AI From the Sky: Stealth Entrepreneur’s Drone Platform Sees into Mines

Christian Sanz isn’t above trying disguises to sneak into places. He once put on a hard hat, vest and steel-toed boots to get onto the construction site of the San Francisco 49ers football stadium to explore applications for his drone startup.

That bold move scored his first deal.

For the entrepreneur who popularized drones in hackathons in 2012 as founder of the Drone Games matches, starting Skycatch in 2013 was a logical next step.

“We decided to look for more industrial uses, so I went and bought construction gear and was able to blend in, and in many cases people didn’t know I wasn’t working for them as I was collecting data,” Sanz said.

Skycatch has since grown up: In recent years the San Francisco-based company has been providing some of the world’s largest mining and construction companies its AI-enabled automated drone surveying and analytics platform. The startup, which has landed $47 million in funding, promises customers automated visibility over operations.

At the heart of the platform is the NVIDIA Jetson TX2-driven Edge1 edge computer and base station. It can create 2D maps and 3D point clouds in real-time, as well as pinpoint features  to within five-centimeter accuracy. Also, it runs AI models to do split-second inference in the field to detect objects.

Today, Skycatch announced its new Discover1 device. The Discover1 connects to industrial machines, enabling customers to plug in a multitude of sensors that can expand the data gathering of Skycatch.

The Discover1 sports a Jetson Nano inside to facilitate the collection of data from sensors and enable computer vision and machine learning on the edge. The device has LTE and WiFi connectivity to stream data to the cloud.

Changing-Tracking AI

Skycatch can capture 3D images of job sites for merging against blueprints to monitor changes.

Such monitoring for one large construction site showed that electrical conduit pipes were installed in the wrong spot. Concrete would be poured next, cementing them in place. Catching the mistake early helped avoid a much costlier revision later.

Skycatch says that customers using its services can expect to compress the timelines on their projects as well as reduce costs by catching errors before they become bigger problems.

Surveying with Speed

Japan’s Komatsu, one of the world’s leading makers of bulldozers, excavators and other industrial machines, is an early customer of Skycatch.

With Japan facing a labor shortage, the equipment maker was looking for ways to help automate its products. One bottleneck was surveying a location, which could take days, before unleashing the machines.

Skycatch automated the process with its drone platform. The result for Komatsu is that less-skilled workers can generate a 3D map of a job site within 30 minutes, enabling operators to get started sooner with the land-moving beasts.

Jetson for AI

As Skycatch was generating massive sums of data, the company’s founder realized they needed more computing capability to handle it. Also, given the environment in which they were operating, the computing had to be done on the edge while consuming minimal power.

They turned to the Jetson TX2, which provides server-level AI performance using the CUDA-enabled NVIDIA Pascal GPU in a small form factor and taps as little as 7.5 watts of power. It’s high memory bandwidth and wide range of hardware interfaces in a rugged form factor are ideal for the industrial environments Skycatch operates in.

Sanz says that “indexing the physical world” is demanding because of all the unstructured data of photos and videos, which require feature extraction to “make sense of it all.”

“When the Jetson TX2 came out, we were super excited. Since 2017, we’ve rewritten our photogrammetry engine to use the CUDA language framework so that we can achieve much faster speed and processing,” Sanz said.

Remote Bulldozers

The Discover1 can collect data right from the shovel of a bulldozer. Inertial measurement unit, or IMU, sensors can be attached to the Discover1 on construction machines to track movements from the bulldozer’s point of view.

One of the largest mining companies in the world uses the Discover1 in pilot tests to help remotely steer its massive mining machines in situations too dangerous for operators.

“Now you can actually enable 3D viewing of the machine to someone who is driving it remotely, which is much more affordable,” Sanz said.

 

Skycatch is a member of NVIDIA Inception, a virtual accelerator program that helps startups in AI and data science get to market faster.

The post AI From the Sky: Stealth Entrepreneur’s Drone Platform Sees into Mines appeared first on The Official NVIDIA Blog.

Office Ready? Jetson-Driven ‘Double Robot’ Supports Remote Working

Apple’s iPad 2 launch in 2011 ignited a touch tablet craze, but when David Cann and Marc DeVidts got their hands on one they saw something different: They rigged it to a remote-controlled golf caddy and posted a video of it in action on YouTube.

Next came phone calls from those interested in buying such a telepresence robot.

