Skip navigation

Analog Garage

7 posts

The auto industry is on a path to offer self-driving cars within the next several years. And with all the headlines about the rapidly advancing technology, automakers’ grand plans, and on-the-street pilot programs, it’s starting to sound as though they soon will become a reality. But a lot still needs to happen before you can pick one up at a local dealership.

 

 

 

Indeed, at least three developments must occur for the automakers to make good on their sensor-to-cloud vision for 

autonomous vehicles. Specifically, self-driving technology must:

  • become several times more reliable on the open road than humans,
  • be small enough to be integrated into the car design, out of sight, and
  • cost a small fraction of what they do today.

 

 

In one way or another, advancing the state-of-the-art in LIDAR laser detection systems will go a long way toward overcoming all three hurdles. Which is exactly what the risk-taking innovators at Analog Devices have set out to do. Through key discoveries from our team and targeted acquisitions – combined with an existing stable of core competencies in critical areas – Analog Devices is poised to get LIDAR to fit in the car. Further, LIDAR systems will enable autonomous machines in a host of other areas, like robots and drone delivery services to cargo ships and combines.  And unimaginable 3D gaming and new user interfaces with precision gesture recognition.

 

Along with RADAR and camera, LIDAR rounds out the key automotive object recognition technologies. The laser detection technology fills a critical gap in the capabilities between the other two, which is why most self-driving pilot programs feature it. Due in large part to the auto industry, in fact, the market for LIDAR sensor systems is forecasted to mushroom to $944.3 million in 2020, more than three times the size of the 2015 market, which stood at $309.8 million (Grand View Research).

 

When it comes to sensing obstacles and hazards on the road, no one object recognition technology can do it all. With robust algorithms, cameras are unmatched for spotting and characterizing objects. With enough contrast and light, they can detect and feed analytics platforms a wealth of visual detail to fuel better decision-making. But cameras cannot accurately determine the distance to objects and are highly impacted by weather and driving conditions.

RADAR is great for assessing motion and distance to targets. It can detect objects in any light and in any weather. But current systems don’t offer up much detail about the objects they spot. RADAR, in fact, may not be able to distinguish between a tree and a pedestrian standing next to it. That’s an important distinction because unless it’s Treebeard from J. R. R. Tolkien’s Middle-earth fantasy world, there’s no danger the tree will step off the curb. The pedestrian on the other hand....

 

(ADI’s upcoming 77/79 GHz Automotive RADAR will help distinguish between objects, but more detail will still be necessary.)

 

Like RADAR, LIDAR works in the dark and in most weather conditions. Unlike camera systems, scanning lasers can offer up a very accurate picture of the size and shape of objects on the road. But LIDAR systems are currently expensive, power-hungry and generate lots of data. And they’re big and unsightly.

 

Indeed, most self-driving cars on the road are easy to spot because of the clunky-looking LIDAR systems perched atop the roof. Even without that visual cue, their sticker would be easy to spot at a dealership, as well: many automotive LIDAR today costs more than twice the average selling price of cars.

 

A big part of the problem is that most LIDAR systems were designed for autopilot systems in airplanes, and for experimental projects. The systems must be re-architected for the needs of the automobile industry.

 

Enter Analog Garage Innovations in LIDAR

 

This is just the sort of problem that the Analog Garage was designed to tackle. Analog Devices established the corporate incubator program to give entrepreneurs from inside and outside the company the help to explore new technologies, applications and business models for sensor-to-cloud systems.

 

Analog Devices’ LIDAR effort began with an idea from an inside innovator. The team has been hard at work for several years developing sensor-to-cloud LIDAR systems for the automotive market. The goal was simple: make LIDAR systems so that they are good enough to sense and detect objects when cameras and RADAR can’t – but compact and inexpensive enough to make them practical for commercial automobiles. We currently have working prototypes and working on ways to further enhance performance and reduce size. 

 

Analog Devices recently acquired Vescent Photonics, a company that had developed a solid-state laser-beam steering technology. This acquisition will help Analog Devices shrink the size and cost of LIDAR systems by eliminating bulky mechanical steering while improving performance and reliability.

 

Analog Devices has pioneered solutions for automotive airbag, stability, and rollover systems for more than 20 years since the company introduced the first-ever commercial MEMS motion sensors.  Accordingly, ADI MEMS sensors are found in one-quarter of vehicle airbag systems today. A 15-year history in 24GHz and 77GHz Automotive Radar has led to ADI technology in half of Automotive Radar modules in recent development. As well, Analog Devices has key technologies that make it uniquely qualified to develop and manufacture difficult-to-make LIDAR components in high volume.

