Picture a humanoid robot, and you probably imagine something sleek, vaguely threatening, or at least a little cold. Maybe it’s built for a factory floor, towering and intimidating, or designed to look eerily human in a way that triggers that uncanny valley feeling. Either way, it’s not exactly something you’d want hanging around your living room.
That’s what makes Sprout so different. This portable humanoid from Fauna Robotics just launched out of stealth mode, and it’s taking a completely opposite approach to robot design. Instead of trying to look impressively human or industrial, Sprout leans into something that feels refreshingly approachable and, dare I say it, genuinely charming.
Standing just 3.5 feet tall and weighing about 50 pounds, Sprout is compact and lightweight in ways that most humanoid robots simply aren’t. But what really sets it apart are those antenna-like eyebrows perched on its wide, rectangular head. They move up and down like little windshield wipers, giving this robot an expressive quality that feels more Pixar character than sterile machine.
The eyebrows work alongside a 360-degree LED facial display that animates with different light patterns and colors, plus body language that includes walking, kneeling, crawling, and sitting. Together, these features create a communication style that doesn’t rely on mimicking human faces or voices alone. Instead, Sprout uses a whole vocabulary of movement and light to express what it’s doing or feeling, which somehow makes it feel less like a failed attempt at humanity and more like its own friendly creature.
The design philosophy here clearly draws inspiration from beloved fictional robots like Baymax from Big Hero 6 or Rosie from The Jetsons, characters designed to feel helpful rather than threatening. Fauna Robotics wrapped the whole thing in a soft, padded exterior that’s safe to touch, and the company emphasizes that Sprout is built to operate in shared human spaces, around adults, children, and even pets.
This isn’t just a cute toy, though. The Creator Edition that’s shipping now is aimed at developers, researchers, and institutions that want to experiment with embodied AI in real-world settings. Sprout comes with some serious tech under that friendly exterior, including an NVIDIA Jetson AGX Orin processor with 64GB, stereoscopic vision, four time-of-flight sensors, a directional microphone array, and dual speakers.
Early customers are already putting Sprout to work. Disney, Boston Dynamics, UC San Diego, and NYU are all testing applications across retail, entertainment, home services, and research. The robot can navigate both indoor and outdoor environments without needing restricted zones, and its battery runs for about 3 to 3.5 hours before needing a swap. The price tag sits at $50,000 for the Creator Edition, which positions it as a serious development platform rather than a consumer product ready for mass adoption. But that’s kind of the point. Fauna Robotics is building the foundation for what humanoid robots could become once they leave the factory and start mingling with regular people in everyday spaces.
What strikes me most about Sprout is how it sidesteps the whole debate about whether robots should look human. By embracing a more abstract, expressive design, it avoids that creepy almost-human trap while still feeling relatable and engaging. Those eyebrows, as simple as they are, do more emotional heavy lifting than a thousand attempts at realistic facial expressions.
The broader question, of course, is whether we’re ready for robots like this in our lives. But maybe that’s the wrong question. Maybe the better question is whether robots are ready for us, designed in ways that make interaction feel natural rather than forced or unsettling. Sprout suggests that the path forward might not be about making robots that look like people, but rather creating robots that feel like they belong in the spaces where people actually live, work, and play.
With its soft exterior, expressive features, and human-scale design, Sprout represents a different vision of what personal robotics could look like. Whether it succeeds in changing minds about humanoid robots remains to be seen, but those articulated eyebrows are certainly making a compelling argument.
Picture this: four robotic arms working in perfect harmony, tracing circular patterns like some kind of futuristic dance performance. But instead of creating art, they’re printing the walls of an actual farm. Welcome to Itaca, a project that just wrapped up its construction in the hills of Northern Italy, and it’s changing how we think about building homes.
WASP, the Italian company behind this audacious venture, just finished printing the walls of what they’re calling the first certified 3D-printed construction in Italy. Located in their Shamballa open-air laboratory, Itaca isn’t just a quirky experiment. It’s a fully functional, self-sufficient farm designed to house a family of four while producing its own food and energy.
The whole concept sounds like something from a sci-fi novel, but the execution is surprisingly grounded in ancient wisdom. The farm’s design takes inspiration from mandala geometry, with four robotic arms positioned at the vertices of a hexagonal structure. These machines use a lime-based printing material that allows the facades to regulate their temperature naturally, breathing like a living organism. No air conditioning required.
What makes Itaca genuinely fascinating is how it challenges our assumptions about both technology and sustainability. The walls aren’t just printed and left hollow. They’re packed with rice husks sourced from agricultural waste, creating natural insulation that keeps the interior comfortable year-round. The radiant heating systems and electrical installations are embedded directly during the printing process, which means less construction time and fewer workers needed on site.
But WASP didn’t stop at the structure itself. They’ve integrated 3D-printed vertical hydroponic systems that ensure fresh vegetables all year round using minimal water. The entire setup operates on a circular micro-economy model, where waste from one system becomes fuel for another. It’s the kind of closed-loop thinking that environmentalists have been advocating for decades, finally made tangible through advanced manufacturing.
