InDro explores USV marine sector – and speaks with a PhD researcher on their work

InDro explores USV marine sector – and speaks with a PhD researcher on their work

Nov 13, 2024 | Engineering, Industry News, Marine USVs, Scott Simmie

By Scott Simmie

 

At InDro Robotics, there’s nothing we love more than research and development.

That shouldn’t be a surprise, because that’s how the company was built. From our early work building and modifying Uncrewed Aerial Vehicles (UAVs) for clients and service provision through to a wide variety of Uncrewed Ground Vehicles (UGVs) we have invented or customised for customers, R&D has always been the heart and soul of InDro. That’s why we have a large and continually scaling team at our Area X.O operations in Ottawa.

We’ve previously done work on the marine side of things and have built and tested Uncrewed Surface Vehicles. Our ‘Talos” USV was remotely piloted and carried a sonar that was deployed via winch. We successfully deployed that on multiple missions, mapping lakebeds and vegetation. Its capabilities were excellent, but our priorities shifted to the aerial and ground side of robotics due to client demands. But we’ve always kept a close eye on marine robotics developments, particularly when it comes to R&D.

There are some really exciting companies in this space in Canada, including Open Ocean Robotics. We are very impressed with its DataXplorer, a solar-powered and self-righting autonomous vehicle suited for long-range data acquisition in the open ocean. It’s a brilliant design, and Co-Founder and CEO Julie Angus is a very impressive individual. With an MSc in Molecular Biology, she’s both a serial entrepreneur and was the first woman to row across the Atlantic Ocean from mainland to mainland. She’s a director on NATO’s Maritime Unmanned System Initiative Innovation Advisory board and was honoured with National Geographic’s Adventurer of the Year award for her trans-Atlantic achievement. Like we said, impressive.

Another company that has caught our attention at conferences is Deep Trekker. It has a solid lineup of ROVs, and we were able to operate its smallest offering at a couple of different trade shows. Recently, it launched an Uncrewed Ground Vehicle that is also submersible. We can see a wide variety of use-cases.

Below: An Open Ocean Robotics video shows off DataXplorer, followed by the InDro Robotics Talos

InDro Robotics Talos

THE R&D FACTOR

 

Of course, companies can’t create products like these without a significant investment in research and development. This is something we truly understand.

We also know that many innovations have their genesis in a lot of hard work from graduate students and those holding PhDs, who often put in untold hours on projects that can lead to commercial breakthroughs. So we thought it would be enlightening to spend some time talking to one of those people.

We sat down for a chat recently with Thomas Sears, a PhD candidate in Electrical and Computer Engineering with Queen’s University’s Offroad Robotics and Ingenuity Labs Research Institute. He holds a Master of Applied Science in Aerospace Engineering and is a Professional Engineer.

And he’s really, really interested in boats and waves. Specifically, working with USVs to learn more about predicting wave patterns and – ultimately – creating algorithms so that autonomous or pilot-assist systems can anticipate what waves might be coming and how best to orient a boat depending on what those waves are likely to do and the desired outcome.

Sears is a really good explainer. And he started the conversation by talking about humans anticipate and react to waves when they are in the water.

 

HOW PEOPLE REACT

 

“As humans when we go to the beach, we can kind of intuitively feel the waves coming and we know, OK, it’s probably four more seconds for another wave,” he says. “How do we give the boat that intuition to know: If I felt a wave here, if I move forward three meters, I’m probably going to feel in four seconds that wave is going to hit me from the side.”

That takes a lot of math, plus a bunch of sensors. But to what end? Is it simply to help ensure a boat might not capsize in rough water?

Well, explains Sears, there are a wide variety of use-case scenarios. Understanding waves, being able to predict them, could for example be of great use to Kingston colleagues who are coastal engineers and study the impact of waves on the coastal environment. A deep understanding of the math and physics involved could be highly useful in predictive models. What’s going to happen to this coastline over time? During a powerful storm?

But there are many other applications. Returning to the human example, Sears points out when a wave is approaching, a human being carries out their own calculations and braces themselves for impact.

“I’d like the boat to be able to do the same thing. If the boat can be out in the water and it can start to notice this trend, whatever the trend is, maybe I can then take an action on that trend,” he says before outlining multiple options for how a boat might respond:

“‘Aha, I’m about to get pushed by the wave.’ Maybe I’d like to surf the wave. Maybe I’d like to push against the wave. Maybe I’d like to turn so I’m safer, whatever that is. That’s sort of for the next person to work on.”

But the work being carried out by Sears will lay the foundation for that next step. He can see, even with an identical set of waves, there might be different optimal autonomous responses depending on the scenario.

“We could see this getting scaled up to crewed vessels…The boat could essentially say: ‘OK, well, we’re worried about passenger comfort.’ Or ‘We’re worried about fuel efficiency’, whatever it (the use-case) is. I’d like to just dial in that option and then the boat can start to go: ‘OK, well, given these wave conditions, here’s how we might want to act.'”

But to get there, you need research, data and predictive models.

“Without the ability to make those predictions of the waves, we have no information to act on. We would just be acting reactively. So we would just say: ‘Oh, I just got hit by a wave, do something quickly’.”

In other words, the boat has to understand what’s coming. And here, things get even more complicated. A boat doesn’t respond immediately to inputs the way an electric car does.

“When you start energizing the motors, it doesn’t move instantly. It starts churning water before something happens. Boats have a bit of a spin-up.”

So that, too, has to be factored into the equation(s) – and would have to be factored into future algorithms suited to specific boats.

“It’s the opportunity to look not just forward in time, but look around the boat for maybe a nicer spot to sit; to let me take an action before the motors are ready to go. So I can I can sort of pre-empt things, which is a sort of a superpower that I’d like to give these boats.”

Below: Thomas Sears with the USV, followed by the USV on a calm day (photos courtesy of Offroad Robotics). YouTube video shows Sears explaining his research

Kingston University Thomas Sears USV
Kingston University Thomas Sears USV

A CUSTOM USV

 

This is the perfect kind of research for an Uncrewed Surface Vehicle. But to get the right USV took a lot of work from Sears and his team.

They initially were looking for an off-the-shelf USV that would come with most of what they needed. And those needs included the Robot Operating System (ROS) software. They had plans to purchase something from a Canadian robotics company, but it had just ended production on its USV. So they were left with simply finding a base platform and doing all the modifications themselves. Researchers often prefer to put their time into algorithms and R&D rather than building and integration, but that was the option they were left with. Thankfully, with his background in Electrical Engineering this was a task Sears was capable of carrying out.

“The boat that we purchased was not designed for robotics research,” he says. “We had to take on a lot of the non-recurring engineering work of turning it into a research vessel. I’ve been involved in everything from the algorithms that are running on board to picking the computer that is running those algorithms. I happen to come from a background where that’s a comfortable thing for me.”

Doing that work, says Sears, was a “considerable time-sink” – but having a ROS-based platform was critical to the research. They not surprisingly went with ROS 2, the latest iteration of the Robot Operating System. The team actually wrote the interface software themselves, and released it on GitHub.

Then there was the sensor integration: The hardware, the wiring, the software. Plus, of course, making everything waterproof. There was a high performance Inertial Measurement Unit (IMU) and a 16-beam Velodyne LiDAR. It was only when the USV was dispatched that they discovered the LiDAR beams were absorbed by the water. It was, he says, a “weird” thing.

“So unlike our our ground vehicles, where we see the ground, we see the floor, the boat is just floating in nothingness. But the really cool thing is we can leverage that because now if we see something, we know it’s not water. We just see objects – so we don’t have to worry about segmenting out ground and objects.”