Hacks like this were second nature for the friends who met in 2002 while working on the set of the BattleBots TV series, featuring team-built robots battling before live audiences.

That’s how Double Robotics began in 2012. The startup went on to attend YCombinator’s accelerator, and it has sold more than 12,000 units. That cash flow has allowed the small team with just $1.8 million in seed funding to carry on without raising capital, a rarity in hardware.

Much has changed since they began. Double Robotics, based in Burlingame, Calif., today launched its third-generation model, the Double 3, sporting an NVIDIA Jetson TX2 for AI workloads.

“We did a bunch of custom CUDA code to be able to process all of the depth data in real time, so it’s much faster than before, and it’s highly tailored to the Jetson TX2 now,” said Cann.

Remote Worker Presence

The Double helped engineers inspect Selene while it was under construction.

The Double device, as it’s known, was designed for remote workers to visit offices in the form of the robot so they could see their co-workers in meetings. Video-over-internet call connections allow people to see and hear their remote colleague on the device’s tablet screen.

The Double has been a popular ticket at tech companies on the East and West Coasts in the five years prior to the pandemic, and interest remains strong but in different use cases, according to the company. It has also proven useful in rural communities across the country, where people travel long distances to get anywhere, the company said.

NVIDIA purchased a telepresence robot from Double Robotics so that non-essential designers sheltering at home could maintain daily contact with work on Selene, the world’s seventh-fastest computer.

Some customers who use it say it breaks down communication barriers for remote workers, with the physical presence of the robot able to interact better than using video conferencing platforms.

Also, COVID-19 has spurred interest for contact-free work using the Double. Pharmaceutical companies have contacted Double Robotics asking how the robot might aid in international development efforts, according to Cann. The biggest use case amid the pandemic is for using the Double robots in place of international business travel, he said. Instead of flying in to visit a company office, the office destination could offer a Double to would-be travelers.

 

Double 3 Jetson Advances

Now shipping, the Double 3 features wide-angle and zoom cameras and can support night vision. It also uses two stereovision sensors for depth vision, five ultrasonic range finders, two wheel encoders and an inertial measurement unit sensor.

Double Robotics will sell the head of the new Double 3 — which includes the Jetson TX2 — to existing customers seeking to upgrade its brains for access to increasing levels of autonomy.

To enable the autonomous capabilities, Double Robotics relied on the NVIDIA Jetson TX2 to process all of the camera and sensor data in realtime, utilizing the CUDA-enabled GPUs and the accelerated multimedia and image processors.

The company is working on autonomous features for improved self-navigation and safety features for obstacle avoidance as well as other capabilities, such as improved auto docking for recharging and auto pilot all the way into offices.

Right now the Double can do automated assisted driving to help people avoid hitting walls. The company next aims for full office autonomy and ways to help it get through closed doors.

“One of the reasons we chose the NVIDIA Jetson TX2 is that it comes with the Jetpack SDK that makes it easy to get started and there’s a lot that’s already done for you — it’s certainly a huge help to us,” said Cann.

 

The post Office Ready? Jetson-Driven ‘Double Robot’ Supports Remote Working appeared first on The Official NVIDIA Blog.

More Than a Wheeling: Boston Band of Roboticists Aim to Rock Sidewalks With Personal Bots

With Lime and Bird scooters covering just about every major U.S. city, you’d think all bets were off for walking. Think again.

Piaggio Fast Forward is staking its future on the idea that people will skip e-scooters or ride-hailing once they take a stroll with its gita robot. A Boston-based subsidiary of the iconic Vespa scooter maker, the company says the recent focus on getting fresh air and walking during the COVID-19 pandemic bodes well for its new robotics concept.

The fashionable gita robot — looking like a curvaceous vintage scooter — can carry up to 40 pounds and automatically keeps stride so you don’t have to lug groceries, picnic goodies or other items on walks. Another mark in gita’s favor: you can exercise in the fashion of those in Milan and Paris, walking sidewalks to meals and stores. “Gita” means short trip in Italian.

The robot may turn some heads on the street. That’s because Piaggio Fast Forward parent Piaggio Group, which also makes Moto Guzzi motorcycles, expects sleek, flashy designs under its brand.

The first idea from Piaggio Fast Forward was to automate something like a scooter to autonomously deliver pizzas. “The investors and leadership came from Italy, and we pitched this idea, and they were just horrified,” quipped CEO and founder Greg Lynn.