Massimo Moretti, WASP’s founder, first unveiled Itaca at Italian Tech Week in Turin as part of the company’s broader vision to democratize sustainable housing. The real genius here is accessibility. The Crane WASP system used to build Itaca is designed to operate even in remote areas, making it possible to replicate this model worldwide. You don’t need massive infrastructure or armies of specialized construction workers. Just the machine, locally sourced materials, and the digital blueprints.
This approach to construction could be transformative for communities dealing with housing shortages or natural disasters. Traditional building methods require extensive supply chains, skilled labor, and months of work. With 3D printing, the timeline compresses dramatically, and the environmental footprint shrinks considerably. Using local materials means less transportation, fewer emissions, and buildings that are naturally suited to their climate. The ventilation system deserves special attention too. It’s designed to allow air to flow through the interior spaces continuously, transforming Itaca into what WASP calls a living house. This isn’t just clever branding. The structure literally responds to environmental conditions, adjusting naturally without mechanical systems that consume energy and break down over time.
What’s striking about Itaca is how it sidesteps the typical debate between high-tech solutions and traditional wisdom. It’s both. The robotic arms and digital design tools represent cutting-edge technology, while the materials and principles draw from centuries of vernacular architecture. Rice husks and lime have been used in construction for millennia because they work. WASP 3D Build, the startup within WASP dedicated to printed construction, executed the project using technology that’s already proven and available. This isn’t a prototype languishing in a research lab. It’s a real building that people will actually live in and farm around. That’s the difference between innovation theater and genuine progress.
The implications extend beyond individual homes. If this model scales, it could reshape how we approach rural development, affordable housing, and disaster relief. Instead of shipping prefabricated structures across continents, communities could print buildings on demand using materials from their own backyards. The rapid transmission of information through digital files means a successful design in Italy could be adapted and printed in Peru or Indonesia within weeks. Itaca represents something rare in architecture: a project that’s simultaneously visionary and practical, high-tech and humble. It proves that sustainability doesn’t require sacrifice or compromise. Sometimes it just requires thinking differently about the tools we have and the wisdom we’ve inherited.
Imagine a robotic hand that not only mimics human dexterity but completely reimagines what a hand can do. Researchers at École Polytechnique Fédérale de Lausanne (EPFL) have developed something that looks like it crawled straight out of a sci-fi fever dream: a modular robotic hand that can detach from its arm, scuttle across surfaces spider-style, and grab multiple objects at once.
The human hand has long been considered the gold standard for dexterity. But here’s the thing about trying to replicate perfection: you often inherit its limitations, too. Our hands are fundamentally asymmetrical. We have one opposable thumb per hand, which means we’re constantly repositioning our wrists and contorting our bodies to reach awkwardly placed objects or grasp items from different angles. Try reaching behind your hand while keeping a firm grip on something, and you’ll quickly understand the problem.
Designer: École Polytechnique Fédérale de Lausanne’s (EPFL) school of engineering
The team at EPFL, led by Aude Billard from the Learning Algorithms and Systems Laboratory, decided to throw the rulebook out the window. Instead of copying human anatomy, they created something better: a symmetrical hand that features up to six identical fingers, each tipped with silicone for grip. The genius lies in the design, where any combination of fingers can form opposing pairs for pinching and grasping. No single designated thumb here.
But wait, it gets wilder. The hand is completely reversible, meaning the palm and back are interchangeable. Flip it over, and it works just as effectively from either side. This eliminates the need for awkward repositioning and opens up grasping possibilities that humans simply can’t achieve. The device can perform 33 different types of human grasping motions, and thanks to its modular design, it can hold multiple objects simultaneously with fewer fingers than we’d need.
The most mind-bending feature? This hand can literally walk away from its job. Using a magnetic attachment and motor-driven bolt system, it detaches from its robotic arm and crawls independently to retrieve objects beyond the arm’s reach. Picture a warehouse robot that needs to grab something just out of range. Instead of the entire system repositioning, the hand simply walks over, grabs what it needs, and returns like a loyal (if slightly creepy) pet.
The practical applications are staggering. In industrial settings, this kind of “loco-manipulation” (locomotion plus manipulation) could revolutionize how robots interact with their environments. Service robots could navigate complex spaces and handle multiple tasks without constant human intervention. In exploratory robotics, think Mars rovers or deep-sea vehicles, a detachable hand could investigate tight spaces or retrieve samples from areas the main body can’t access.
The research team’s work, published in Nature, demonstrates that symmetrical design provides measurably better performance, with 5 to 10 percent improvements in crawling distance compared to traditional asymmetric configurations. The hand’s 160mm diameter palm houses motors that mimic the natural forward movement of human finger joints, but without being constrained by human limitations.
What makes this project so compelling isn’t just the technical achievement. It’s the philosophical shift it represents. For years, robotics has been obsessed with replicating human form and function. But by questioning whether human design is actually optimal for all tasks, the EPFL team has created something that surpasses our biological blueprint. It’s a reminder that innovation often requires abandoning our assumptions about how things should work.