That has been particularly useful in research by others using the same USV that involves identifying the coastline. The USV also carries a dual-antenna RTK-enabled GPS receiver.

“That’s critical on a USV platform because you can move sideways on a boat, if the water pushes you sideways, you can move sideways,” he says. “And that fuses with the gyroscope and with the accelerometers on board to give us a really good position measurement.”

For the data to be useful. Sears has to know precisely where the USV is at any given moment – both in terms of its absolute position and its position relative to the waves. There’s also a sonar unit, which is of great use to researchers on the civil engineering side of things. There’s also a camera on board, though Sears laughs that watching its feed is “nausea-inducing.”)

With Queen’s University’s proximity to Lake Ontario, Sears and others can literally launch the USV in about 20 minutes. They also do research inside a wave tank at Queen’s.

 

THE BIGGER PICTURE

 

As mentioned, other researchers at the university also capture and analyze data from the USV. All of them have a deep appreciation for the importance of Lake Ontario – and not just as a shipping corridor.

“Lake Ontario is full of life. It’s our source of water for drinking and agriculture, so it needs to be monitored and protected,” says Sears. “Having these water drones watching the lake on our behalf is going to help us ensure that the lake stays healthy, that we stay healthy, that wildlife stays healthy.

“We‘re working toward monitoring this very large space uninhabited by humans that we take for granted in daily life.”

Below: Queen’s University researchers look at data being collected by the USV

 
Kingston University Thomas Sears USV

INDRO’S TAKE

 

Marine robotics are kind of the third leg when it comes to uncrewed vehicles. And, given our reliance on water, a very important one. Our initial vision for InDro Robotics was that we would develop products for all three realms – and we’re still quite proud of our Talos USV.

But during the company’s initial growth we made the decision to put our energy into UAV innovations such as remote teleoperations, deliveries, enhanced service provision and more. (InDro was the first company in Canada to operate UAVs over 4G and 4G, and was the first to obtain a cargo license for drones from the Canadian Transportation Agency, among other firsts). This decision was largely driven by customer demand at the time, as well as our then-startup status.

InDro has now scaled sufficiently that we are once again exploring the marine sector.

“We will have some ROS-based offerings soon that we can customize to enable R&D researchers and commercial clients to carry out complex data acquisition in a marine environment,” says InDro Robotics Founder and CEO Philip Reece. “We’re testing the waters, so to speak, but are optimistic this could be the  next sector for our engineers to tackle.”

Already, we have some platforms available that can be used for cleaning surface garbage and cutting aquatic vegetation that’s impinging on the surface. But, like all of InDro’s offerings, these can be customized with additional sensors and teleoperation capabilities based on client needs.

“We have had a mandate since Day One that we want to be experts in unmanned systems,” says Head of R&D Sales Luke Corbeth. “To date, that’s really meant just UAVs and ground robots. But ultimately, we want to be experts on land, air and water. This is our first move into water, and I’m incredibly excited.”

We all are. If you’re interested in our offerings, contact us to learn more.

Feature image at top of story shows the DataXplorer in action; photo courtesy of Open Ocean Robotics

NAV CANADA says enhanced capabilities coming to NAV Drone app

NAV CANADA says enhanced capabilities coming to NAV Drone app

Nov 11, 2024 | Aerial Evolution Association of Canada, Industry News, NAV CANADA, NAV DRONE, Scott Simmie

By Scott Simmie

 

If you’re an RPAS pilot in Canada, you’re likely using NAV Drone (and if you’re not, you should be).

The mobile and web app from NAV Canada is the app to ensure your mission is approved. As the NAV CANADA website explains: “NAV Drone is the only app that lets you safely and legally request permission to fly a drone in airspace controlled by NAV CANADA. From the web or a mobile device, professional and recreational drone pilots and operators can easily see where they can and cannot fly with interactive maps and, when needed, submit requests to fly in controlled airspace.”

It’s a snap to use. The app lets you know where you can fly – and where you can’t – and could save you from both dangerous operations and potential fines. The app also notifies you if there are other drone operations underway in the vicinity of your operations, which is really useful for situational awareness.

Last week, at the Aerial Evolution Association of Canada‘s annual conference and exhibition, NAV CANADA offered an update on usage stats for the app – and revealed there are more enhancements on the horizon.

Below: Screengrabs from the NAV Drone mobile app, followed by a NAV CANADA explainer video

NAV Drone
NAV Drone

BY THE NUMBERS

 

NAV Drone has been operational now for several years. There was a lot of buzz in the industry when it was first released, but what has that translated to in terms of actual use? Here, NAV CANADA offered some numbers – which indicate the app has been widely embraced across the sector.

In 2024, NAV Drone had processed 53,000 permission requests as of early November, a growth rate of 26 per cent over the previous year. By automating this process – and avoiding manual approval (30 minutes per request at $130/hour), NAV CANADA says the app has saved more than $6.5M in Air Traffic Service (ATS) costs. What’s more, users seem to really like the app; it has excellent ratings on the App Store and Google Play.

And, of course, NAV Drone has greatly enhanced safety (and provided a huge amount of data) for NAV CANADA, the country’s privately run non-profit corporation that operates our civil air navigation system.

“Safety is the key reason it’s there. It’s all about keeping the airspace safe,” explained Alan Chapman, NAV CANADA’s director of RPAS Traffic Management.

As we head toward increased RPAS traffic, including regulations that will permit low-risk Beyond Visual Line of Sight flights in 2025, NAV CANADA has bold plans to enhance the offerings of the NAV Drone app. And that’s good news for both RPAS operators and also those operating traditional crewed aviation.

“Some big changes are coming to NAV Drone in 2025,” said Stewart Paveling, Product Family Leader, RPAS Traffic Management NAV CANADA during a panel discussion.

That includes a number of additional features to the app, including greater capabilities with RPAS Traffic Management (RTM), low-risk BVLOS and EVLOS flight approvals – Including the ability to record flights undertaken with a Special Flight Operations Certificate through the app.

These are big changes, indicative of recognition this industry will continue to grow as well as NAV CANADA’s desire to safely help the industry expand as we head, ultimately, into the era of Advanced Air Mobility (AAM).

“NAV CANADA’s strategic direction positions us to take a leadership role to effect change across the air navigation system,” read a slide during its presentation. “To unlock not just our own potential, but also the potential of the industry to be more effective, more efficient, and more environmentally sustainable going forward.”

To further emphasise that, the slide continued – including the bold in the following paragraph:

“RTM facilitates the safe integration of RPAS, in a highly automated way, enabling growth of operations and expansion of use cases to capture the potential aviation and societal benefits.”

That was followed by a high-level road map indicating priorities for the coming years.

NAV CANADA Nav Drone

NEXT STEPS

 

Following the slides, there was a panel discussion about future plans, along with other suggestions on ways to improve the existing app. In addition to Alan Chapman and Stewart Aveling, the panel included Joanne Moon (Manager of RPAS Operations, NAV CANADA), Anne Sophie Ripple-Bouvier (Flight Safety Officer, Aerial Evolution Association of Canada) and Brian Fentiman (Project Manager, InDro Robotics/CEO BlueForce UAV Consulting, Inc.).

As the slide above notes, NAV Drone will keep pace with Transport Canada regulations – including the much anticipated changes that will allow low-risk BVLOS flights in 2025. The emphasis here is on pushing the envelope with a highly automated RTM system “to support safe, efficient and scalable BVLOS operations.”

