRpdHMiOiB7InJlc2l6ZSI6IHsid2lkdGgiOiA5NTAsICJmaXQiOiAiY292ZXIifX19" style="width: 150px;"></p><p><br></p>

We talk with SamacSys founder and CEO about his startup journey.

Alex MacDougall is on a mission to solve a problem at the core of the electronics industry

<p dir="ltr">Voice command will continue to become a natural and broadly accessible method of interacting with technology. As described in our previous article, Voice At The Edge Helps Technology Work For More People, controlling devices with speech offers a huge range of advantages to users and designers.&nbsp;</p><p dir="ltr">Devices with voice interfaces are <a href="https://www.juniperresearch.com/press/press-releases/digital-voice-assistants-in-use-to-8-million-2023" rel="noopener noreferrer" target="_blank">expected to rise</a> from 3 billion devices worldwide to 8 billion by the end of 2035. These won’t just be more sophisticated versions of the home assistants that we know today, but a whole new range of devices and applications that will offer natural voice interaction.&nbsp;</p><p dir="ltr">In this article, we dive deeper into how voice command on edge devices works, and take a look at the leading low power devices available for voice command system design by examining a recent <a href="https://www.syntiant.com/post/keyword-spotting-power-comparison" rel="noopener noreferrer" target="_blank">white paper</a> from Syntiant.</p><h1 dir="ltr">The basics of keyword spotting</h1><p dir="ltr">Smart devices are always active - listening for the predefined “wake” up instruction, such as "Alexa," "Ok Google," etc. This action is commonly known as keyword spotting (KWS). When a keyword is detected, the device wakes up and its full-scale voice recognition is activated either on the cloud or on the device. In some devices, keywords are also used as voice commands, for example, ‘hello, start, stop’ in a voice-enabled robot vacuum.&nbsp;</p><p dir="ltr">As a KWS system is always-on, it must have very low power consumption. &nbsp;A KWS system also should detect the spoken keywords with high accuracy and low latency to attain the best user experience. Low power consumption is especially important for portable devices, such as smartphones and wearables.&nbsp;</p><p dir="ltr"><span class="fr-img-caption fr-fic fr-dib" style="width: 788px;"><span class="fr-img-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjAxMjc4NDg5ODUxLXNvbnkuanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ=="><span class="fr-inner" spellcheck="false">Image: Sony</span></span></span></p><p dir="ltr">These tough conflicting system requirements, in combination with the increasing amount of voice command applications and audiences, make KWS a hugely relevant research area.&nbsp;</p><p dir="ltr">Until recently, the only devices capable of performing KWS at edge-compatible power levels were low-power microcontroller units (MCUs) and digital signal processors (DSPs). Processor-designer, Syntiant, has recently introduced the NDP10x series of its Neural Decision Processors (NDPs), a suite of highly efficient chips purpose-built for KWS using deep neural networks that increase the options for system designers.</p><h1 dir="ltr">Introduction to microcontrollers</h1><p dir="ltr">Microcontrollers, sometimes known as an embedded controller, &nbsp;are present in applications with and without voice command, such as vehicles, robots, office machines, medical devices, vending machines, and home appliances. They were first developed by Intel in the early 1970s and are now produced by many other manufacturers, including &nbsp;Microchip (PIC microcontrollers), Atmel ( AVR microcontrollers), Hitachi, Phillips, Maxim, NXP, Intel, etc.