If the company gets it right, walking could even become fashionable in the U.S. Early adopters have been picking up gita robots since the November debut. The stylish personal gita robot, enabled by the NVIDIA Jetson TX2 supercomputer on a module, comes in signal red, twilight blue or thunder gray.

Gita as Companion

The robot was designed to follow a person. That means the company didn’t have to create a completely autonomous robot that uses simultaneous localization and mapping, or SLAM, to get around fully on its own, said Lynn. And it doesn’t use GPS.

Instead, a gita user taps a button and the robot’s cameras and sensors immediately capture images that pair it with its leader to follow the person.

Using neural networks and the Jetson’s GPU to perform complex image processing tasks, the gita can avoid collisions with people by understanding how people move  in sidewalk traffic, according to the company. “We have a pretty deep library of what we call ‘pedestrian etiquette,’ which we use to make decisions about how we navigate,” said Lynn.

Pose-estimation networks with 3D point cloud processing allow it to see the gestures of people to anticipate movements, for example. The company recorded thousands of hours of walking data to study human behavior and tune gita’s networks. It used simulation training much the way the auto industry does, using virtual environments. Piaggio Fast Forward also created environments in its labs for training with actual gitas.

“So we know that if a person’s shoulders rotate at a certain degree relative to their pelvis, they are going to make a turn,” Lynn said. “We also know how close to get to people and how close to follow.”

‘Impossible’ Without Jetson 

The robot has a stereo depth camera to understand the speed and distance of moving people, and it has three other cameras for seeing pedestrians for help in path planning. The ability to do split-second inference to make sidewalk navigation decisions was important.

“We switched over and started to take advantage of CUDA for all the parallel processing we could do on the Jetson TX2,” said Lynn.

Piaggio Fast Forward used lidar on its early design prototype robots, which were tethered to a bulky desktop computer, in all costing tens of thousands of dollars. It needed to find a compact, energy-efficient and affordable embedded AI processor to sell its robot at a reasonable price.

“We have hundreds of machines out in the world, and nobody is joy-sticking them out of trouble. It would have been impossible to produce a robot for $3,250 if we didn’t rely on the Jetson platform,” he said.

Enterprise Gita Rollouts

Gita robots have been off to a good start in U.S. sales with early technology adopters, according to the company, which declined to disclose unit sales. They have also begun to roll out in enterprise customer pilot tests, said Lynn.   

Cincinnati-Northern Kentucky International Airport is running gita pilots for delivery of merchandise purchased in airports as well as food and beverage orders from mobile devices at the gates.

Piaggio Fast Forward is also working with some retailers who are experimenting with the gita robots for handling curbside deliveries, which have grown in popularity for avoiding the insides of stores.

The company is also in discussions with residential communities exploring usage of gita robots for the replacement of golf carts to encourage walking in new developments.

Piaggio Fast Forward plans to launch several variations in the gita line of robots by next year.

“Rather than do autonomous vehicles to move people around, we started to think about a way to unlock the walkability of people’s neighborhoods and of businesses,” said Lynn.

 

Piaggio Fast Forward is a member of NVIDIA Inception, a virtual accelerator program that helps startups in AI and data science get to market faster.

The post More Than a Wheeling: Boston Band of Roboticists Aim to Rock Sidewalks With Personal Bots appeared first on The Official NVIDIA Blog.

Meet the Maker: YouTuber Insists It’s Easier Than You Think to Make Something Super Using AI

Alex Schepelmann went from being a teacher’s assistant for an Intro to Programming class to educating 40,000 YouTube subscribers by championing the mantra: anyone can make something super using AI and machine learning.

His YouTube channel, Super Make Something, posts two types of videos. “Basics” videos provide in-depth explanations of technologies and their methods, using fun, understandable lingo. “Project” videos let viewers follow along with instructions for creating a product.

About the Maker

Schepelmann got a B.S. and M.S. in mechanical engineering from Case Western Reserve University and a Ph.D. in robotics from Carnegie Mellon University. His master’s thesis focused on employing computer vision to identify grass and obstacles in a camera stream, and he was part of a team that created an award-winning autonomous lawnmower.

Now, he’s a technical fellow for an engineering consulting firm and an aerospace contractor supporting various robotics projects in partnership with NASA. In his free time, he creates content for his channel, based out of his home in Cleveland.