For years, the sector has been eager to enable BVLOS flight without the need for a time-consuming Special Flight Operations Certificate. This obviously opens the door to a broad range of use-case scenarios, ranging from monitoring long-range assets like railroad tracks and pipelines through to large-scale mapping and other data acquisition.

For those operations that will still require an SFOC, NAV Canada revealed that the capability will be in place to allow flights to be recorded in the app. Though that will simplify the process of recording for operators, NAV Canada will not approve SFOCs; these applications will still be reviewed by Transport Canada, which is responsible for approving SFOCs.

Later this year, Paveling added, there will be new map layers for restricted airspace. NAV Canada is also planning to improve the flight clipboard that comes with the system, redesigning it and making it easier to read. There will also be changes to the web-based support site, including a move away from PDF manuals “with better content that’s easier to consume and search.”

Outside of the app, NAV Canada said it is working to beef up its ability to detect drone incursions.

“We see reports of RPAS in control zones on approach paths,” said Joanne Moon of NAV Canada, adding that the corporation also obtains data from drone detection systems in place at airports. (InDro Robotics is the chief technology partner with the drone detection system at YOW. That data is shared with NAV CANADA and Transport Canada, among others.)

NAV Canada, she said, is looking at strengthening its capabilities and enforcement in this arena.

“(We’ve) Been working with industry partners, looking at things like drone detection, information sharing, emergency response, collaboratiion with airport authorities (as well as) our own air traffic services unit.”

 

OTHER IMPROVEMENTS

 

There was also an opportunity during the panel to discuss other improvements that could be made to the NAV Drone app. And here, InDro’s Brian Fentiman offered some suggestions.

“One of the biggest things I find, more as a trainer than an operator, is the weak spot. The weak spot seems to be emergency procedures…With a flyaway, I would much prefer that there’s a single number. I’d like to see that phone number up front so it’s easy for people to find. In controlled airspace, you do get a phone number but it’s buried in a flight report…Sometimes you’ll get that phone number and the tower is not even open during those hours.”

It’s an important point – and one NAV Canada says it’s about to address.

“We are actively working on that right now…for an upcoming change to NAV Drone,” said Moon.

The other point Fentiman raised was with regards to conspicuity – meaning the electronic visibility of a drone within a broader RTM system.

“To enable BVLOS, we need conspicuity…whether it’s from the drone to other (RPAS) traffic or to commercial aviation,” he said.

That is something, said NAV CANADA, that is precisely on its roadmap. And the best way to fully get there, it was suggested, was to ensure that everyone in the industry uses the NAV Drone app.

“The more people who use the tool, the better situational awareness we have,” said Chapman.

Below: Brian Fentiman on the NAV CANADA panel at AEAC2024. Photo by Scott Simmie, InDro Robotics

Brian Fentiman AEAC 2024 NAV CANADA

INDRO’S TAKE

 

The annual Aerial Evolution Association of Canada’s conference and exhibit is always a great event – and precisely due to learning opportunities like this one. Conversations with bodies like NAV CANADA and Transport Canada are tremendously important for the growth of the sector.

“We are fortunate in Canada to have a collaborative relationship with NAV CANADA and Transport Canada, as that’s not always the case between the industry and regulators or air traffic systems organizations,” says Philip Reece, Founder and CEO of InDro Robotics.

“We have seen a true evolution over the years in terms of this relationship – and from both sides. There’s a greater recognition now from the industry that safety has to remain paramount if the sector is going to continue its growth trajectory. And we’ve also seen a real willingness from NAV CANADA and Transport Canada to work with RPAS operators to safely continue growth. The NAV Drone app – and how widely it’s now used – is evidence of this collaboration from both sides. We look forward to enhanced capabilities on this already excellent tool.”

Want to learn more about the benefits of membership with the Aerial Evolution Association of Canada? You can find all the details here.

Feature image by Scott Simmie, InDro Robotics

GCXpo 2024: A stunning showcase of Smart Mobility

GCXpo 2024: A stunning showcase of Smart Mobility

Sep 27, 2024 | GCXpo, Industry News, Scott Simmie, Smart Mobility

By Scott Simmie

 

The third annual showcase of Canada’s Smart Mobility sector – formerly known as TCXpo – is a wrap.

Bringing together more than 80 companies from across Canada and abroad, more than 1500 attendees registered to see the latest and greatest innovations – some of them being shown publicly for the first time. Ground robots, drones, even agricultural equipment and demonstrations of new technologies – it was all on display at Ottawa’s Area X.O, a private facility where technology companies (including InDro Robotics) build and test innovative products on a daily basis.

This was the largest event so far – and that’s reflected in the title. It’s now called “GCXpo” – with the first two letters standing for Government of Canada (the previous “TC” stood for Transport Canada). It’s a reflection of the importance Canada puts on supporting this growing sector as companies develop new products and push toward commercialisation. And there are a *lot* of agencies and departments behind this event.

GCXpo is hosted by Area X.O and operated by Invest Ottawa in partnership with the Government of Canada and event sponsors, including:

“GCXpo Is truly about celebrating Canadian innovation, companies driving the smart revolution that are changing our country for the better,” said Invest Ottawa President and CEO Sonya Shorey during opening remarks. She also pointed out why Area X.O in the nation’s capital is such a fitting location: Ottawa per capita, has “the top tech talent concentration in all of North America.”

And GCXpo 2024 did not disappoint.

Below: A crowd watches as Matt Johnston, Assistant Test Integration Engineer with Lockheed Martin Skunkworks Calgary, demonstrates a drone that can fly (and land) in GPS-denied environments, followed by the drone in flight. All photos by Scott Simmie

A LOT TO SEE

 

With some 80 companies, government agencies, academic institutions and others at the show, there was a lot of ground to cover. And while the exhibits were underway, the CAVCanada Stage provided top-flight panels and keynotes on a wide range of topics.

InDro Robotics Founder and CEO Philip Reece took part in a panel entitled: “Creating the Cities of Tomorrow,” which looked at how municipalities and regulators can best work together to safely encourage the transition toward newer technologies.

‘I would say failing fast is a super important thing,” he said. “We started flying drones 10-12 years ago, when it was really new. And the answer to everything at the start was: ‘No, you can’t do that.’ So instead of accepting that, we basically brought them (Transport Canada) with us, and we’d say ‘What would it take to do this? How can we do this next step?'”

There were some failures, but with the regulator on site there was a joint understanding of why things had failed – and the willingness to work together to identify those points of failure and take another run at things. This helped both the company – and the regulator itself. And it ultimately led toward a new way of thinking – with both parties viewing themselves as partners with a common goal.

“It’s much better to invite them in – let’s (jointly) spur innovation forward,” said Reece.

Interestingly, as the move toward Smart Cities continues, there’s obviously a lot of adoption of AI technologies and research in that realm. Because those AI processors can use a lot of energy – and because AI-enabled devices are starting to become ubiquitous in our lives – Ottawa Hydro has noticed a surge in energy demands and has had to adjust its own resources to ensure it’s keeping up with the transition. This surge has also, presumably, been influenced by the increasing adoption of electric vehicles (which, in addition to charging, rely heavily on AI).

“Bringing on AI has a very different energy footprint, and it’s not just one section of the city we’re seeing that in – we’re seeing it throughout,” said Julie Lupinacci, Chief Customer Officer with Ottawa Hydro.

“We’re moving from a utility that was planning and building one substation every five years – to one every year. So these are very interesting and exciting times, but it’s very crucial to get this right for the future.”