</p><p dir="ltr">The need for low power consumption for keyword spotting systems makes microcontrollers a natural choice for deploying KWS in an always-on system. However, deployment of neural network-based KWS on microcontrollers comes with the challenges of limited memory footprint and limited computer resources.&nbsp;</p><h1 dir="ltr">Introduction to neural decision processors</h1><p dir="ltr">The Syntiant<sup>R</sup> NDP100<sup>TM</sup> microwatt-power <a href="https://www.syntiant.com/" rel="noopener noreferrer" target="_blank">Neural Decision Processor</a><sup>TM</sup> is the first and currently the only commercial silicon device designed to put machine learning processing into almost any consumer device. The custom-built chips are specialized to run TensorFlow neural networks. TensorFlow is an open-source software library developed by Google and available for free for dataflow and differentiable programming across a range of tasks.&nbsp;</p><p dir="ltr">The Syntiant NDP is specifically designed for devices that use voice commands and have ultra-low power requirements making them well-suited to devices with KWS systems.</p><p dir="ltr">The Syntiant NDP100 and NDP101 chips have been certified by Amazon, which enables the company’s neural processors to be used in Alexa-enabled devices, however, Syntiant NDPs are not limited to Alexa devices only.</p><p dir="ltr"><span class="fr-img-caption fr-fic fr-dib" style="width: 788px;"><span class="fr-img-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNTk3MzE4NzkyNTM2LWNyb3BwZWQgZWFyYnVkcyBzeW50aWFudC5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19"><span class="fr-inner" spellcheck="false">The Syntiant NDP100 microwatt-power Neural Decision Processor&nbsp;</span></span></span></p><h1 dir="ltr">How do they compare and what do I need for my device?</h1><p dir="ltr">System designers are faced with a growing number of high-quality options for adding a KWS algorithm to their devices. As previously described, a voice command interface often requires the device to be ‘always on’ and listening for its wake words, thus low power consumption is essential. However, it can be difficult to compare the power consumption of different devices from different manufacturers. Datasheets may describe current consumption in uA/MHz, but it is not generally possible to convert that into the power required for a given task. Additionally, different network topologies, training procedures, etc., can affect system accuracy and power consumption.</p><p dir="ltr">The critical question system designers must ask is how much power consumption will be added by a solution running a KWS algorithm with sufficient accuracy to satisfy the use case?</p><h1 dir="ltr">Syntiant White Paper</h1><p dir="ltr">Two recent research projects have compared device options for KWS. The 2018, “Hello Edge,” paper<sup>&nbsp;[1]</sup> performed neural network architecture evaluation and exploration for running KWS on resource-constrained microcontrollers. In 2019, Syntiant tested their NDP10x series of Neural Decision Processors against a range of MCU’s suitable for KWS which they outlined in this whitepaper <sup>[2]</sup>. The rest of this article will be dedicated to examining the results of the Syntiant test, which provides a good overview of some of the leading options for adding KWS to edge devices.</p><h1>The line-up</h1><p dir="ltr">The test compared several of the lowest-power options for KWS available, including their own NDP10x, and compared speed, accuracy, and power on a common task: the Google keyword<a href="https://ai.googleblog.com/2017/08/launching-speech-commands-dataset.html" target="_blank">&nbsp;dataset</a> assembled by Pete Warden of Google.