His Inspiration

In his undergrad years, Schepelmann saw how classmates found the introductory programming class hard because the assignments didn’t relate to their everyday lives. So, when he got to teach the class as a grad student, he implemented fun projects, like coding a Tamagotchi digital pet.

His aim was to help students realize that choosing topics they’re interested in can make learning easy and enjoyable. Schepelmann later heard from one of his students, an art history major, that his class had inspired her to add a computer science minor to her degree.

“Since then, I’ve thought it was great to introduce these topics to people who might never have considered them or felt that they were too hard,” he said. “I want to show people that AI can be really fun and easy to learn. With YouTube, it’s now possible to reach an audience of any background or age range on a large scale.”

Schepelmann’s YouTube channel started as a hobby during his years at Carnegie Mellon. It’s grown to reach 2.1 million total views on videos explaining 3D printing, robotics and machine learning, including how to use the NVIDIA Jetson platform to train AI models.

His Favorite Jetson Projects

“It’s super, super easy to use the NVIDIA Jetson products,” said Schepelmann. “It’s a great machine learning platform and an inexpensive way for people to learn AI and experiment with computationally intensive applications.”

To show viewers exactly how, he’s created two Jetson-based tutorials:

Machine Learning 101: Intro to Neural Networks – Schepelmann dives into what neural networks are and walks through how to set up the NVIDIA Jetson Nano developer kit to train a neural network model from scratch.

Machine Learning 101: Naive Bayes Classifier – Schepelmann explains how the probabilistic classifier can be used for image processing and speech recognition applications, using the NVIDIA Jetson Xavier NX developer kit to demonstrate.

The creator has released the full code used in both tutorials on his GitHub site for anyone to explore.

Where to Learn More 

To make something super with Super Make Something, visit Schepelmann’s YouTube channel.

Discover tools, inspiration and three easy steps to help kickstart your project with AI on our “Get AI, Learn AI, Build AI” page.

The post Meet the Maker: YouTuber Insists It’s Easier Than You Think to Make Something Super Using AI appeared first on The Official NVIDIA Blog.

Teen’s Gambit: 15-Year-Old Chess Master Puts Blundering Laptop in Check with Jetson Platform

Only 846 people in the world hold the title of Woman International Master of chess. Evelyn Zhu, age 15, is one of them.

A rising high school junior in Long Island, outside New York City, Zhu began playing chess competitively at the age of seven and has worked her way up to being one of the top players of her age.

Before COVID-19 limited in-person gatherings, Zhu typically spent two to three hours a day practicing online for an upcoming tournament — if only her laptop could keep up.

Chess engines like Leela Chess Zero — Zhu’s go-to practice partner, which recently beat all others at the 17th season of the Top Chess Engine Championship — use artificial neural network algorithms to mimic the human brain and make moves.

It takes a lot of processing power to take full advantage of such algorithms, so Zhu’s two-year-old laptop would often crash from overheating.

Zhu turned to the NVIDIA Jetson Xavier NX module to solve the issue. She connected the module to her laptop with a MicroUSB-to-USB cable and launched the engine on it. The engine ran smoothly. She also noted that doing the same with the NVIDIA Jetson AGX Xavier module doubled the speed at which the engine analyzed chess positions.

This solution is game-changing, said Zhu, as running Leela Chess Zero on her laptop allows her to improve her skills even while on the go.

AI-based chess engines allow players like Zhu to perform opening preparation, the process of figuring out new lines of moves to be made during the beginning stage of the game. Engines also help with game analysis, as they point out subtle mistakes that a player makes during gameplay.

Opening New Moves Between Chess and Computer Science

“My favorite thing about chess is the peace that comes from being deep in your thoughts when playing or studying a game,” said Zhu. “And getting to meet friends at various tournaments.”

One of her favorite memories is from the 2020 U.S. Team East Tournament, the last she competed at before the COVID-19 outbreak. Instead of the usual competition where one wins or loses as an individual, this was a tournament where players scored points for their teams by winning individual matches.

Zhu’s squad, comprising three other girls around her age, placed second out of 318 teams of all ages.

“Nobody expected that, especially because we were a young all-girls team,” she said. “It was so memorable.”

Besides chess, Zhu has a passion for computer science and hopes to study it in college.

“What excites me most about CS is that it’s so futuristic,” she said. “It seems like we’re making progress in AI on a daily basis, and I really think that it’s the route to advancing society.”

