Jake Dyson
Jake Dyson is Dyson’s Chief Engineer, focused on core innovation, new product development, software connectivity and future technology.
Dyson is making big strides in the world of robot vacuums, and its latest robovac — the Dyson Spot+Scrub Ai — uses a camera combined with artificial intelligence to tackle tough stains that other robot vacuums tend to miss, and get your floors as clean as possible. But why did Dyson choose to tackle that particular problem, and what does the future hold when it comes to household robots?
I visited Dyson’s UK Innovation Campus in Wiltshire, where many of the company’s advanced engineering teams work on new products and technologies, using rapid prototyping to develop and test ideas. The campus is also the home of the Dyson Institute, where undergraduate students from around the world come to learn, and work on real-life projects.
There, I sat down with Jake Dyson, the company’s Chief Engineer, to learn more about his own experience, and Dyson’s approach to AI and robotics.
Despite being the son of founder James Dyson, Jake hasn’t always worked for the company. After a brief spell at Dyson at the age of 22, he left to pursue an independent career in industrial design. He built his own workshop and began to specialize in lighting, separately from the family business, before returning, bringing that experience with him. I asked him how that early work translated into his current endeavors.
“It comes down to identifying problems and solving them,” he explained. “When LEDs first entered the market, I realized people weren’t cooling them properly. The promise of LEDs is that they should last a lifetime, but in reality they were being treated like disposable lightbulbs. I visited Osram in Asia, and they explained that if you keep the diode temperature below about 50C, you can maintain brightness, color quality, and lifespan. That became my goal.”
“I looked at how satellites manage heat. In space, temperatures swing from extremely hot to extremely cold, so they need precise thermal control. I applied similar thinking by designing systems that passively dissipate heat. For example, the heat moves away from the chip and is cooled by airflow, maintaining a stable temperature even at high power.
“That process, spotting a problem and solving it, is what drives everything.”
Stairs and arms
Dyson’s latest robot vacuum has been designed to tackle the specific problem of tricky stains on hard floors, which other wet-and-dry cleaners fail to tackle. The Dyson Spot+Scrub Ai uses a high-definition camera and an LLM that includes over 190 different household objects and stains.
Spotting a problem and solving it is what drives everything
Jake Dyson
I asked Jake why Dyson had chosen to tackle such a (literally) ground-level problem when other companies are debuting robot vacuums that can climb stairs and lift objects with mechanical arms. He explained that Dyson has been tackling those more advanced problems for about 10 years already, but the solutions aren’t yet genuinely useful and reliable.
Having seen some other companies’ ambitious robots, I can see what he means. The Roborock Saros Z70, for example, has a pincer arm that can lift lightweight objects out of the way, but in our tests it failed to identify and move them independently, instead relying on you to control the pincer remotely. It also has a lower success rate on carpet due to what Roborock calls a “hardware limitation”.
Stairs are also a major challenge. My colleague Ruth Hamilton saw two stair-climbing robovacs in action at last year’s IFA tech show, but explained that the legs/treads used to navigate stairs aren’t actually attached to the robots themselves (they are more like a cradle that holds the bot), which means they can’t clean the stairs as they go. Only one robot managed to tackle the first step with confidence as well. According to Ruth, the other “approached this initial challenge at the speed of a geriatric turtle”.
They’re interesting concepts, but neither looked ready for the mainstream — and as Jake explains, they’re attempting to solve a very difficult problem.
“Every staircase is different height, spacing, materials and then you add in pets, children, and people moving around. It becomes a very complex and potentially unsafe problem,” he said. “Something going up and down stairs autonomously needs to be extremely reliable. It’s actually more complex than autonomous driving in some respects.”
“So while it’s an interesting challenge, and being able to clean an entire home, including all floors, with one machine would be ideal, it has to meet a very high bar for safety and usefulness. Until it does, we focus on delivering products that work reliably in real homes today.”
Safer decision-making
Dyson has never been shy about dropping products that don’t work out (such as the CR01 Contrarotator washing machine and the Dyson car), but its work on cordless vacuums continues apace. We recently reviewed the super-compact Dyson Pencilvac Fluffycones, and just a few weeks ago the company debuted its first self-emptying cordless vacuum. I asked Jake whether he thinks robots will eventually handle all your cleaning tasks, or whether there will always be a place for stick vacuums.
“No, I don’t see that happening, at least not completely,” he said. “Right now, robot vacuums are very good at regular maintenance, keeping floors tidy day-to-day. But people still want a to clean with a cordless vacuum when they do a deeper clean, as well as being able to clean surfaces other than the floor.”
In the future robots will learn from each other via the cloud
Jake Dyson
However, he added that the world of robotics is advancing incredibly quickly, especially when it comes to AI.
“Previously, robots could see and navigate, but they struggled when they encountered something unfamiliar. Now, with reasoning, they can make safer, more informed decisions.
“We’re also seeing rapid development globally, the US is leading in AI and ‘brains’, and China is producing robots at scale and more affordably.
“In the future robots will learn from each other via the cloud,; one robot’s experience will instantly improve others, and one robot will be able to repair a fault on another robot. That will massively accelerate development.
“However, regulation and safety will slow adoption. These technologies may be ready soon, but it could take around 10 years before they’re widely allowed in homes. Elon Musk said he thinks humanoid robots will be in many homes in three years, and I agree with him. Though they use up a lot of energy to walk for example, so a robot vacuum cleaner is much more energy efficient than a humanoid [robot] using a vacuum cleaner.
“So yes, robots will become more capable, but I think traditional tools will still exist alongside them.”
Although you might like the idea of handing over all your household chores to a robot, it seems cordless and handheld vacuums will be around for a while yet — and you’ll still need to climb the stairs and pick up socks yourself for now.
Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds.
https://cdn.mos.cms.futurecdn.net/5p5oFdMM9oRg94N56vVHKU-1920-80.jpg
Source link
catherine.ellis@futurenet.com (Cat Ellis)