&nbsp;</p><p dir="ltr">Included in the test were the STM32F746 Discovery<a href="http://www.st.com/en/evaluation-tools/32f746gdiscovery.html" target="_blank">&nbsp;board</a>, the STM32L476G, and its <a href="https://www.st.com/en/evaluation-tools/32l476gdiscovery.html" target="_blank">evaluation board</a>, as well as the Ambiq Apollo 3 Blue, using the <a href="https://learn.sparkfun.com/tutorials/using-sparkfun-edge-board-with-ambiq-apollo3-sdk" target="_blank"></a><a href="https://learn.sparkfun.com/tutorials/using-sparkfun-edge-board-with-ambiq-apollo3-sdk" target="_blank">SparkFun Edge Board</a>, a joint effort by Google, Ambiq, and SparkFun, and the Syntiant’s NDP100 solution using their own internal development board.</p><p dir="ltr"><img class="fr-fic fr-dib" src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNTk3MzE4ODc1OTA4LWNyb3BwZWQgc3ludGlhbnQgYm94LmpwZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 788px;"></p><h1 dir="ltr">The test</h1><p dir="ltr">The researchers modified the code to run a batch of 20 inference cycles on each of the platforms. For the MCU targets, the input audio was taken from a pre-recorded waveform stored in memory to avoid contaminating the measurements with microphone power. The measured power includes computation of<a href="http://practicalcryptography.com/miscellaneous/machine-learning/guide-mel-frequency-cepstral-coefficients-mfccs/" target="_blank">&nbsp;MFCC</a> or filter-bank energy features, but not an ADC or microphone power. The NDP measurements include decimation of <a href="https://en.wikipedia.org/wiki/Pulse-density_modulation" target="_blank">PDM outpu</a>t from a digital microphone, as well as feature extraction and the neural inference energy.&nbsp;</p><p dir="ltr">MCUs often have several on and off-chip peripherals powered from the same supply, so the Syntiant team subtracted a baseline current measurement made with the MCU powered up but idle. The NDP results are direct measurements with nothing subtracted. The MCU experiments were performed with HW settings as set in the available open-source software linked above.</p><h1 dir="ltr">The results</h1><p dir="ltr">The table below summarizes the measurements. Simple ‘side by side’ comparisons are difficult due to the trade-offs between model complexity, accuracy, compute time, and energy. To make reading the results more clearly, the researchers compared across three axes:</p><p>- Energy per inference is the energy required to process one frame of audio samples and produce a label (e.g., “yes,” "no,” “hello”), including feature extraction and running inference.</p><p>- Inference time is the time required to process one frame of audio and frame rate is its inverse, indicating the maximum number of audio frames per second that the processor is capable of processing with a given network.&nbsp;</p><p>- G10 Accuracy is the accuracy result on the Google-10 keyword task.</p><p dir="ltr">Estimates for the operations and parameter counts for the Small FC and Small DS-CNN networks are taken from the “Hello Edge” paper. For the TinyConv network used on the Ambiq chip, those figures were estimated from the code in the “Speech Commands” TensorFlow example.</p><p dir="ltr"><img class="fr-fic fr-dib" src="https://images.wevolver.com/eyJidWNrZXQiOiAid2V2b2x2ZXItcHJvamVjdC1pbWFnZXMiLCAia2V5IjogImZyb2FsYS8xNTk3MzA5ODAxMjI3LXRhYmxlMSBhcnRpY2xlLmpwZyIsICJlZGl0cyI6IHsicmVzaXplIjogeyJ3aWR0aCI6IDk1MCwgImZpdCI6ICJjb3ZlciJ9fX0=" style="width: 788px;"></p><h1 dir="ltr">What does this mean?</h1><p dir="ltr">It’s clear that the purpose-built compute path in the NDP100 provides dramatic energy savings relative to the stored-program architecture of an MCU solution. The closest result in energy, from the Ambiq Apollo 3 Blue, is 27x higher than the NDP energy, operating with a much smaller and less accurate network.