This robotic hand represents more than just another engineering marvel. It’s a glimpse into a future where machines aren’t limited by human constraints, where form follows function in unexpected ways, and where a hand doesn’t need to stay attached to be incredibly handy. Whether it’s retrieving your dropped phone from under the couch or assembling complex machinery in factories, this crawling, grasping, reversible wonder proves that sometimes the best way forward is to let go of convention entirely.
There’s something quietly revolutionary happening in the world of workplace maintenance, and it comes in a surprisingly sleek package. Meet Pulito, a cleaning system designed by Yilmaz Salman that’s challenging everything we thought we knew about keeping shared spaces spotless.
Most cleaning robots feel like expensive toys that promise the moon and deliver, well, a slightly cleaner floor. Pulito takes a completely different approach. Instead of being just another gadget you buy and forget about, it’s designed as a subscription-based service that actually makes sense for how modern workplaces function. Think of it less as a product and more as a cleaning partner that shows up ready to work.
Designer: Yilmaz Salman
What makes Pulito different is its three-pronged strategy for tackling workplace hygiene. The main unit houses a continuous air filtration system that quietly works away at improving indoor air quality while everything else happens around it. This isn’t just about appearances. We spend so much time indoors now, and air quality has become one of those invisible factors that affects how we feel and work without us even realizing it.
Then there’s the autonomous floor cleaning component, a detachable unit that handles the vacuuming and wiping without anyone needing to babysit it. It’s the kind of set-it-and-forget-it functionality that actually lives up to the promise. The robot navigates work areas independently, freeing up cleaning staff to focus on tasks that genuinely need a human touch.
And that’s where the third element comes in. Pulito includes an integrated storage drawer filled with specialized window cleaning tools designed for staff to use. Rather than trying to automate absolutely everything (because let’s be real, robot window washers still have a ways to go), it embraces a hybrid model where technology and human expertise work together. It’s a refreshingly honest approach to design that acknowledges the limitations of automation while maximizing its strengths.
The business model behind Pulito is just as thoughtful as the design itself. The rental service approach taps into the growing circular economy movement, where ownership matters less than access and sustainability. Recent projections suggest the service robot sector could hit $175 billion by 2030, and rental models are proving to increase operational convenience by 83% and sustainability by 76%. Those aren’t just impressive numbers. They represent a fundamental shift in how businesses think about equipment and resources.
For facility managers and business owners, the subscription model solves one of the biggest headaches with commercial cleaning equipment: the massive upfront cost and the inevitable maintenance nightmares. With Pulito, you’re essentially renting a service that includes the hardware, updates, and support. When something breaks or needs upgrading, it’s not your problem to solve. That’s a game changer for smaller businesses or startups that need professional-grade cleaning solutions without the capital investment.
The portability factor deserves attention too. Pulito’s main body features an ergonomic strap system that lets cleaning personnel carry it like a high-tech backpack between different zones. Look at those product shots of someone wearing it while navigating between buildings. It’s almost futuristic, transforming cleaning staff into something that feels more like tech-equipped professionals than traditional janitorial workers. There’s dignity in that design choice.
Aesthetically, Pulito doesn’t look like your typical cleaning equipment. The textured grey finish with those lime green accents feels contemporary without trying too hard. The perforated details on the air filtration unit give it an industrial-chic vibe that wouldn’t look out of place in a design-forward coworking space or a tech startup’s headquarters. It’s the kind of object you wouldn’t feel embarrassed to have sitting in your office lobby.
What Salman has created with Pulito is bigger than just another cleaning robot. It’s a complete rethinking of workplace hygiene infrastructure for the modern era. By combining autonomous technology, human collaboration, accessible pricing through subscriptions, and genuinely thoughtful industrial design, Pulito represents where facility management might actually be headed. Not a future where robots do everything, but one where smart design makes both human workers and automated systems more effective together.
Lego unveiled its Smart Play system at CES 2026 earlier this month, with a selection of sets designed for the engaging feature. Now, the toy company has announced five new compatible sets — all Stars Wars themed — available now for pre-order. Anthony Daniels, the original C-3PO, shared the news during the Nuremberg Toy Fair.
The Smart Play system, Lego's newest venture, involves a Smart Brick, Smart Tags and Smart Minifigures. Each Smart Brick has proximity sensors, an accelerometer, a speaker and more. The Smart Tags and Smart Minifigures relay what's happening to the Brick. For example, if you whoosh a spaceship through the air, the Smart Brick should make a sound that imitates that. Vader, of course, also makes his deep breathing sound. Plus, it requires no screens or apps, so the fun remains in its true, tactical form.
The five new Smart Play sets span the Star Wars universe:
These sets join three initially announced Star Wars Smart Play ones: Darth Vader's TIE Fighter ($70), Luke's Red Five X-Wing ($90) and Throne Room Duel & A-Wing ($150). However, these three are "all-in-one" sets, meaning they come with the Smart Bricks. The newly announced options don't come with a Smart Brick, requiring an extra purchase, but will have the Smart Tags and Smart Minifigures that will know what to do.