Below: InDro Robotics CEO Philip Reece

FROST, FOG AND Electric vehicles

 

If you’re a Canadian who drives in the winter, you’ll know all about the challenges of frost and fog on your windshield. But you likely haven’t given much thought to the energy requirements it takes to de-ice or de-fog that windshield, particularly in electric vehicles (EVs).

But one Ontario company based in Oakville, Betterfrost Technologies, has given this problem a lot of thought over many years. And it has developed a solution for the problem that uses 10x to 20x less energy than traditional methods.

And how does it do that? Well, there’s an invisible layer in the windshields of most cars today that is used for passive cooling, by deflecting infrared rays. That same layer can be energised using rapid pulses of power to concentrate on melting the frost or ice right where at counts: At the point where it adheres to the windshield. The company has produced an algorithm that’s embedded on a small chip that can be added to pretty much any modern vehicle with a couple of wires. When that algorithm gets the energy pulsing at the right frequency and intensity, that boundary layer is quickly and efficiently melted, allowing for the easy physical removal of frost or ice.

“This was researched at New Hampshire’s Dartmouth College’s Ice Research Laboratory,” explains company co-founder and CTO Sameh Saad. “They looked at how ice attaches to surfaces and the best way to break that bond, between ice and any surface. Most of the stickiness of ice happens at the interface. So if you can melt the ice at the interface it will fall off with external force.”

And so the company developed an algorithm that ensures the heat only goes to that boundary layer – and isn’t wasted beyond.

“The pulsing gives us better control, so the heat doesn’t move as far. So even though the pulsing is high power, the way this works leads to low energy consumption,” says CEO Derrick Redding.

And it’s not just about EVs.

“The other application besides automotive is aerospace, where airplane wings or critical surfaces need to be clear of ice and frost before takeoff and during flight,” says Saad. “So this could be done using the same technology, using a polymer coating. And if we do automotive vehicles, we can do defence vehicles, bridge windows on ships – it doesn’t matter how thick the glass is. What’s important is that we can defrost it and defog it very quickly.”

The company has been around since 2015, and Better Frost Technologies is hoping its product may soon come standard on vehicles straight off the production line.

“We’re working closely with two car OEMs and one truck OEM, and that’s going very well,” says CEO Redding.

Below: CTO Sameh Saad, a mechanical engineer, with the company’s proprietary algorithm-embedded chip.

Better Frost Technologies CTO Sameh Saad

A LITTLE BIT OF EVERYTHING

 

Though the overarching theme of the show is Smart Mobility, one of the joys of this event is the variety of companies showing off innovations you might not immediately associate with the sector but which are nonetheless both interesting and related. One such surprise was KTV Working Drone Ottawa, a company that uses a drone for high-rise window and facade cleaning. The company’s president, Gesummino Sala, explained he’d come across the idea of using drones for cleaning, and was thinking of starting his own drone company.

He then discovered Norwegian company KTV Working Drone already had such a product and was franchising it. In fact, it had operations in Halifax and Vancouver. Sala managed to secure the franchise for Ottawa (along with rights for a large portion of Ontario). He launched earlier this month.

“It’s been about a year in the making, but lots of preparation was needed for this,” he says.

The platform is a DJI M350 RTK, where that realtime kinematic sensor allows for very precise positioning. A hose attached to a spraying unit on that drone sucks up purified water (to 0 ppm) heated to 80° C and applies it directly to the windows of facade. Because of that hot, pure water – Sala says the building dries quickly and cleanly. He says the drone can loft that hose up to the Transport Canada ceiling of 400′ AGL, meaning it could clean a 40-storey building.

“The finish is spotless,” says Sala. “It’s safer, the building doesn’t get damaged from swing stages (which are used in traditional window washing operations), it’s more efficient, and it’s faster. Everybody’s interested; people who have heard about it want to see it.”

Below: KTV Working Drone Ottawa’s President, Gesummino Sala

RIDESHARK

 

When it comes to commuting, Smart Mobility doesn’t just mean autonomous vehicles (though there were plenty of those at GCXpo). It can also mean a smarter way of commuting that will eventually include self-driving cars. And that’s why an Ottawa-based company called RideShark was at the show. We asked President and Co-Founder Sharon Lewinson to give us the elevator pitch.

“RideShark is a multi-modal platform that helps people choose sustainable transportation options to reduce congestion, emissions, and improve quality of life,” she says.

And how does it do that? Well, with a very sophisticated mobile app.

“In one click, a person can enter their destination and it automatically gives them all their multi-modal transportation options: Carpool partners, transit options, bike buddies, shuttles…And then it has carpooling. People can book, pay and communicate all in-app.”

RideShark sells its SaaS platform to clients, and it’s then “white labelled” – meaning the app might bear the name and branding of a university, large corporation, or one of the many other institutions and sectors where it’s in use. The company secured Nortel as its first customer back in 2006. It’s grown a lot since then, and has multiple high-profile clients across North America.

Now, says, Lewinson, it’s time for the next step.

“We’ve been around a lot and now we’re looking to globally scale. We’re a partner with Invest Ottawa – they provide a lot of support. GCXpo is where the future is of what we call ‘unified mobility.’ With all the autonomous vehicles, ultimately they have to get people into those vehicles – and our technology will help with that.”

Below: A video explaining how RideShark works, followed by a photo of company president Sharon Lewinson.

Sharon Lewinson RideShark

THE NEXT GENERATION

 

Innovation is on a stellar trajectory. With the accelerated use of AI and related technologies, the breakthroughs just keep on coming. So it’s worth noting that many educational institutes were at GCXpo, along with government agencies and accelerators that help fund startups to encourage continued innovation.

We stopped briefly at the Algonquin College booth, partly to let them know we’d recently profiled two InDro employees – both of whom came to Canada from India – to study engineering there. (Their story documents a pretty remarkable voyage and can be found here.)

“Why GCXpo?” we asked Algonquin representatives.

“We’re here to kind of market the value of not only the Co-op & Career Centre, but everything our Experiential and Innovation centre can offer – ranging from applied research, co-op positions, through to entrepreneurship co-ops,” explained Ashoka Patel, the College’s Industry Engagement Specialist Team Lead.

“When we’re at these events, we want to meet with anyone interested in attending the college, so (we talk about) work-integrated learning opportunities, which could be a placement, a short-term internship. And then we speak to our current students to encourage them to look for jobs and ask how we can help them, help out with research projects. And then we want to meet with employers and see what we kind of different programs we can provide to students and graduates.”

And, says Patel, that commitment doesn’t end with commencement.

“Once a student leaves Algonquin College, we still offer them post-graduation support to find their career of choice.”

And those are the people, from Algonquin College and elsewhere, who will forge the next wave of innovations.

Below: Ashoka Patel, along with Industry Engagement Specialist Alexandra Trudel.

Algonquin College Ashoka Patel and Alexandra Trudel

INDRO’S TAKE

 

This event is now in its third year – and GCXpo has truly become the showcase of Canadian and international companies in the Smart Mobility and related sectors. It’s an opportunity for everyone from big industry players through to small entrepreneurs and interested students and members of the public to learn about the products, services and agencies that are committed to helping shape the future in a positive way.

“As always, Area X.O and Invest Ottawa have done a tremendous job of hosting and planning this event,” says InDro Robotics CEO Philip Reece. “The shift from TCXpo to GCXpo really highlights the commitment of the Government of Canada to this future, and also illustrates how truly engaged regulators and funding agencies are to this growing sector. Of course, it’s always nice to show what InDro has been up to – but the real value here is the diversity of thought and innovation on display, all in one place and in one day. We look forward to 2025.”

See you next year!