&nbsp;</p><p dir="ltr">The STM32L4786 running the Small DS-CNN network had a comparable accuracy to the NDP but requires 193x the energy.</p><p dir="ltr">The frame rates are also critical to examine. Production KWS systems typically require at least 20 and often 100 fps in order to avoid “stepping over” a target utterance. The NDP also provides a speed advantage over low-power MCUs thanks to its parallelism and dedicated data path.</p><p dir="ltr">The Apollo's energy advantage comes with a speed penalty resulting in a maximum frame rate of 3.7fps, which will typically yield much lower real-world precision than the software accuracy of 66 percent &nbsp;(in TensorFlow on pre-aligned data) would predict.&nbsp;</p><p dir="ltr">Of the tested MCUs, only the STM32F746, from ST’s high-performance F7xx line, exceeds 20 fps, and it does so at an energy cost about 700x higher than the NDP, resulting in a power cost of about 50 mW (milliwatts), in addition to the baseline power required to power up the MCU initially.</p><h1 dir="ltr">Conclusion</h1><p dir="ltr">This test clearly demonstrates that a purpose-built compute engine for neural inference can provide energy and speed advantages over stored-program architectures. The continued development of ultra-low-power MCU’s and highly efficient purpose-built chips will bring voice to the edge in a range of applications that have the potential to disrupt the way we interact with technology.&nbsp;</p><hr><h1 dir="ltr"><em>AI Voice Applications: Call for Projects</em></h1><p><em>Are you developing devices that include a voice interface or another application of voice technology? We would love to hear from you!&nbsp;</em></p><p><em>Wevolver is looking to connect with exciting relevant projects to profile in an upcoming article about AI empowered voice applications. This is a great opportunity to get exposure among the engineering community!&nbsp;</em></p><p><em>Please leave your details via this <a href="https://forms.gle/3HuBqDiRqX3wEHtK8" rel="noopener noreferrer" target="_blank">short form</a>. &nbsp;We will be in touch shortly.</em></p><hr><h1 dir="ltr"><em>About the sponsor: Syntiant</em></h1><h2><em>Voice at the edge</em></h2><p dir="ltr"><em>Semiconductor company Syntiant is pushing forward voice at the edge possibilities with the development of the Neural Decision Processors™ (NDP10x). These high power r devices offer highly accurate wake word, command word, and event detection in a tiny package with near-zero power consumption.&nbsp;</em></p><p dir="ltr"><em>Currently, in production with Amazon’s Alexa Voice Service firmware, the NDP10x family makes Always-On Voice interfaces a reality by supporting entirely new form factors designed to wake up and respond to speech rather than touch. These processors will move voice interfaces from the cloud on to devices of all sizes and types, including ultra-portable wearables and devices.</em><em></em><br></p><hr><h1 dir="ltr">References</h1><p dir="ltr">1. <em>Zhang, Y., Suda, N., Lai, L., &amp; Chandra, V. Hello Edge: Keyword Spotting on Microcontrollers. ArXiv, abs/1711.07128. Feb 2018. Available from:</em><a href="https://arxiv.org/pdf/1711.07128.pdf" target="_blank"><em>https://arxiv.org/pdf/1711.07128.pdf</em></a></p><p dir="ltr">2. <em>Holleman, J. The Speed and Power Advantage of a Purpose-Built Neural Compute Engine, June 2019. Available from: https://www.syntiant.com/post/keyword-spotting-power-comparison</em></p><p><br></p><p dir="ltr"><br></p><p dir="ltr"><br></p><p dir="ltr"><br></p><p><br></p><p><br></p>