All of the Smart Play Star Wars sets are available to pre-order as of today. They should be available starting March 1.
This article originally appeared on Engadget at https://www.engadget.com/lego-has-a-new-round-of-star-wars-sets-that-work-with-the-smart-brick-131210482.html?src=rss
Elon Musk just took the stage at the World Economic Forum in Davos, Switzerland and announced that Tesla's Optimus humanoid robot will be sold to the public by the end of next year. Musk is the master of unrealistic timetables, but this may be the nuttiest one yet. These are humanoid robots that are supposed to be able to do just about any task a human can do.
Musk, as usual, gave himself an out if the robots don't start rolling off the assembly line in 2027, saying that they'll only be released when Tesla is "confident that it’s very high reliability, very high safety and the range of functionality is also very high."
He stated that the robots have already begun doing simple tasks in the Tesla factory, but there's no proof of this other than his word. In the real world, Optimus robots have continuously failed to live up to the marketing hype.
If there was any question that Optimus uses teleop for their robots. Here one clearly has a guy take the headset off and it falls over.
There have been plenty of reports suggesting that previous demos of the robots in action were actually smoke and mirrors, as they were being remotely piloted by human operators.
Tesla's stock jumped over three percent upon this announcement because company investors live in a world of magical rainbows, unicorns and robots mixing drinks at home in the year 2027. Musk also recently stated that the robots would be ready for commercial deployment in 2026. That's this year. It's worth noting that the program head for the project, Milan Kovac, recently left the company.
Again, these are autonomous robots that are supposed to be able to perform complex tasks across a wide variety of categories. That'll likely happen someday, but not by 2027. I'm just gonna go ahead and throw Musk's timeline in with "two years to AGI" and "five years until the singularity."
On a related note, the Tesla CEO also said that the long-awaited Cybercab will enter production in April, with a goal of two million vehicles manufactured each year. This isn't quite as far-fetched as the Optimus promise, but that two million number seems highly suspect. Just how many consumers does he think want a car without a steering wheel that only holds two people?
This article originally appeared on Engadget at https://www.engadget.com/big-tech/elon-musk-just-told-davos-that-tesla-will-sell-humanoid-robots-next-year-really-he-swears-192515568.html?src=rss
Walking machines are hard. Really hard. Which is why most LEGO motorized builds stick to wheels or treads, and the ones that do attempt legs usually end up with something that shuffles more than it strides. But every so often someone figures out the mechanical magic trick that makes it work, and this six-legged walker currently on LEGO Ideas is one of those builds that actually delivers on the promise. The creator has managed to build something that moves with genuine fluidity, the kind where you can see the weight transfer from leg to leg.
The secret is in the gearing system. Rather than trying to program each leg’s movement independently, the build uses variable-speed gears that automatically adjust leg velocity based on where it is in the stride cycle. Slow and deliberate when the foot is planted, quick when it swings through the air. Combined with a vertical stabilization mechanism and shock-absorbing feet, you get something that can handle real terrain rather than just demonstration videos on smooth surfaces. It’s styled as a space exploration rover complete with a crew cabin and solar panels, leaning into that AT-AT aesthetic without directly copying it.
Designer: Alexis_MOCs_FR
Here’s the thing about making LEGO walk. You can throw servos at the problem and program every joint independently, which is how Boston Dynamics does it and why their robots cost more than a house. Or you can do what Theo Jansen did with his Strandbeest sculptures and let the mechanism itself figure out the gait. Jansen’s beach creatures run on wind power and pure geometry, converting constant rotation into this weirdly organic walking motion that makes you forget you’re watching PVC pipe and zip ties. That’s the approach Alexis_MOCs_FR took here, using two L motors and a gear train that does all the thinking mechanically. No Arduino, no sensor feedback loops, just smart engineering that exploits the physics of rotating linkages.
The look is peak 1970s futurism. White body panels, black structural framework, blue solar arrays, elevated cockpit with room for two astronaut minifigs. There’s a satellite dish up top because of course there is. The whole thing sits maybe 12 to 16 inches tall based on minifig scale, and all that gearing is completely visible. Some builds try to hide the mechanism under cosmetic panels, but here the exposed gear trains are the entire point. Watching the motion transfer from motors down through the variable-speed system and into the legs is genuinely mesmerizing, like those transparent mechanical watch movements that cost absurd money because people will pay to see the machinery work.
The vertical stabilization bit is where you can tell someone really understood the assignment. When your upper leg is swinging through a 60 or 70 degree arc, keeping the foot flat on the ground becomes this annoying trigonometry problem. Most people either accept some wobble or add complexity with extra actuators. This build has a sliding element in the lower leg that compensates for the angle automatically. Upper leg tilts, slider adjusts, foot stays vertical. It’s passive, it’s reliable, and it’s the kind of solution that only works because someone actually prototyped this thing instead of just CAD modeling it and calling it a day.