InDro deploys drones, ground robots in Kelowna precision agriculture project

InDro deploys drones, ground robots in Kelowna precision agriculture project

Aug 1, 2024 | InDro News, Industry News, Photogrammetry, Scott Simmie

By Scott Simmie

There’s a buzz around Kelowna these days.

Well, actually, there are two kinds of buzz. The first is the occasional faint sound of a small but smart drone, carrying out flights every two weeks over two separate orchards. These orchards grow peaches, pears, cherries and more.

And the other buzz? Well, that’s the discussion this special two-year project – a collaboration between InDro Robotics and the City of Kelowna (enabled with funding from Agriculture and Agri-Food Canada’s Agriculture Clean Technology Program) – is generating among farmers in the region.

“Technology is always getting bigger and better,” says Riley Johnson, a manager at Byrnes Farms – one of the two locations where the project is being carried out. Johnson is an experienced farmer, and the land has been in the hands of his wife’s family for five generations. He knows the land and crops well, but is curious to see what additional data can be gathered.

“Anything in agriculture, the more information you get, you’re not going to be worse off. Especially for new farmers coming into the industry, any new kind of information can help out ten-fold – particularly if you’re on new land. Any information outside of the Old Farmer’s Almanac is always appreciated.”

What InDro is doing, to the best of our knowledge, is a type of precision agriculture that hasn’t been carried out before. It combines data acquisition from both drones and ground robots to ensure the most robust and reliable data possible.

This data is then used to assess overall vegetation health. Are there indications of pests in certain areas? Are any plants indicating low levels of chlorophyl? Does it look like that patch needs some pesticide – or maybe additional watering?

These are important questions for farmers whose livelihoods depend on maximizing the yield and health of their crops.

And this project? It’s all about finding the answers – and implementing solutions. Those solutions will include precision spraying of nutrients or other compounds in the precise location where they are required. The end result should be maximum yields with minimal – or no – areas of unhealthy crops.

Below: Healthy pears growing at Byrnes Farm. Photo courtesy Riley Johnson

Healthy pears in Kelowna. Photo courtesy Riley Johnson

AN INTRODUCTION

 

Before we get into all the details, it’s worth introducing you to Dr. Eric Saczuk (assuming you haven’t already met). He’s our Chief of Flight Operations – and comes with some serious chops.

Eric holds a PhD in Remote Sensing. He’s been assessing vegetation health (among many other things) using satellite data since the early days – long before drones came on the scene. But when drones did come on the scene, he quickly recognized their potential for the acquisition and interpretation of multiple kinds of data. He has flown missions all over the world on behalf of InDro, all involving complex data and analysis.

But that’s not all. He’s been an instructor at the British Columbia Institute of Technology since 2003 and has been the director of the institute’s RPAS Hub since 2016. He’s divided his time between BCIT and InDro since 2018 and is our go-to for highly complex operations. He’s also carried out multiple missions to acquire data for projects undertaken by Canada’s National Research Council – including this fascinating research on urban wind tunnels. There’s likely not a more qualified person in the country when it comes to drones and data.

Below: Dr. Eric Saczuk on an InDro mission. Image by Scott Simmie

SkyScout Ai Eric Saczuk

THE PROJECT

 

Okay. You’ve most likely heard of precision agriculture by now. When it comes to drones, most of us picture something like this: A drone with a multispectral camera flies over a field of wheat or some other crop. That multispectral camera captures spectrums of light both visible and invisible to the human eye. When that data is crunched, it provides a detailed picture of crop health (we’ll explore more of this shortly).

In collaboration with the City of Kelowna and local farmers, we’ve been flying a mission every two weeks over two separate fruit orchards. We use a drone with a special type of camera. It has five lenses. One of those lenses simply captures RGB (or simply, colour) images. But the other four have filters that are tuned to pick up light only within specific spectrums that can be collectively analyzed to indicate the health of vegetation.

“So in addition to the RGB camera, you’d have one camera capturing just red reflected light, one capturing just green reflected light using filters, and then the other two are what we call red edge and near-infrared,” says Dr. Saczuk.

Red edge is particularly useful in the early detection of disease or stress in plants – as it is highly reflected by healthy chlorophyl. But the real magic happens when you take the data captured in these different light wavelengths of light and run some calculations on them. That’s what gives you the bigger picture.

“Think of each of these images as a number. Capturing these multiple spectral bands allows you to combine them using complex equations in a type of calculator to give you various indicators of vegetation health,” he says.

That data can answer a lot of questions.

“Is it healthy? Is it not healthy? Is it being productive? Is there chlorophyll? If so, how active is it?” he says.

“These are the kinds of questions we can answer when we do what we call ‘multispectral band combinations.’ And it gives us a really clear picture that cannot be detected by the human eye.”

A CLOSER LOOK

 

We’re going to take a look at an image in a moment.

Before we get there, though, it’s worth exploring something Eric said earlier. He mentioned complex math. He’s right. The math happens at the individual pixel level between each of the input bands and there are millions of pixels per band. The most common calculation is used to produce a result called NDVI (not be be confused with NVIDIA, the producer of AI chipsets). The acronym stands for Normalized Difference Vegetation Index. And once the math is done, it gives you an accurate picture of vegetation health.

NDVI is calculated by using near infrared (NIR) and red bands (you’ll see the formula below).

The resulting pixel number in an NDVI image, will always be between -1 and +1. The higher the number, the better the health. If the number is low, it means there’s something worth looking at. The NDVI provides a detailed look at crop health and while it is regarded as the gold standard, there are also other calculations that can drill down to more specific indicators of vegetation health.

Below: Healthy vegetation absorbs most of the visible light that hits it, reflecting a large portion of the near-infrared spectrum. Unhealthy or sparse vegetation (right) reflects more visible light and less near-infrared light. When you do the math, it yields a lower NDVI number. (Public domain image by Robert Simmon.)

The second image is the equation used to calculate NDVI (which explains what those numbers are at the bottom of the first image).

NDVI
NDVI

FROM DATA TO DECISIONS

 

Using the equation above (as well as other formulas), Dr. Saczuk turns all of that data into something both meaningful and actionable. By looking at the data – and calculating not just NDVI but other indexes, images are generated that provide an at-a-glance look at crop health.

Traditionally, this has been a hugely time-consuming task involving multiple steps (and plenty of processing) on a laptop. Now, new tools are available that streamline the process. Dr. Saczuk is using a cloud-based solution specifically for precision agriculture.

“It really makes the whole process very efficient – because not only does it do the photogrammetry on the images, stitches them into these orthomosaics, but it also gives you the tools with which to analyse them. This would typically be a multi-step process, but this software makes it a one-stop shop, which is really nice.”

That’s without even getting into some of the AI capabilities of the software. It can, for example, count all the trees in a given orchard – and even give you the elevation of a specific tree.

Below: An NDVI image of one of the farms in the Kelowna project.

Solvi Kelowna NDVI

NOW WHAT?

 

At this phase of the project, InDro is gathering data by drone alone. But as it progresses, two more things will happen: We will introduce ground robots and precision spraying.

The plan is that a ground robot will initially be fitted with the same kind of multispectral sensor used by the drone. Autonomous missions will be plotted and the robot will capture a series of images from the ground as it drives through the orchard. That data will be crunched and compared with the results captured from the air.

“This is a way of doing ground-based validation of what we’re seeing from the air, from the aerial images of the drones,” says Dr. Saczuk.