Ultra-low-power MCU’s and highly efficient purpose-built chips are bringing voice to the edge.

Keyword Spotting in Edge Device

<div data-element_type="widget" data-id="ece92e" data-widget_type="text-editor.default"><p>Speeding up innovation is always easier with the right tools. Additive manufacturing is already revolutionizing various industries from the <a href="https://www.sculpteo.com/en/3d-learning-hub/3d-printing-applications/3d-printed-car/" target="_blank">automotive sector</a> to the <a href="https://www.sculpteo.com/en/3d-learning-hub/3d-printing-applications/medical-3d-printing/" target="_blank">medical field</a>, can this technology disrupt the electronic industry? We will see here that 3D printing gives you the flexibility and the speed you need when building new hardware and electronic products. Discover the benefits of <a href="https://www.sculpteo.com/en/3d-learning-hub/3d-printing-applications/3d-printing-electronics/" rel="noopener noreferrer" target="_blank">3D printing for electronics</a>!</p></div><div data-element_type="widget" data-id="72893c8b" data-widget_type="heading.default"><h2>What are the advantages of 3D printing for electronics?</h2></div><div data-element_type="widget" data-id="a647257" data-widget_type="text-editor.default"><h3>3D print the perfect prototype</h3><p>3D printing helps you get from the idea to the product in a matter of days. Thus, 3D printing electronic devices appears to be really interesting. The professional 3D printers used by Sculpteo&rsquo;s online&nbsp;<a href="https://www.sculpteo.com/en/" target="_blank">3D printing service</a> allow you to create high-quality casings for your devices with the highest level of details. They will perfectly match your electronics components such as a circuit board. Rapid prototyping is also made easy thanks to the 3D printing process and will allow you to build the best product designs.</p><h3>Launch your first series</h3><p>Moreover, the electronics industry can truly benefit from additive manufacturing. No stock, no minimum number of units and short turnaround are the key upsides of using Sculpteo&rsquo;s 3D printing service for your electronic devices, regardless of where they are in product life cycle management. Electronic production is made easy thanks to our 3D printing technology and will improve and simplify your whole&nbsp;<a href="https://www.sculpteo.com/en/3d-learning-hub/3d-printing-business/rethink-your-supply-chain-management-3d-printing/" target="_blank">supply chain management</a>!</p><p>3D printing and electronics are strongly linked. Online 3D printing allows you to create a new kind of relationship with your clients. You can easily produce small series, limited editions and spare parts in a small batch. Whether you&rsquo;re looking for just a prototype or a thousand units, your 3D printing product will benefit from our experience and know-how to achieve the best quality.</p><h3>Design freedom</h3><p>Electronic components production can now be thought in terms of 3D design and not only 2D, with new ways of stacking the circuits. It opens new possibilities to design for electronics, that are new to explore! Customization is becoming a big asset while using additive manufacturing for the creation of your products: you can create parts perfectly adapted to a circuit board or any electronic device. 3D printing can be used to create personalized electronic enclosures, USB stick cases, and keyboards, for example.</p><p>Using additive manufacturing also offers you flexibility in the creation of your design. More than a perfectly adapted device, you can also elaborate complex geometries impossible to make with other traditional manufacturing techniques. With 3D printing, you can also make the most of parts that don&rsquo;t require any assembly process!&nbsp;</p></div><div data-element_type="widget" data-id="437f7296" data-widget_type="heading.default"><h2>Conductive 3D printing offering new opportunities</h2></div><div data-element_type="widget" data-id="5eeef67" data-widget_type="text-editor.default"><p>3D printing complex electronic components could go even further with <a href="https://www.sculpteo.com/blog/2018/09/04/conductive-3d-printing-how-can-additive-manufacturing-help-electronics/" target="_blank">conductive 3D printing</a>. The creation of electronic devices with conductive features using 3D printing can particularly be <a href="https://www.sculpteo.com/blog/2018/07/25/iot-and-3d-printing-how-to-combine-these-two-technologies-to-build-better-products/" target="_blank">useful to develop IoT (Internet of Things) projects</a>. This innovative technology could allow creating 3D printed devices like LED, or touch sensors. But this ability to 3D print conductive devices could be involved in bigger projects, in soft robotics, 3D electronics, and also for communication devices such as 3D printed Near Field Communication (NFC) antennas.</p></div><div data-element_type="widget" data-id="61caf8c0" data-widget_type="heading.default"><h2>3D printed electronics: What is possible?