Working with the Jetson platform has opened up a pathway for Zhu to combine her passions for chess and AI. After she posted online instructions on how she supercharged her crashing laptop with NVIDIA technology, Zhu heard from people all around the world.

Her post even sparked discussion of chess in the context of AI, she said, showing her that there’s a global community interested in the topic.

Find out more about Zhu’s chess and tech endeavors.

Learn more about the Jetson platform.

The post Teen’s Gambit: 15-Year-Old Chess Master Puts Blundering Laptop in Check with Jetson Platform appeared first on The Official NVIDIA Blog.

It’s Not Pocket Science: Undergrads at Hackathon Create App to Evaluate At-Home Physical Therapy Exercises

The four undergrads met for the first at the Stanford TreeHacks hackathon, became close friends, and developed an AI-powered app to help physical therapy patients ensure correct posture for their at-home exercises — all within 36 hours.

Back in February, just before the lockdown, Shachi Champaneri, Lilliana de Souza, Riley Howk and Deepa Marti happened to sit across from each other at the event’s introductory session and almost immediately decided to form a team for the competition.

Together, they created PocketPT, an app that lets users know whether they’re completing a physical therapy exercise with the correct posture and form. It captured two prizes against a crowded field, and inspired them to continue using AI to help others.

The app’s AI model uses the NVIDIA Jetson Nano developer kit to detect a user doing the tree pose, a position known to increase shoulder muscle strength and improve balance. The Jetson Nano performs image classification so the model can tell whether the pose is being done correctly based on 100+ images it was trained on, which the team took of themselves. Then, it provides feedback to the user, letting them know if they should adjust their form.

“It can be taxing for patients to go to the physical therapist often, both financially and physically,” said Howk.

Continuing exercises at home is a crucial part of recovery for physical therapy patients, but doing them incorrectly can actually hinder progress, she explained.

Bringing the Idea to Life

In the months leading up to the hackathon, Howk, a rising senior at the University of Alabama, was interning in Los Angeles, where a yoga studio is virtually on every corner. She’d arrived at the competition with the idea to create some kind of yoga app, but it wasn’t until the team came across the NVIDIA table at the hackathon’s sponsor fair that they realized the idea’s potential to expand and help those in need.

“A demo of the Jetson Nano displayed how the system can track bodily movement down to the joint,” said Marti, a rising sophomore at UC Davis. “That’s what sparked the possibility of making a physical therapy app, rather than limiting it to yoga.”

None of the team members had prior experience working with deep learning and computer vision, so they faced the challenge of learning how to implement the model in such a short period of time.

“The NVIDIA mentors were really helpful,” said Champaneri, a rising senior at UC Davis. “They put together a tutorial guide on how to use the Nano that gave us the right footing and outline to follow and implement the idea.”

Over the first night of the hackathon, the team took NVIDIA’s Deep Learning Institute course on getting started with AI on the Jetson Nano. They’d grasped the basics of deep learning. The next morning, they began hacking and training the model with images of themselves displaying correct versus incorrect exercise poses.

In just 36 hours since the idea first emerged, PocketPT was born.

Winning More Than Just Awards

The most exciting part of the weekend was finding out the team had made it to final pitches, according to Howk. They presented their project in front of a crowd of 500 and later found out that it had won the two prizes.

The hackathon attracted 197 projects. Competing against 65 other projects in the Medical Access category — many of which used cloud or other platforms — their project took home the category’s grand prize. It was also chosen as the “Best Use of Jetson Hack,” among 11 other groups that borrowed a Jetson for their projects.

But the quartet is looking to do more with their app than win awards.

Because of the fast-paced nature of the hackathon, PocketPT was only able to fully implement one pose, with others still in the works. However, the team is committed to expanding the product and promoting their overall mission of making physical therapy easily accessible to all.

While the hackathon took place just before the COVID outbreak in the U.S., the team highlighted how their project seems to be all the more relevant now.

“We didn’t even realize we were developing something that would become the future, which is telemedicine,” said de Souza, a rising senior at Northwestern University. “We were creating an at-home version of PT, which is very much needed right now. It’s definitely worth our time to continue working on this project.”

Read about other Jetson projects on the Jetson community projects page and get acquainted with other developers on the Jetson forum page.

Learn how to get started on a Jetson project of your own on the Jetson developers page.