Once that validation is complete and if problem areas are detected, the next phase would involve precision spraying – which could be carried out by an AGRAS agricultural drone – or even potentially by ground robot. Because all of the data is georeferenced, that means the fertilizer (or possibly pesticide or herbicide, depending on the issue) can be precisely applied to only the required locations. That, of course, is where the term Precision Agriculture comes from.

VICE-VERSA

 

This project is data-driven, with aerial and ground acquisition. But at the outset, shortly after our initial flight in April of 2024, farmer Riley Johnson noticed that a couple of trees weren’t doing well. It wasn’t clear what was causing this failure to thrive, but he didn’t want to take any chances that a potential disease might spread further in the orchard. So those trees were taken down.

In this case, because the issue was spotted early and the location was known, Dr. Saczuk is quite interested in doing some deep drilling into the data at that spot. In fact, that’s the very issue he has recently been exploring.

“So we’ve got that data, that information that’s saying, ‘Hey, these trees were actually not doing well.’ And then the next question is: Can we see anything in the multi-spectral images that would indicate that these trees are somehow spectrally or reflecting light differently than the ones that are healthy?”

This is something that is also of particular interest to Johnson. Will the data reflect what years of experience indicated was a problem to his naked eye?

“As the season progresses, it will be really interesting to see what InDro comes up with,” he says. “But I can definitely see the value of this for someone just getting into farming, or for farms up the hills with new plantings, new growth. This could be very useful.”

Below: Another image of a Kelowna orchard from this project, showing elevation

Solvi Kelowna Elevation

INDRO’S TAKE

 

We’ve been involved with precision agriculture projects in the past. In fact, we pioneered a “drone-in-a-box‘ solution, where we’ve shipped a drone to farmers. We talk them through the process of being a visual observer, then instruct them on how to power up the drone. InDro then carries out the flight remotely, using 4G or 5G – while in constant contact with the observer. When it’s done, the farmer puts the drone in the box and sends it back. InDro carries out the data analysis and quickly sends an easy-to-understand report indicating what areas require attention – and what kind of attention they require.

But this project is very different, and exciting for multiple reasons.

“The bi-weekly flights by drone will provide a huge amount of timely data, enabling us to detect any potential problems at an early stage,” says InDro Robotics Founder and CEO Philip Reece. “But by adding robots to validate from the ground, we’ll have a more robust dataset that can be used to truly pinpoint areas of concern and which may require precision spraying. We are going to learn a lot with this project – and believe our findings will be of great benefit to farmers down the road.”

A final note. When Dr. Saczuk isn’t carrying out these flights, they’re being flown by a new addition to the InDro team, Jon Chubb. He’s already had interest from other farmers in the Okanogan who are eager to maximize their own yields and have an early detection system for any trouble spots. If you’re in that neck of the woods and would like to arrange a demo, you can contact Jon here.

Sales and support: The InDro Experience

Sales and support: The InDro Experience

Jul 26, 2024 | InDro News, Industry News, Robotics, Scott Simmie

By Scott Simmie

 

We’ve all had them. Some unfamiliar number shows up on your phone, and the next thing you know someone is trying to pitch duct cleaning, a new cellular plan, or something else you likely don’t want or need.

You’ll never receive a call like that from us. For one thing, we don’t do duct cleaning (though we could probably build a robot capable of that). But there’s a bigger, more important reason. We cater – above all – to building a relationship with and satisfying the needs of the client. That’s both before we agree on a sale, and for long after the product is delivered.

While InDro is known for such ground-breaking stand-alone products as InDro Commander, the new InDro Cortex and InDro Controller, along with other platforms that enable researchers and R&D companies to build their own robots and drones with greater efficiency and simplicity, the bulk of our sales are custom products.

That means designing and building a robot or other device based on the specific needs and use-cases of the customer. Sometimes it’s a single, one-off design. But it could also be, as we recently reported, an entire fleet of custom robots for swarm research.

Regardless of the product or platform, the process nearly always begins with the first of many conversations with Luke Corbeth, our Head of R&D sales.

Below: Luke at a recent conference

Luke Corbeth

CORBY CAR CLEANERS

 

The story, or part of it, begins with a company called Corby Car Cleaners. “Corby” was Luke’s nickname in high school. An entrepreneur at heart, the prospect of working a traditional job didn’t appeal much. Corbeth wanted to learn about running his own business and was looking for the satisfaction that comes with building something from scratch. So he opened an on-demand car detailing business, where he’d show up at the client’s home and perform the service. How many people do you know that had the drive to start their own company in high school? (I can think of only one other; a friend who installed car stereos. I ran into him, decades later, at a CES show. His company was by then installing high-end systems – $100k+ – into cars owned by pro athletes, actors etc.)

“That was my way of building a basic business – doing sales and then actually executing the business,” he recalls.

With that – and high school – under his belt, Corbeth went to McGill University. Specifically, the prestigious Desautels Faculty of Management for a degree in Management. Corbeth had already shown a real knack for finance, which was part of the course. But he had the option of choosing specialisations. He was tremendously interested in technology – learning about AI, startups, the growing impact of other forms of tech – so he selected Digital Innovation as one of his tracks. But there was still another specialty he could select.

“I had something I was interested in (Digital Innovation), something I was good at (Finance) and something I felt I was missing,” he says. And that third piece of the puzzle?

“I didn’t understand the way operations are conducted. So I felt Operations Management was the missing piece; data science and understanding the optimal way to carry out operations. So that became the third piece of my arsenal.”

 

FROM CAR CLEANING TO WALL STREET

 

With his degree fresh in hand in 2019, Corbeth quickly landed two impressive jobs straight out of the gate. He did equity research at a hedge fund in New York, working to identify investment opportunities that the company referred to as having “material dislocation from fair value.” In other words, assets and stock that were undervalued. He also worked at a private real estate investment firm – which only had a single product to sell. He didn’t like that one much.

“When you have only one offering as a sales professional, it occasionally it feels like you’re trying to put a triangle into a circular hole – like you’re trying to force something upon someone.”

That wasn’t a fit for Corbeth. He was still drawn to technology; felt that was the future. Plus, something A McGill professor once said still resonated with him. It was along the lines of: ‘All the best investments in life, you need to be contrarian and right.’

“I was like, ‘Wow, that’s a very profound thought.’ Another way to think of that is: ‘You have to believe in a future that people don’t yet believe in, but will one day also believe in.’ And that’s what really attracted me to robotics,” he says.

“Sci-fi would suggest that it’s the future, but not everyone sees a future where robots are assistants to humans – carrying out useful and valuable tasks and doing the jobs we don’t want our kids to do. But I believe in that future, and I think people are going to want that future. And you know what? It’s becoming increasingly true.”

And then came the perfect fit: An opening for a sales professional at InDro Robotics in 2021.

“I was very excited at the prospect of joining the very field I was most interested in,” he says.

Below: Head of R&D Sales Luke Corbeth doing a public demo at the opening of Area X.O’s DARTT – the Drone and Advanced Robot Training and Testing facility 

 

 

THE INDRO EXPERIENCE

 

With this background, Corbeth had the perfect skill set – and passion – to take on sales with InDro Robotics. His keen interest in technology led him to quickly absorb everything possible when it came to sensors, compute capabilities, autonomy and more. But it was the chance to tailor something very specifically suited to the needs of a customer that truly appealed. He would never again be in a position of trying to put a triangle into a circular hole.

“What’s very unique about InDro Robotics is that because we take such a modular approach and we have so many partners and ways to bring solutions together, It feels like I always have the right shape to put in each hole – regardless of what shape it is.”

As mentioned, InDro most often builds completely custom robots for its clients. Corbeth is truly passionate about working with clients to fully understand their needs before even beginning to explore what options might be developed for them.