</h2></div><div data-element_type="widget" data-id="3e49c7c" data-widget_type="text-editor.default"><p>As you will see, this 3D technology can be used for various applications in the electronics industry. Get inspired by these innovative electronic devices made using additive manufacturing!&nbsp;</p><h3>3D printed circuit board by Nano Dimension and Harris Corp: 3D Printed Circuit Boards</h3><p>Nano Dimension is known to work actively on 3D printed electronic devices &nbsp;The Nano Dimension&rsquo;s DragonFly&trade; system is used to 3D print functional electronics prototypes and complex multi-layer Printed Circuit Boards (PCBs). But that is not all.</p><p>Nano Dimension and Harris Corp partnered to develop 3D printed electronic devices to create a radio frequency (RF) amplifier. They now work to go further and create hardware for the International Space Station. Their goal is to optimize the 3D printing process for RF components for flight studies aboard the ISS. Using additive manufacturing is a solution for them to find new ways to create radio frequency and circuit boards to find new innovative techniques.&nbsp;</p><h3>The Simusolar project</h3><p>At&nbsp;<a href="https://sculpteo.com/" target="_blank">Sculpteo</a>, some of our customers are working on solar energy using 3D printing. On the blog, we already told you about&nbsp;<a href="https://www.sculpteo.com/blog/2017/07/26/3d-printing-and-solar-energy-in-tanzania-simusolar/" target="_blank">Simusolar</a>, a company created in 2014 and looking to bring solar energy to the rural population of Tanzania. They develop and implement small-scale sustainable solutions to help local people in their everyday life.&nbsp;</p><p>They decided to use 3D printing because they needed a lot of custom made parts, for a low price. Their clients are farmers, fishers, or rural residents looking for various equipment powered by solar energy.</p><h3>Optomec developing the Aerosol Jet Technology</h3><p>Optomec announced that their Aerosol Jet Technology will be printing embedded electronics at the micron scale. The innovative process relies on both local deposition and local curing. This way, electronics parts are more affordable and require less waste of materials, and all of this with a superior resolution.</p><h3>Start 3D printing enclosures!</h3><p>3D printing enclosures are one of the most common uses of 3D printing for the electronic industry. Solidity, quality, customization, and accuracy, this is what you will make the most of while 3D printing your electronics enclosures.&nbsp;</p><p>If you are interested in 3D printing your own enclosure, you can follow our <a href="https://www.sculpteo.com/blog/2017/06/14/3d-printed-enclosures-learn-the-basic-design-guidelines/" target="_blank">3D printed enclosure design guide</a>!</p></div><div data-element_type="widget" data-id="542d15a" data-widget_type="heading.default"><h2>What about the future of 3D printing in the electronics industry?</h2></div><div data-element_type="widget" data-id="5fd7084" data-widget_type="text-editor.default"><p>What if in a few years, we could be able to create fully-functional smartphones or multi-material products using additive manufacturing? If these ideas are still dreams today, the innovations related to conductive 3D printing and electronic devices are now showing new opportunities. It might be time to rethink the way we conceive enclosures, circuit boards, and electronic components. From your prototyping process to the production and the management of your supply-chain, additive manufacturing could help you go through new challenges.</p><p>As you can see additive manufacturing has a lot to offer for electronics. It could become quite common to 3D print electrical elements. If you have an electronic project, but you don&rsquo;t know what software you could use to start it: here is our selection of <a href="https://www.sculpteo.com/blog/2017/11/29/top-10-of-the-best-3d-design-software-for-electronics/" target="_blank">the best CAD software for electronics</a>. Then, don&rsquo;t hesitate to try out our <a href="https://www.sculpteo.com/en/" target="_blank">online 3D printing service</a>. You will just have to <a href="https://www.sculpteo.com/en/upload/" target="_blank">upload your 3D file</a>, we will take care of it and send you your 3D printed objects in a few days.</p></div>

3D printing gives you the flexibility and the speed you need when building new hardware and electronic products.

3D printing electronics: Transforming the electronic industry

Four trends are setting the scene for 3D printing to become ever more versatile and deliver products that are closer to end-use, production level

Trends in 3D Printing

Automotive semiconductors are getting smaller and lighter. Image: Nexperia

PCB

Latest Posts

Technologies Converge to Help Drive Manufacturing Applications

Alex MacDougall is on a mission to solve a problem at the core of the electronics industry

Keyword Spotting in Edge Device

3D printing electronics: Transforming the electronic industry

Trends in 3D Printing

Putting high-performance computing into cars: automotive discrete semiconductors for autonomous driving

Profiles