 

LIDAR is a key pillar of Analog Devices’ Drive360 autonomous driving solutions. Safe, autonomous driving relies on technologies which continuously provide redundant and reliable information. Drive360 LIDAR, RADAR and Inertial MEMS will work harmoniously and form a 360-degree safety shield around the car which provides multiple data points for vehicle positioning and object recognition. In this way, autonomous vehicles will drastically reduce traffic accidents in all cases and weather scenarios. 

 

Analog Devices is the world leader in high-speed amplifiers and data acquisition – a key technology required for LIDAR in addition to digital signal processing vital to piecing the torrent of data produced by the LIDAR system into an intelligible 3d view of the world around the car. Exactly the space where Analog Devices has been innovating for more than 50 years.

The rapid adoption of the Internet of Things (IoT) is accelerating the growth of the Industrial and Factory Automation Market, which is forecasted to reach $221.17 Billion by 2021 (Industry Arch). Since its inception, Analog Devices has been helping industrial customers automate. So, it should come as no surprise that we are keenly aware of this vast opportunity, and are challenging the status quo by bringing to life cutting-edge, cloud-connected solutions to drive Industrial Revolution 4.0.

 

Analog Devices understands the needs of the factory of the future. And through the Analog Garage, our corporate venture program, we are incubating new ideas to make factories and buildings safer, greener and smarter. Like Sentinel, an Analog Garage original industrial equipment monitoring platform. The Analog Garage has been demonstrating Sentinel at industry events for the past several months and is signing on strategic partners to begin beta-testing the platform.

 

In a recent question & answer session with Analog Garage team member Igor Chernyy, we spoke about the Sentinel platform and what it means to the market.

 

Q: What kind of interest have you been getting from the industrial equipment monitoring platform?
A: There’s been a lot of interest in sensor-to-cloud capabilities for industrial equipment monitoring. I think that companies grasp the promise of continuous monitoring – safety, efficiency, productivity. When we demonstrate Sentinel, it seems to make it real for them. It’s also helped them see Analog Devices in a different light, more than a semiconductor manufacturer, and much more of a problem solver. We demonstrated our complete system that captures thermal images sends them to the cloud for analysis by our machine learning algorithms and sends alerts and notifications to a plant manager.

 

Q: Can you describe the mechanics of the demonstration?
A: Our system includes infrared imaging sensors inside power distribution boxes that monitor continuously to detect hotspots. The system can generate real-time alerts before problems occur. Reliable power is critical to modern society, but especially so in factory floor operation where the value of the equipment – millions to billions of dollars – and the loss of revenue due to downtime can be catastrophic. To demonstrate the system, we mounted a circuit breaker box inside a clear case and power it using a PC power supply. The Sentinel camera points at the circuit breakers and our cloud-hosted algorithms perform image analysis to detect hot spots.

 

Q: How did this project come about in the Analog Garage?
A: This idea started with an employee who works in one of ADI’s wafer fabs. He helped us understand the problem more deeply. We wanted to show manufacturers how, with sensor-to-cloud platforms, they could have much finer control over preventive maintenance. You can send technicians out, and they can periodically check power boxes to ensure they’re working OK but it’s costly and time-consuming. And you do it, knowing you’re not always checking the right box at the right time. We decided to apply our hardware, cloud software, and machine learning algorithms expertise to solve this human factors problem. We thought we could help plant managers to rest easier knowing that an autonomous system would take care of monitoring their assets and simply notify them when a problem arose.

 

Q: How portable is what you demonstrated? What are some of the other applications besides on the factory floor?
A: It’s very applicable to other problems. Just about anything you can think of that requires maintenance and repair can be handled with more precision and reliability by adding sensor-to-cloud capabilities. We’ve developed a complete system using an infrared camera as the sensor. We can easily add capabilities to monitor entire factories and commercial buildings with vibration sensing, flow monitoring, or electrical power measurement. Our long-term goal is to have a comprehensive solution to monitor your factory.

 

Q: Are systems like this in place now? When do you think sensor-to-cloud implementations like this will be widespread?
A: There are some, yes. We’re seeing systems monitor very expensive oil drilling equipment, for example. And remote patient monitoring is starting to improve healthcare. But in many ways, these are still the early days. A lot of capabilities are coming into play all at once. In 10 years, I believe preventive maintenance monitoring systems will be pretty much standard on new assets and far more widespread than they are today for existing assets.

 

Q: What do you think this will mean for companies in terms of man-hours expended, money saved, improved productivity?
A: Well, it means they can save time and money. Downtime is the enemy. Avoiding downtime is a big money saver. And equipment will last longer because you’re not operating it unless it’s in tip-top shape. So more profits. Which means they can invest in new products. And build more factories.

At Analog Devices, we never stop asking “What if?” It’s what led us to invest in the Internet of Tomatoes and in SCiO spectroscopy technology. And then we asked, “What if we applied one to the other?” The question is leading to some very palatable answers.