“The way I think about my job is this: People present a problem that they envision a solution for that requires uncrewed systems of some kind, whether that’s robots or drones. And I take it upon myself to thoroughly understand that problem and recommend all of the best available hardware and software at our disposal to solve that problem,” he says.

With rare exceptions, this isn’t just a simple phone call. Nor is it a process of simply ticking boxes for sensors, compute, platform etc. For Corbeth (and InDro), it’s the beginning of a relationship where together we explore every conceivable option to ensure that the client’s needs are met and their problem is solved. It generally starts with Corbeth sending a resource package to potential clients prior to any deeper conversation, so that they can fully understand InDro’s offerings, expertise, platforms, etc.

“The whole idea there is: Let’s identify the problem – and let’s identify the desired future. And since they’ve done their homework, ideally with the resources I’ve sent, then we can really dive into exactly what InDro Robotics can do specifically to get them there.”

This is a key part of the process.

“So the initial part of the conversation is always trying to understand the client’s desired future: What is it they’re actually trying to accomplish? And often times, just by talking it out with the client, I make discoveries about what they’re trying to do. They even make discoveries about what they’re trying to do. That’s always the first part: Thoroughly identifying the problem and what the ideal future should be.”

In some cases, for example, clients have come in looking for a wheeled platform, perhaps because they’ve seen a similar robot with wheels. But after further exploration of the use-case and terrain, they might together discover that a quadruped or tracked platform might be more suitable.

“If a client doesn’t know the existence of something, then it’s impossible for them to know that’s actually what they need,” he explains. “So part of my job is informing them of what is available, what is trending, what has been successful. It’s all about clarifying that problem and that vision for the future – and then seeing if we have something in the arsenal that can help get them there quickly.”

Below: Luke being interviewed at Area X.O’s DARTT

FROM PROBLEM TO SOLUTION

 

So then what happens?

Well, the second phase is seeing if there’s a fit. Can we provide what the client is seeking? Usually, of course, the answer is yes.

“With all that is available to us, can we offer something that meets their budget, meets their timeline, meets all of the project requirements so that we can help them achieve this future they’re seeking?”

This is something we really want to nail down.

“Sometimes in sales, companies will say: ‘Yes, my solution can solve every problem’ – and that’s not always the case. So if it makes sense to refer them to an adjacent providers outside our immediate circle, I’ll do that. But we’re in a fortunate position where we can solve a lot of problems – so that doesn’t happen very often.”

Once the client’s needs are fully understood, Corbeth works closely with them to drill down to the specifics: What type of LiDAR and other sensors best suit the application? How much compute power is needed? What platform and locomotion is best suited to the use-case? Is an autonomy stack required? The list, of course, goes on. And InDro has multiple options in every category to ensure the end product is the right one.

 

NEXT STEPS

 

We live, unfortunately, in a world where there’s a lot of hype – particularly when it comes to technology. There’s no shortage of vapourware, renders for products that don’t yet exist, and other techniques to draw clients into a sales funnel. At InDro, we take great pride in the fact our products are real and do exactly what we state.

“We’ve built custom products for everyone from small colleges and research teams right up to the largest technology companies in the world,” says Corbeth.

It’s one thing to say that; it’s quite another to prove it. And so Corbeth frequently arranges for an in-person or remote demonstration, where clients can control an existing robot or drone and take it for a test drive. They can experience the near-zero latency with remote ops, see the intuitiveness of the control system, and view all sensors, robot health (and much more) through the secure InDro Controller dashboard.

“We get them time on the sticks – ideally in person, but very often over Teams – and let them control a robot on our site. They can see how we plan missions, how we execute missions, and just how user-friendly and effective this technology is.”

That demo – controlling and seeing InDro products in action – generally seals the deal.

“Usually we move from there to quotes and service agreements and then, ultimately, a purchase order.”

Below: Luke engages with an attendee at the big IROS conference in Detroit in fall, 2023

FULFILLMENT AND SUPPORT

 

Even with the PO signed, the job isn’t done. Prior to starting the build, there’s generally a review call with the client along with engineering staff on the call. We want to ensure we have everything right, and understand every single facet of what the client is expecting.

“It’s a way of ensuring that what we end up delivering ultimately meets every expectation – because the worst thing you can do is send something out the door that doesn’t meet expectations. So we do that, and then we execute,” he says.

With the build complete, the product is shipped. Then there’s another call once it arrives. That ‘kickoff’ call points the client to the vast array of resources and continuously updated documentation InDro provides, as well as answering any initial questions the client might have. The whole concept here is to flatten the learning curve and ensure the client can get up and running with their robot or drone as quickly as possible. That support continues with any issues or questions that might arise after the client becomes familiar with their robot or drone or other device. At InDro, we are just as concerned with ensuring the client is satisfied and able to fully exploit their new product as we were with the original sale.

“We really value the client’s experience and the client’s feedback. In some ways, we create a feedback loop. And that feedback loop is what has enabled us to improve and evolve our products and our documentation at such a fast rate.”

 

KNOWLEDGE BASE

 

Luke Corbeth is frequently our lead person at robotics conferences and academic gatherings. He’s the guy PhD engineers will often engage with on InDro products and solutions. And the funny thing here? Luke’s comprehensive understanding of the technologies involved frequently lead people to assume he’s an engineer. In fact, that happened just this week at a University of Toronto event.

“That was like the penultimate compliment,” he says. “Despite having no formal education in engineering, I understand every part of our solution in enough detail that I can knowledgeably discuss hardware and solutions with some of the best professors in the world. Granted, I can’t build an autonomy algorithm. But I know what the robot needs to enable that.”

Of course, Luke would not have been able to reach that knowledge level without working closely with InDro’s talented engineering team at Area X.O. Whenever he’s had a question – they’ve had the answer. Many on our team have served as mentors for him.

Now, it’s one thing for us to say all this. But the real credibility comes with feedback from our clients. Luke received this note after the delivery of a custom robot build for, truly, one of the biggest companies in the world:

“Hey Luke – The robot is fantastic; the craftsmanship is superb; the power on the base is enabling; the intricate way in which the computer fits in the base housing is incredible; the compute box + mast feels “just right” (there’s no template for social robot design, but I feel like we got very close); all these things make me really confident that, with the right algorithms (my responsibility) we can safely and efficiently navigate through crowds.  It’s a really special robot that I can’t wait to put in the field.  Your team deserves a raise!”

(We’ll have to ask our CEO about that last bit.)

Below, our recent swarm robotics build for a US client

 

 

Robosense LiDAR Swarm

INDRO’S TAKE

 

InDro would not be thriving without satisfying our clients (many of whom are repeat customers, or are referred to us by existing ones). It is part of our very ethos to fully understand the problems they are trying to solve before we ever start discussing a solution. And it’s only then, through a very collaborative process with the client, that we can deliver a product that not only meets – but frequently exceeds – their expectations.

“Luke is a crucial and always enthusiastic part of the InDro Robotics team,” says Founder and CEO Philip Reece. “His understanding of the technology is phenomenal, and his drive to truly help clients achieve the future they envision seems to be hard-wired into him. Yes, meticulous builds are a key part of client satisfaction and InDro’s reputation. Luke plays an absolutely key role in ensuring that what we ultimately build and deliver is a match with their expectations.”

If you’re considering a robotics solution, contact Luke Corbeth here. He’ll be happy to arrange a test drive.