High-stepping gaits hit hard. You’re lifting legs way off the ground and slamming them back down at whatever speed your motors can manage. Without damping, every impact rattles through the structure and either knocks gears out of alignment or turns the whole thing into a vibrating mess. Custom shock absorbers at each foot solve this, which is why the creator can apparently run it over rumpled blankets and piles of Kapla blocks without it face-planting. The build is allegedly both lightweight and robust, which sounds like marketing speak until you consider that you need enough mass for stability but not so much that momentum tears the gear teeth apart during direction changes.
The project is currently in its very early stages, with 424 more days to gather votes and hit the next milestone. If it gets to the coveted 10,000 mark, LEGO actually reviews it for production. The Technic lineup has been pretty safe lately, lots of supercars and construction equipment but not much that pushes mechanical boundaries. This thing demonstrates actual engineering innovation, the kind where someone solved hard problems with clever solutions instead of just adding more motors. If you want to see it become a real set, go cast your vote on the LEGO Ideas website!
Apple and Google have confirmed that Gemini’s models power the new version of Siri and other generative AI features. CNBC broke the news, but Apple and Google soon followed up with a lengthy joint statement. Here’s part of it: “Apple determined that Google’s Al technology provides the most capable foundation for Apple Foundation Models… Apple Intelligence will continue to run on Apple devices and Private Cloud Compute, while maintaining Apple’s industry-leading privacy standards.”
In June, it was reported that Apple was considering partnerships with OpenAI and Anthropic for Siri (the voice assistant can currently tap ChatGPT for certain queries as part of Apple Intelligence). Two months later, Google emerged as a contender. Another report suggested Apple might build the new Siri using a custom version of Gemini — and that it would pay Google around $1 billion a year for the privilege. However, no official deal numbers were shared.
It’s also notable that current iPhones have direct access to OpenAI’s ChatGPT. But how long for?
Netflix’s hit show Adolescence received four awards, including best limited or anthology series. It also won best actor (Stephen Graham), supporting actor (Owen Cooper) and supporting actress (Erin Doherty) in a miniseries or television film.
KPop Demon Hunters — which my nieces refuse to stop talking about — won best animated feature and best original song. “I just want to say this award goes to people who have had doors closed on them, and I can confidently say rejection is redirection. So never give up.”
It’s not all good news. Netflix also won best performance in stand-up comedy on television for Ricky Gervais: Mortality. Apple and HBO Max each won three, and Hulu got one award on the night.
The agency is targeting a February launch date for Artemis 2.
A few years ago, NASA announced it was pushing the Artemis 2 mission back to April 2026. The agency now says it could launch as early as February. NASA is finalizing preparations for the mission and will soon roll out the Space Launch System (SLS) rocket and the Orion spacecraft to the launch pad at the Kennedy Space Center in Florida.
Artemis 2 is the first crewed mission to the moon since the Apollo program’s final flight in 1972. The 10-day mission will have four astronauts, who’ll test whether Orion’s critical life-support systems can sustain human passengers on future longer-duration missions. They will first orbit the Earth twice before making their way 4,700 miles beyond the far side of the moon.
Pre-orders for the first three Lego-Pokémon kits are open now. One of the debut pocket monsters is, of course, Pikachu. You can build the 2,050-piece kit to show Pikachu either at rest or leaping out of an open Poké Ball into battle. It costs $200.
There’s also a 587-piece model of Eevee, for $60. On the bigger side is a set featuring a trio of Pokémon: Venusaur, Charizard and Blastoise. This kit has 6,838 pieces and can show the group together in battle formation or separately in their own mini environments. It retails for $650 and is a bit much.
Agibot entered the U.S. spotlight at CES 2026 as a company that has been busy actually building and shipping robots instead of just talking about what might be possible someday. Founded in 2023 with the ambition of creating robots that can live and learn alongside people, it has already moved 5,000 humanoid units into real deployments worldwide. That number matters because it puts AGIBOT past the prototype stage, where many humanoid projects still sit, and into a space where robots are expected to be reliable, repeatable, and ready for everyday use.
Instead of centering everything on one showpiece machine, AGIBOT has built out a broad portfolio that stretches across very different environments. At CES 2026, the company showed full-sized humanoids for public and customer-facing spaces, compact expressive robots for entertainment and research, industrial units aimed at factories and logistics centers, quadrupeds for inspection in complex terrain, and a dexterous robotic hand system. Each product has its own job, but they all share a simple expectation. Robots should be able to move through the world, communicate with people, and carry out useful work without constant human babysitting or elaborate staging.
Designer: Agibot
You really feel that philosophy when you stop reading spec sheets and just stand in front of one of the robots. On the CES show floor, my colleague in a blue sweater walked up to an AGIBOT A2 and greeted it from directly in front. The robot answered with an easy “hello,” then followed up with a friendly compliment that referred to her as “the lady in blue.” The recognition landed instantly with no visible lag, no frozen expression, and no glitchy audio. The exchange felt less like triggering a scripted demo and more like stepping into a light, everyday interaction with a staff member who just happens to be a humanoid robot.