The post It’s Not Pocket Science: Undergrads at Hackathon Create App to Evaluate At-Home Physical Therapy Exercises appeared first on The Official NVIDIA Blog.

Meet the Maker: ‘Smells Like ML’ Duo Nose Where It’s at with Machine Learning

Whether you want to know if your squats have the correct form, you’re at the mirror deciding how to dress and wondering what the weather’s like, or you keep losing track of your darts score, the Smells Like ML duo have you covered — in all senses.

This maker pair is using machine learning powered by NVIDIA Jetson’s edge AI capabilities to provide smart solutions to everyday problems.

About the Makers

Behind Smells Like ML are Terry Rodriguez and Salma Mayorquin, freelance machine learning consultants based in San Francisco. The business partners met as math majors in 2013 at UC Berkeley and have been working together ever since. The duo wondered how they could apply their knowledge in theoretical mathematics more generally. Robotics, IoT and computer vision projects, they found, are the answer.

Their Inspiration

The team name, Smells Like ML, stems from the idea that the nose is often used in literature to symbolize intuition. Rodriguez described their projects as “the ongoing process of building the intuition to understand and process data, and apply machine learning in ways that are helpful to everyday life.”

To create proofs of concept for their projects, they turned to the NVIDIA Jetson platform.

“The Jetson platform makes deploying machine learning applications really friendly even to those who don’t have much of a background in the area,” said Mayorquin.

Their Favorite Jetson Projects

Of Smells Like ML’s many projects using the Jetson platform, here are some highlights:

SpecMirror — Make eye contact with this AI-powered mirror, ask it a question and it searches the web to provide an answer. The smart assistant mirror can be easily integrated into your home. It processes sound and video input simultaneously, with the help of NVIDIA Jetson Xavier NX and NVIDIA DeepStream SDK.

ActionAI — Whether you’re squatting, spinning or loitering, this device classifies all kinds of human movement. It’s optimized by the Jetson Nano developer kit’s pose estimation inference capabilities. Upon detecting the type of movement someone displays, it annotates the results right back onto the video it was analyzing. ActionAI can be used to prototype any products that require human movement detection, such as a yoga app or an invisible keyboard.

Shoot Your Shot — Bring a little analytics to your dart game. This computer vision booth analyzes dart throws from multiple camera angles, and then scores, logs and even predicts the results. The application runs on a single Jetson Nano system on module.

Where to Learn More 

In June, Smells Like ML won second place in NVIDIA’s AI at the Edge Hackster.io competition in the intelligent video analytics category.

For more sensory overload, check out other cool projects from Smells Like ML.

Anyone can get started on a Jetson project. Learn how on the Jetson developers page.

The post Meet the Maker: ‘Smells Like ML’ Duo Nose Where It’s at with Machine Learning appeared first on The Official NVIDIA Blog.

Smart Hospitals: DARVIS Automates PPE Checks, Hospital Inventories Amid COVID Crisis

After an exhausting 12-hour shift caring for patients, it’s hard to blame frontline workers for forgetting to sing “Happy Birthday” twice to guarantee a full 30 seconds of proper hand-washing.

Though at times tedious, the process of confirming such detailed, protective measures like the amount of time hospital employees spend sanitizing their hands, the cleaning status of a room, or the number of beds available is crucial to preventing the spread of infectious diseases such as COVID-19.

DARVIS, an AI company founded in San Francisco in 2015, automates tasks like these to make hospitals “smarter” and give hospital employees more time for patient care, as well as peace of mind for their own protection.

The company developed a COVID-19 infection-control compliance model within a month of the pandemic breaking out. It provides a structure to ensure that workers are wearing personal protective equipment and complying with hygiene protocols amidst the hectic pace of hospital operations, compounded by the pandemic. The system can also provide information on the availability of beds and other equipment.

Short for “Data Analytics Real-World Visual Information System,” DARVIS uses the NVIDIA Clara Guardian application framework, employing machine learning and advanced computer vision.

The system analyzes information processed by optical sensors, which act as the “eyes and ears” of the machine, and alerts users if a bed is clean or not, or if a worker is missing a glove, among other contextual insights. Upon providing feedback, all records are fully anonymized.

“It’s all about compliance,” said Jan-Philipp Mohr, co-founder and CEO of the company. “It’s not about surveilling workers, but giving them feedback where they could harm themselves. It’s for both worker protection and patient security.”