InDro completes design, build and delivery of robots for swarm research

InDro completes design, build and delivery of robots for swarm research

Jul 16, 2024 | InDro News, Industry News, Scott Simmie, Swarm Robotics

By Scott Simmie

You’ve likely seen swarm behaviour in nature – or at least video of it.

Flocks of starlings produce incredible patterns known as murmurations, undulating with split-second speed. Certain species of termites build massive and complex mounds, complete with sophisticated ventilation shafts to ensure air exchange and temperature regulation. Some types of fish, when attacked by predators, form tightly whirling balls as a defense mechanism. Bees build complex hives and have specific roles that all contribute to the collective. And ants, as you’re aware, can do a lot more than spoil picnics.

All of these, though very different, are examples of swarm behaviour. No single individual is in charge, yet these creatures work together to great synergic effect.

Below: A starling murmuration at Rigg by Walter Baxter, CC BY-SA 2.0 via Wikimedia Commons

A_starling_murmuration_at_Rigg_

SWARM ROBOTICS

 

It was actually through these observations in nature, particularly of insects, that the concept of swarm robotics first emerged.

“In a robot swarm, the collective behavior of the robots results from local interactions between the robots and between the robots and the environment in which they act… The research of swarm robotics is to study the physical body and the controlling behaviours of robots. It is inspired but not limited by the emergent behaviour observed in social insects, called swarm intelligence. Relatively simple individual rules can produce a large set of complex swarm behaviours. A key component is the communication between the members of the group that build a system of constant feedback. The swarm behaviour involves constant change of individuals in cooperation with others, as well as the behaviour of the whole group,” states this Wikipedia entry.

Much of the early research (and some of the more complex, current research) involves high numbers of very simple robotic devices. But as the field has developed, so too has the size and capabilities of the robots being used in swarm applications and research.

“The idea behind swarm robotics is the robots are able to communicate with each other and thus improve their decision-making and data acquisition in a given environment from a real world application standpoint,” explains Head of R&D Sales Luke Corbeth.

 

THE BOSTON EXAMPLE

 

One InDro client, Boston University, is using a very large fleet of small but smart robots called LIMO in swarm scenarios. One aspect of their research involves how autonomous vehicles interact with each other. Can the robots detect others merging and take appropriate action? How can autonomous vehicles detect and interact with robots that have been programmed to behave as if they’re human-driven vehicles?

Research like this is obviously more practical (and far less costly) to carry out in a lab rather than on city streets. It’s important work as we head toward the Smart Cities of the future, where eventually all vehicles will be autonomous – and much of the current infrastructure (traffic lights, stop signs) will no longer be necessary because all Connected Automated Vehicles will be part of a network.

“These vehicles become nodes in an Internet in which the vehicles talk to each other,” said Christos Cassandras, Distinguished Professor of Engineering, Head of the Division of Systems Engineering, and Professor of Electrical and Computer Engineering in an earlier interview with InDro.

“They exchange information and so, ideally cooperatively, they can improve metrics of congestion, of energy, of pollution, of comfort, of safety – perhaps safety being predominant.”

It’s fascinating work, and you can check out our story about it here.

But the ability of swarms to move and collect and share data collaboratively also opens up other use-case scenarios.

“If you are able to team your robots together, obviously you can cover a lot more area in a shorter period of time because the robots are essentially building a map together rather than being dependent on a single robot to build that map. One of the most obvious applications is search and rescue,” says Corbeth.

To illustrate, we borrow this example from research being carried out at Carnegie Mellon University:

INDRO’S CUSTOM SWARM

 

We recently built and shipped four identical custom robots for North Carolina State University’s Department of Mechanical and Aerospace Engineering. Corbeth was the conduit, putting together a package that suited their very specific needs. It began with selecting one of our 18 available platforms.

“They chose the Scout Mini, which is far and away our most cost-effective platform. And it’s unique in that it’s capable both indoors, like in their lab, but also for outdoor use,” says Corbeth.

That, of course, was just the start. Each robot was outfitted with the InDro Commander, which tucks a lot of power and flexibility within its IP54-rated enclosure. Commander houses the brains or the robot – which in this case is a very powerful piece of compute. Commander is completely customisable based on client requirements and contains ROS1 and ROS2 folders. (It also enables rapid integration and recognition of multiple sensors, and has the option of shipping with either or both of InDro’s autonomy stacks for outdoor or indoor use – think GPS-denied and SLAM. In this case, the client will be building their own autonomy stack, as that’s part of their research.)

And this client wanted Commander equipped with a powerhouse.

“They upgraded from a Jetson Xavier NX to the AGX Orin Developer Kit. That’s the best-in-class onboard compute you can add to a robot these days,” he adds.

That’s not hyperbole. The AGX contains a 2048-core NVIDIA Ampere architecture GPU with 64 Tensor Cores. Unfamiliar with Tensor Cores? They mean ultra fast AI processing.

“Tensor Cores enable mixed-precision computing, dynamically adapting calculations to accelerate throughput while preserving accuracy and providing enhanced security,” states the NVIDIA website. “The latest generation of Tensor Cores are faster than ever on a broad array of AI and high-performance computing (HPC) tasks. From 4X speedups in training trillion-parameter generative AI models to a 30X increase in inference performance, NVIDIA Tensor Cores accelerate all workloads…”

That AI computer is capable of – wait for it – 275 TOPS, or trillions of operations per second. (Yes, it’s kind of hard to get your head around that.)

 

SENSORS, SENSORS, SENSORS

 

Corbeth worked with the client to outfit each swarm robot with the sensors needed for the job. Starting with the basics, each robot contains two pinhole cameras (one front, one rear) so the operator can remotely see the robot’s eye view using our proprietary dashboard, InDro Controller. For depth perception, we added ZED X stereo cameras which – like human eyes – see the world in three dimensions. These are used for obstacle avoidance (in conjunction with LiDAR, which we’ll get to).

Connectivity is key with any robot. But when it comes to swarm robotics, it’s particularly important to have high-speed, low-latency communication not just with the controller, but between the robots themselves.

“Obviously doing swarm requires 5G connectivity,” says Corbeth. “So there’s a 5G modem in each robot as well as our Wi-Fi development module. In addition to communication between the robots and with InDro Controller, this also means they can program these robots without having to hard-wire into them. In fact, students or researchers could upload algorithms from pretty much any location – they don’t need to be on-site or on the same WiFi network, which has been the traditional route.”

Each robot features GPS and IMU modules, plus a Robosense Helios RS-5515 32-beam LiDAR module. These sense the environment in three dimensions by rapidly scattering and receiving the reflections from eye-safe laser beams. It allows the robot to safely navigate and map in completely unfamiliar and GPS-denied locations, and even carry out precision scans. We recently featured Robosense in this post, detailing how the quality is absolutely on par with the biggest names in the industry. (Selecting Robosense for this project saved the client close to $80,000 without losing any capabilities.)

Outstanding in their field: A look at the InDro-built swarm fleet just prior to shipping to the client

Robot Swarm

INDRO’S TAKE

 

It was a fascinating project to build a small swarm from the ground up for the specific needs of this client. We look forward to checking in with North Carolina State University once the research is fully underway – and will report back to you.

“There’s no doubt that swarm robotics is an important tool, not only in R&D but increasingly in real-world applications,” says InDro Robotics Founder and CEO Philip Reece. “Whether it’s search and rescue, mapping difficult environments at scale, or developing algorithms that will enable Connected Automated Vehicles in the Smart Cities of the future, swarms are synergic tools that produce outcomes far greater than the sum of their parts – and that do so with greater speed and efficiency.”

Interested in exploring options for swarm robotics? Contact Luke Corbeth here.