The A2’s digital face helped make that moment feel approachable rather than uncanny. Instead of a fixed set of cartoon features, the display shifted through different visual modes as the interaction unfolded. At times, it showed a simple, stylized face that made it clear where its attention was focused. At other moments, it flipped into a flowing heart animation or playful emoji-like graphics that matched the energy of the show floor. Those changes acted as live signals that the robot was listening, processing, or responding, and they gave the encounter a kind of emotional rhythm that pulled people in instead of pushing them away.
A second interaction underlined how aware the robot could be of what people were doing around it. While I stood in front of the A2 snapping photos, the robot clocked what I was doing and casually acknowledged that I was taking pictures. It did not sit there waiting for a wake word or a preset gesture. Instead, it folded that small piece of context into the way it responded, treating the camera as part of the scene rather than a distraction. In the middle of a crowded, noisy hall, that ability to notice and adapt in real time made the robot feel present and attentive rather than mechanical.
What makes these scenes interesting is not simply that a robot can spot a blue sweater or a raised smartphone. It is that the whole exchange runs at a human pace. There are no long pauses while the system silently catches up, no handlers stepping in to reset things, and no sense that the robot is about to break character. The conversation and the gestures move forward with the timing you expect from a front desk host or a showroom guide. That sense of ease is hard to fake, and it hints at how much careful engineering it takes to keep perception, speech, and movement in sync under real-world pressure.
Agibot’s broader deployment history helps explain why those details feel so polished. The company’s robots are already working in reception and hospitality roles, performing in entertainment settings, supporting industrial manufacturing, sorting items in logistics operations, patrolling for security, collecting data, and serving as platforms for research and education. Each environment stresses the systems in different ways, from handling background noise to navigating cluttered layouts and unpredictable human behavior. The lessons from those deployments fed directly into the behavior visitors saw at CES 2026, where the robots had to cope with constant traffic and curious crowds without losing composure.
Looking back at the show, Agibot’s U.S. debut feels less like a distant promise of what humanoid robots might one day become and more like a grounded snapshot of where they already are. Multiple robots moved in coordinated demonstrations, interacted with people, and handled small but meaningful tasks in full view of a demanding crowd. In that context, the A2 recognizing a passerby in blue and another visitor behind a camera is not a show trick. It is a quiet, convincing example of a company that has decided to measure progress by what its robots can do on an ordinary day, in a very public place, with no second take.
CES always has its share of attention-grabbing robots. But this year in particular seemed to be a landmark year for robotics. The advancement in AI technology has not only given robots better “brains,” it’s enabled new levels of autonomy and given rise to an ambitious, if sometimes questionable, vision for our robot-filled future.
From sassy humanoids to AI-powered pets and chore-handling assistants, we sought out as many cute, strange and capable robots as we could find in Las Vegas. These are the ones that made the biggest impression.
Agibot Humanoids
Agibot's X2 humanoid robot.
Karissa Bell for Engadget
Of all the humanoids we saw at CES, Agibot's made the biggest impression. The company was showing off two models: the larger A2 and the smaller X2 (pictured above). The latter impressed us with its dance moves — the company told us it can learn surprisingly complex choreography — but the A2 turned out to be surprisingly capable at chatting up CES goers.
Later in the show, we came across the A2 at IntBot's booth, where the company had custom versions of both Agibot humanoids "running" their booth. I spent several minutes talking with "Nylo" and was genuinely impressed by its conversational skills, even if its roasts could use a little work. — Karissa Bell, Senior Reporter
Dreame's robo vac arms and legs
Dreame was back this year with some wild robot vacuums. The company showed of the Cyber 10 Ultra, a robot vacuum with a multipurpose extendable arm. The arm, which we got a glimpse of at last year's show, can pick up stuff, but it also has its own cleaning attachments, allowing the robot to clean hard-to-reach corners and other spots that wouldn't otherwise be accessible.
Dreame also brought its latest wild concept, the Cyber X, which has legs that propel it up and down full-size staircases. The legs are somewhat unsettling — they look alarmingly similar to mini chainsaws — but watching it glide up and down stairs was impressive all the same. — KB
OlloBot
The long neck version of OlloBot.
Cheyenne MacDonald for Engadget
OlloBot is one of those semi-ridiculous CES robots that's just impossible not to smile at. It has the goofiest face, with top-sitting frog eyes slapped onto a tablet where its mouth is displayed. Then, on top of that, it has a patch of soft fur on its neck and nowhere else on its body, which is penguin shaped and complete with flappy little arms. There are two versions of OlloBot, one that's short with a fixed neck and another where the neck can stretch out to make it much taller. And of course, it can be dressed up in silly outfits.
It's a family-focused robot that responds to voice commands and touch, and is meant to capture memories as they happen, snapping pics and videos for its diary of notable moments. It can be used to make calls and control smart home devices. Everything is stored locally in its removable heart module, and there's a companion app for additional interactions. — Cheyenne MacDonald, Weekend Editor
Rovie
A robot with a dust pan like appendage dumps toys into a bin.