DARVIS is a member of NVIDIA Inception, a program that helps startups working in AI and data science accelerate their product development, prototyping and deployment.

The Smarter the Hospital, the Better

Automation in hospitals has always been critical to saving lives and increasing efficiency, said Paul Warren, vice president of Product and team lead for AI at DARVIS. However, the need for smart hospitals is all the more urgent in the midst of the COVID-19 crisis, he said.

“We talk to the frontline caregivers, the doctors, the nurses, the transport staff and figure out what part of their jobs is particularly repetitive, frustrating or complicated,” said Warren. “And if we can help automate that in real time, they’re able to do their job a lot more efficiently, which is ultimately good for improving patient outcomes.”

DARVIS can help save money as well as lives. Even before the COVID crisis, the U.S. Centers for Disease Control and Prevention estimated the annual direct medical costs of infectious diseases in U.S. hospitals to be around $45 billion, a cost bound to rise due to the global pandemic. By optimizing infection control practices and minimizing the spread of infectious disease, smart hospitals can decrease this burden, Mohr said.

To save costs and time needed to train and deploy their own devices, DARVIS uses PyTorch and TensorFlow optimized on NGC, NVIDIA’s registry of GPU-accelerated software containers.

“NVIDIA engineering efforts to optimize deep learning solutions is a game-changer for us,” said Warren. “NGC makes structuring and maintaining the infrastructure environment very easy for us.”

DARVIS’s current centralized approach involves deep learning techniques optimized on NVIDIA GPU-powered servers running on large workstations within the hospital’s data center.

As they onboard more users, the company plans to also use NVIDIA DeepStream SDK on edge AI embedded systems like NVIDIA Jetson Xavier NX to scale out and deploy at hospitals in a more decentralized manner, according to Mohr.

Same Technology, Numerous Possibilities

While DARVIS was initially focused on tracking beds and inventory, user feedback led to the expansion of its platform to different areas of need.

The same technology was developed to evaluate proper usage of PPE, to analyze worker compliance with infection control practices and to account for needed equipment in an operating room.

The team at DARVIS continues to research what’s possible with their device, as well as in the field of AI more generally, as they expand and deploy their product at hospitals around the world.

Watch DARVIS in action:

Learn more about NVIDIA’s healthcare-application framework on the NVIDIA Clara developers page.

Images courtesy of DARVIS, Inc.

The post Smart Hospitals: DARVIS Automates PPE Checks, Hospital Inventories Amid COVID Crisis appeared first on The Official NVIDIA Blog.

Hardhats and AI: Startup Navigates 3D Aerial Images for Inspections

Childhood buddies from back in South Africa, Nicholas Pilkington, Jono Millin and Mike Winn went off together to a nearby college, teamed up on a handful of startups and kept a pact: work on drones once a week.

That dedication is paying off. Their drone startup, based in San Francisco, is picking up interest worldwide and has landed $35 million in Series D funding.

It all catalyzed in 2014, when the friends were accepted into the AngelPad accelerator program in Silicon Valley. They founded DroneDeploy there, enabling contractors to capture photos, maps, videos and high-fidelity panoramic images for remote inspections of job sites.

“We had this a-ha moment: Almost any industry can benefit from aerial imagery, so we set out to build the best drone software out there and make it easy for everyone,” said Pilkington, co-founder and CTO at DroneDeploy.

DroneDeploy’s AI software platform — it’s the navigational brains and eyes — is operating in more than 200 countries and handling more than 1 million flights a year.

Nailing Down Applications

DroneDeploy’s software has been adopted in construction, agriculture, forestry, search and rescue, inspection, conservation and mining.

In construction, DroneDeploy is used by one-quarter of the world’s 400 largest building contractors and six of the top 10 oil and gas companies, according to the company.

DroneDeploy was one of three startups that recently presented at an NVIDIA Inception Connect event held by Japanese insurer Sompo Holdings. For good reason: Startups are helping insurance and reinsurance firms become more competitive by analyzing portfolio risks with AI.

The NVIDIA Inception program nurtures startups with access to GPU guidance, Deep Learning Institute courses, networking and marketing opportunities.

Navigating Drone Software

DroneDeploy offers features like fast setup of autonomous flights, photogrammetry to take physical measurements and APIs for drone data.