 

The Analog Garage isn’t just about scouting around for innovations. Sometimes it’s also about making new discoveries by applying one innovation to another.

 

Take, for example, the Analog Garage’s collaboration with start-up Consumer Physics. The start-up’s SCiO spectroscopy technology uses near-infrared lasers and cloud-based analytics to determine the composition of liquid and solid materials. ADI is helping Consumer Physics to scale the solution and miniaturize it into a module small enough to embed in smartphones.

 

Mentors for ADI’s corporate incubator, together with an internal Analog Devices development team, recently found that if it could apply the sensor-to-cloud material-sensing innovation to the team’s Internet of Tomatoes project, it could not only help farmers improve yields and cut costs. It could also help them grow tomatoes that taste better.

 

The Analog Garage is always searching for tough problems whose solutions are linked to the connection between the physical world and digital.  The science of spectroscopy is well known, but the opto-electronic systems are expensive and cumbersome. New technology like handheld spectroscopes applied to the Internet of Tomatoes platform revealed a compelling use case with great potential for the precision agriculture market, which is forecasted to mushroom to nearly $5 billion by 2020.

 

Thus far, the Internet of Tomatoes initiative has helped New England farmers inject precision into their processes by planting sensors amidst rows of tomatoes to collect temperature, humidity, and ambient light measurements. Solar-powered gateways send the data up to the cloud for analysis. Farmers view insights from the system on their smartphones.

 

Precision Payoff

First, the IoT (that’s tomatoes) tackled pest management, helping farmers pinpoint the best time to treat the crops to combat specific insects. More recently, the initiative has been putting the in-field sensors to work on reducing damage from mold.

 

Historically, farmers would rely on online weather data to help decide how much to water. They now know, thanks to the Internet of Tomatoes, that the online data doesn’t correlate very well with actual plant-by-plant moisture levels. Armed with precise insights from the sensor-to-cloud system, the farmers knew to water less this past summer because the analytics revealed that, despite an extended drought, their fields were getting moisture from unusually high humidity.

 

The successes are generating interest from a growing group of farmers who now see the potential for the Internet of Tomatoes to better their businesses. So the team is beginning to develop business models to take the service to market.

 

In the meantime, the Internet of Tomatoes team is exploring new market potential by adding insight gleaned from the handheld Consumer Physics SCiO spectrometer devices. Consumer Physics plugged into the Analog Garage via MassChallenge, one of the Analog Garage’s incubator partners. (For its part, the Internet of Tomatoes sprang from an internal Analog Devices project.)

 

The Quest for Taste

The team is finding that, with their cloud analytics, they can “teach” the handheld devices to identify the tastiest tomatoes. That’s an exciting prospect for New England farmers because tomatoes suitable for the produce aisle command a tenfold premium over those destined for ketchup bottles and sauce cans, where much of  New England’s crop ends up.

 

First, the team built a quality database in the cloud. They asked three chefs to taste-test 40 tomatoes, and then they tested them destructively and recorded the results. Then late this summer, they put the system to the test at the Annual Massachusetts Tomato Contest in Boston.

 

Ahead of the tasting, the team nondestructively scanned over 400 entrants and sent their water, glucose and salt content to the cloud for analysis. After the judges’ scorecards were tabulated, it turned out that Version 1.0 of the Internet of Tomatoes’ new Taste-o-meter accurately predicted the top four tomatoes in the Cherry category, five of the top ten in the Heirloom category and the actual winner in the Field category.

 

The team is already at work to improve the system’s predictive prowess. It had better. In addition to the farmers, chefs familiar with the test are asking to buy the devices. If they had a tool that could pick tomatoes as well as they could, it would mean they could save time by sending helpers to buy produce at the market rather than doing it themselves.

 

Which just goes to show you that, sometimes, two Analog Garage projects are better than one!

The Analog Garage’s network of incubators is crucial to bringing a steady stream of discoveries to its attention. And for finding answers to the world’s energy and environmental challenges, Greentown Labs has emerged as a vital channel for Analog Devices’ venture program.

 

The Analog Garage has been working with Greentown Labs since the inception of its corporate incubator program. Pat O’Doherty, Vice President of the Emerging Business Group, sat on Greentown Lab’s advisory board up until this year.  As we entered 2017, Pat’s board seat transferred into a business unit at ADI and is now supported by Ian Lawee, GM for Energy Group at ADI.  We view this as a positive step and validation that ideas coming from cleantech startups are entering the market and changing the energy ecosystem in a great way.

 

On January 19th, Greentown Labs, the world’s largest cleantech incubator, hosted more than 80 people for the Analog Devices Startup Day, which gave startups and partners in the Greentown Labs Partner Network a chance to meet, interact and share ideas.   