Cheyenne MacDonald for Engadget
Sure, we've seen multiple robots (particularly robovacuums) that can pick objects up off the floor and put them away to make homes tidier, but this one is cute and has a little face. Instead of using an arm to grab one thing at a time, Clutterbot's Rovie has a dustpan-style tray with two sweepers that fold out from its front. It drives around and, using computer vision, identifies toys that have been left on the floor and scoops them up. Then, it dumps them in a designated bin where they're consolidated and out of the way.
It's still in the R&D phase, a team member said when I visited the booth, but this is one I'm hoping to see become a real, purchasable product soon. For parents of small children who are constantly leaving their toys around, it would be pretty convenient to have a tiny robot picking up after them. Also for me, who doesn't have children but a very sweet and hardworking cat who loves to steal socks and then deliver them as if they're her kills, leaving socks scattered all over the house. Clutterbot team, if you're reading this, please add socks to the list of items Rovie can sweep up. — CM
Saros Rover
Not to be outdone, Roborock also brought a stairclimbing robot vacuum to CES, Saros Rover. And, unlike Dreame's prototype, the Roborock can also clean the stairs while it climbs. No word on when it will be available or how much it might cost (probably a lot!) but the company says it is "a real product in development." -KB
CLOiD
CLOiD folded laundry at LG's CES booth.
Karissa Bell for Engadget
LG's CLOiD was definitely the most ambitious robot we saw at CES 2026. The company showed its home helper concept (slowly) folding and sorting laundry, fetching drinks from the fridge, putting food in the oven and retrieving a set of lost keys. But while the 15-minute demo gave us a tantalizing look at the appliance maker's vision for a "zero labor home," it's unlikely to be anything more than a slick demo anytime soon. The company has made no commitment to actually make a version of CLOiD people can actually buy. — KB
Allex
WIRobotics' Allex robot makes a heart sign with its hands.
Cheyenne MacDonald for Engadget
WIRobotics brought its new humanoid, Allex, to CES, and the robot was really hamming it up when we stopped by the booth, striking poses and engaging with visitors. It's a waist-up robot with articulated parts, from its arms to its fingers, and is meant to be a general purpose tool that could be used in manufacturing, the service industry or even households. Each hand can hold objects of up to about 6.6 lbs, and the robotic hand has 15 degrees of freedom. The company's website shows the robot's fingers are dexterous enough to do the Gen-Z heart sign, but when it looked at Karissa and me it threw a millennial heart up. Did Allex lowkey call us unc? — CM
Poketomo
Poketomo in one of the many outfits Sharp brought to CES.
Cheyenne MacDonald for Engadget
Sharp's Poketomo is an improbably adorable tiny meerkat. Well, technically it's an AI companion shaped like a fuzzy, portable meerkat. It might look like a toy, but the company says it's actually to be a companion for adults.
It’s small enough you can carry it around with you throughout the day (Sharp even makes a tiny Poketomo-sized clear backpack). Like a lot of AI companion devices we saw at CES, it’s equipped with a small camera and microphone that enables it to constantly interact with you. The camera also enables its “memory” so the pet can recognize and deliver personalized updates to its person. Poketomo launched recently in Japan, but sadly Sharp says it has no current plans to sell it in other markets. — KB
Bibo
Moony bibo (I-Type).
Cheyenne MacDonald for Engadget
It seemed like everyone was trying to cash in on Labubu hype at CES 2026. There were Pop Mart-style bag charms all over the place and countless products that looked suspiciously like the now ubiquitous toy monster. We even got one pitch for a "a labubu-like robot that talks to you" that, in fact, did not look like a Labubu in any way, shape or form. But there was one truly Labubu-like tiny robot that managed to stand out from the rest and kind of stole my heart, even though I'm not particularly into Labubus. (Please don't make me say Labubu ever again.)
Bibo is a cute-as-hell AI toy that's meant to be a companion you bring with you everywhere. It has a little camera on its head that it uses to see the world around it, and can recognize its owner's face and tone of voice, so it can respond to interactions in an emotionally appropriate way. It'll keep a daily diary of its activities, and while the toy comes in two starting personality "types" — Sunny bibo (E-Type), the bubbly extrovert, and Moony bibo (I-Type), the gentle, sensitive one — they'll develop more unique personalities over time. Their fur is soft and warm, so it feels like you're petting a kitten.
Why is it even cuter like this?
Cheyenne MacDonald
At the booth, the team had several of them on display wearing various outfits, in little dioramas showing them in classroom and camping scenes, and even deconstructed with the fur removed, which somehow made it look even cuter. Bibo isn't available to purchase yet, and when it is, it'll launch first in China before potentially expanding depending on its success at home. — CM
Sharpa
Sharpa's humanoid robot is seen playing ping-pong.
Cheyenne MacDonald for Engadget
Sharpa's booth had a lot going on and was definitely one of the bigger crowd-pullers. There was a humanoid robot playing ping-pong, another taking selfies with people and another dealing blackjack, along with a disembodied robotic hand that could mirror visitors' finger movements. The autonomous demos showed off what that highly dexterous hand can do, and it was pretty impressive — especially seeing it draw individual cards from the deck. — CM
Zeroth
Zeroth's W1 robot.