In addition to supporting industry-leading drones and hardware, DroneDeploy operates an app ecosystem for partners to build apps using its drone data platform. John Deere, for example, offers an app for customers to upload aerial drone maps of their fields to their John Deere account so that they can plan flights based on the field data.

Split-second photogrammetry and 360-degree images provided by DroneDeploy’s algorithms running on NVIDIA GPUs in the cloud help provide pioneering mapping and visibility.

AI on Safety, Cost and Time

Drones used in high places instead of people can aid in safety. The U.S. Occupational Safety and Health Administration last year reported that 22 people were killed in roofing-related accidents in the U.S.

Inspecting roofs and solar panels with drone technology can improve that safety record. It can also save on cost: The traditional alternative to having people on rooftops to perform these inspections is using helicopters.

Customers of the DroneDeploy platform can follow a quickly created map to carry out a sequence of inspections with guidance from cameras fed into image recognition algorithms.

Using drones, customers can speed up inspections by 80 percent, according to the company.  

“In areas like oil, gas and energy, it’s about zero-downtime inspections of facilities for operations and safety, which is a huge value driver for these customers,” said Pilkington.

The post Hardhats and AI: Startup Navigates 3D Aerial Images for Inspections appeared first on The Official NVIDIA Blog.

You Can’t Touch This: Deep Clean System Flags Potentially Contaminated Surfaces

Amid the continued spread of coronavirus, extra care is being taken by just about everyone to wash hands and wipe down surfaces, from countertops to groceries.

To spotlight potentially contaminated surfaces, hobbyist Nick Bild has come up with Deep Clean, a stereo camera system that flags objects that have been touched in a room.

The device can be used by cleaning crews at hospitals and assisted living facilities or anyone  who’d like to know what areas need special attention when trying to prevent disease transmission.

Courtesy of Nick Bild.

Deep Clean uses an NVIDIA Jetson AGX Xavier developer kit as the main processing unit to map out a room, detecting where different objects lie within it. Jetson helps pinpoint the exact location (x,y-coordinates) and depth (z-coordinate) of each object.

When an object overlaps with a person’s hand, which is identified by an open-source body keypoint detection system called OpenPose, those coordinates are stored in the system’s memory. To maintain users’ privacy, only the coordinates are stored, not the images.

Then, the coordinates are used to automatically annotate an image of the unoccupied room, displaying what has been touched and thus potentially contaminated.

Nick the Bild-er: Equipped with the Right Tools

When news broke in early March that COVID-19 was spreading in the U.S., Bild knew he had to take action.

“I’m not a medical doctor. I’m not a biologist. So, I thought, what can I do as a software developer slash hardware hacker to help?” said Bild.

Juggling a software engineering job by day, as well as two kids at home in Orlando, Florida, Bild faced the challenges of finding the time and resources to get this machine built. He knew getting his hands on a 3D camera would be expensive, which is why he turned to Jetson, an edge AI platform he found to be simultaneously affordable and powerful.

Deep Clean’s stereo camera system. Image courtesy of Nick Bild.

“It’s really a good general-purpose tool that hits the sweet spot of low price and good performance,” said Bild. “You can do a lot of different types of tasks — classify images, sounds, pretty much whatever kind of AI inference you need to do.”

Within a week and a half, Bild had made a 3D camera of his own, which he further developed into the prototype for Deep Clean.

Looking ahead, Bild hopes to improve the device to detect sources of potential contamination beyond human touch, such as cough or sneeze droplets.

Technology to Help the Community

Deep Clean isn’t Bild’s first instance of helping the community through his technological pursuits. He’s developed seven different projects since he began using NVIDIA products when the first Jetson Nano was released in March 2019.

One of these projects, a pair of AI-enabled glasses, won NVIDIA’s Jetson Community Project of the Month Award for allowing people to switch devices such as a lamp or stereo on and off simply by looking at them and waving. The shAIdes are especially helpful for those with limited mobility.

Bild calls himself a “prototyper,” as he creates a variety of smart, useful devices like Deep Clean in hopes that someday one will be made available for wide commercial use.

A fast learner who’s committed to making a difference, Bild is always exploring how to make a device better and looking for what to embark upon as his next project.

Anyone can get started on a Jetson project. Learn how on the Jetson developers page.

The post You Can’t Touch This: Deep Clean System Flags Potentially Contaminated Surfaces appeared first on The Official NVIDIA Blog.