 

On hand at the Startup Day were innovators working on new ways to generate, store and distribute energy to power the connected world efficiently and sustainably. Start-ups on hand included: Sense, SparkPlug Power, Multisensor Scientific, Voxel8, TagUp, and NewGrid.

 

As well, the Analog Garage displayed several demos all aimed at showcasing Analog Devices’ sensor-to-cloud capabilities for monitoring.

 

Two such demos were Sentinel, a platform that watches for hotspots in power distribution boxes to head off failures before they occur in factories and commercial buildings, and mSure for utilities to continuously monitor power meters for accuracy and tampering.

 

Watch this space for more about the latest discoveries at the Analog Garage!

The Analog Garage is adding a new accelerator to its network. Along with Ericsson and Johnson Controls, the venture arm of Analog Devices has become a limited partner in the new $2.5 million fund at Alchemist, a six-month mentor program in Silicon Valley for very early-stage startups. The three-year-old Alchemist has a successful track record, with 75 of the 138 companies mentored raising at least $500,000 within six months of graduating from the program.

“The Alchemist Accelerator’s focus on helping technical founders develop ideas that can change the game for hospitals, cities, farms, factories and other businesses fits really well with our mission at the Analog Garage,” said Pat O’Doherty, vice president for the Emerging Business Group at Analog Devices (ADI). “Our goal is to help the entrepreneurs that are innovating at the intersection of the digital and real world to disrupt industries using new and existing technologies from sensors and electronics to machine learning and energy harvesting.”

You can read TechCrunch’s coverage of this new round at Alchemist HERE.

 

Introducing the Analog Garage Master Mechanic Blog!

 

The team at the Analog Garage is excited to start blogging about the ideas we're incubating inside and outside Analog Devices.  In our Master Mechanic blog series, we’ll share work from across the Analog Garage community of start-ups, accelerators and research partners.

 

We’ll show you how these innovators and their projects bridge the gap between today’s impossible and tomorrow’s ordinary and how together we are tackling myriad challenges at the intersection of analog and digital. The Master Mechanic will share stories about energy harvesting and machine learning, as well as new sensor-to-cloud innovations we think you'll  want to hear about.

 

Through the Analog Garage, start-ups, universities, and even our own employees get the support they need to solve tough problems, collaborating in a learn fast, roll-up your sleeves and experiment environment.  The Master Mechanic will keep you updated on these emerging technologies.

 

These are lightning-fast times. So watch this space. Because this is just the beginning.

 

 

In this time of hyper-innovation, it can be difficult for inventors with new discoveries to be heard. But one Analog Garage collaboration is so compelling to hardware makers, developers and consumers alike that it managed to rise above the clatter – even at the world’s loudest tech show, CES.

 

And a not-yet-launched Analog Garage innovation made some noise behind closed doors because it enhances what everyone was hearing about at the annual event: voice UI.

 

Embedded SCiO spectroscopy technology from Consumer Physics, an Analog Garage collaborator, was on display at CES in two very different products: a smartphone and a food scale. The breakthrough uses near infrared lasers and cloud-based analytics to identify the composition of myriad liquids and solids – everything from strawberries to medications. Analog Devices is helping Consumer Physics advance the technology, making it small enough to embed in smartphones.

 

The two devices: the H2 smartphone from China’s Changhong, and the NutriSmart, from French home appliance maker Terraillon. USA Today called the H2 one of the seven devices from CES “I would actually buy.” And Chef George Duran highlighted the NutriSmart in his roundup of can’t-miss kitchen tech products. The devices also attracted coverage from many other media outlets, including Cnet, The Verge, Mashable and Venture Beat.

 

It is becoming clear that spectroscopy has a place in the consumer and enterprise markets. Consumer Physics recognized this significance early on and Analog Devices is excited to continue with the company on its journey toward opening up many more applications and industries. An upcoming Master Mechanic post will highlight the potential in smart agriculture.

 

Voice all the rage

It seemed like you couldn’t take more than 100 steps anywhere across the nearly 2.5 million square feet of show floor space without hearing about Alexa, the voice UI persona inside the Amazon Echo. She was everywhere: inside connected cars and refrigerators, Wi-Fi routers and robots, speakers and lights. Google Voice also turned up the volume on voice UI. There were many proprietary solutions as well.

 

But what good are voice commands if the hardware can’t hear you? No one wants to roll up the windows and turn off the stereo just to ask for directions to the nearest gas station.

 

That’s why the Analog Garage decided to demonstrate to prospective customers its upcoming far-field voice processor at CES, inside the serenity-challenged Las Vegas Convention Center. Because if the sensor-to-cloud machine-learning platform could make out voice commands there, then it could make them out almost anywhere.

                                                                     

We’ve got more posts planned on both the voice UI processor and Consumer Physics’ SCiO, so as always – stay tuned!