Cheyenne MacDonald for Engadget
Chinese robotics startup Zeroth brought two adorable home robots to CES: a pint-sized humanoid companion bot and a rolling robot that looks like Wall-E, with tank-style tracked treads so it can ride around outside. We didn't see these guys doing too much, but they sure were cute. The one that resembles Wall-E, called W1, kind of melted my heart just looking at it. (Don't get attached, you can't afford it.)
The tiny humanoid, M1, costs $2,400 while W1 costs $5,000. Both are expected to ship this spring, with a tentative date of April 15. — CM
Sweekar
Sweekars in their little outfits.
Karissa Bell for Engadget
Takway's Sweekar pocket pet was something I looked at and immediately thought, sigh, I'm going to buy that. It's a Tamagotchi-like virtual pet with AI smarts so it can form a personality based on your interactions with it and the activities you do together. The idea is that it "grows" with you. Like a Tamagotchi, it will require more frequent care in the younger stages of its life cycle. But after it reaches the adult level, it autonomously cares for itself, and it never dies. It can eventually keep itself entertained, and go off on its own virtual adventures and bring you back tales of its travels.
Sweekar is super cute as is, and it can be dressed up in little outfits for more personalization. The device comes in light yellow, pink, and blue, and we saw it sporting a snowboarder outfit and a full cowboy getup. — CM
Realbotix
One of Realbotix' robots.
Cheyenne MacDonald for Engadget
Realbotix is a company we've seen a lot at CES over the years, and it was at the show again for 2026 with several of its highly customizable, realistic humanoid robots. As always, it was among the most unnerving exhibits we saw. New for this year, Realbotix was demonstrating its Robotic Vision System, which allows its robots to see and react to their surroundings more naturally, tracking faces to look directly at whoever is talking and better reading emotion from facial expressions. Damn, it can sense my fear now… — CM
Onero H1
Onero H1 had an endearingly blank stare.
Karissa Bell for Engadget
Switchbot surprised us with its own chore-handling robot, Onero H1, which also won Engadget editors' pick for best robot of CES 2026. We were immediately taken by its weirdly long body and endearingly blank stare as it slowly wheeled around picking up laundry and depositing the items in a washing machine.
Like a lot of robot demos we saw at CES, we only saw Onero performing a small part of what Switchbot says it's actually capable of. But Onero also seemed much more realistic in terms of the type of robot helpers that people might actually see outside of CES, and the company told us it does plan to sell Onero (albeit in limited quantities) by the end of the year. — KB
Cocomo
Ludens AI Cocomo robot.
Cheyenne MacDonald for Engadget
Another robot pet that won us over immediately was Cocomo. Created by Japanese startup Ludens AI, Cocomo is an autonomous robot friend that yes, uses AI to respond to voice and touch and is meant to bond with its owners over time. The egg-shaped creature can scoot around on a wheeled base, or you can carry it around with you.
But what we loved about Cocomo is that it's not trying to be yet another AI assistant, give out life advice or perform tasks. Its goal is to provide companionship and well, be your friend. And while it can respond to voice input it doesn't exactly have a voice of its own: it communicates via cute humming sounds, which is a lot less creepy than some of the talking robots we saw. — KB
Yonbo
Yonbo at CES.
Cheyenne MacDonald for Engadget
Yonbo is a kids' AI companion robot that totally charmed us. It kind of looks like a dog, and when we visited its booth at Unveiled, there were four of them playfully bopping their heads to a pop song and cycling through different cute facial expressions and emoji eyes (including bowls of ramen). It's designed to be an intelligent playmate that can tag along for activities, talk with a child and read them stories, and even help them work through emotions, like getting frustrated during a game.
Yonbo's movement is controlled by a wristband, so it doesn't require a phone to play with. It can also be used as an extra pair of eyes for parents around the house. In Parental Monitor mode, which the team says is the only time its camera will be able to stream and store video, parents are able to see what Yonbo sees. The robot costs $800 and is available now. — CM
MÖFO
MÖFO in a glass case at CES.
Cheyenne MacDonald for Engadget
If we're being completely honest, the pitch for will.i.am's MÖFO (yes, MOFO, like motherfucker) had us a bit, um, perplexed for a hot second. We read it and all the accompanying materials over and over trying to figure out what, exactly, this thing does. Some of the claims that added to this confusion: "the agent 'octopuses' across your digital ecosystem through its eight USB-C connections"; it "converts moments into objects"; it "turns life notes into a life operating system."
We get it now, (we think): It's agentic AI hardware, kind of like a Rabbit R1 or AI Pin but in the form of a teddy bear. Sadly, we didn't get to see MÖFO up close or watch it do anything, but we are nonetheless intrigued, if still a bit confused, by this strange teddy bear. — CM and KB
This article originally appeared on Engadget at https://www.engadget.com/ai/the-robots-we-saw-at-ces-2026-the-lovable-the-creepy-and-the-utterly-confusing-153537930.html?src=rss
