Packaging potassium sulfate, a fertilizer vital to the planet’s food supply, is visually striking—not because of what you see, but because you don’t see much at all. In China’s Xinjiang region, home to the world’s largest deposit of the mineral, piling it up in warehouses creates dust clouds so severe that workers are forced to drive heavy machinery by feel.

Some companies are now turning to a technology that not only offers a way to see through the dust but also keeps workers from entering the warehouse at all. The system, developed by BuilderX Robotics, a Chinese tech company, uses cameras that are like night-vision for dusty areas. More significantly, operators drive excavators, loaders, and other machines from a remote office filled with rows of videogame-like stations. All they need is a 5G or satellite connection.

The ability to control physical machines from a distance is called teleoperation, and it could become a significant force of change in the global economy.

In Japan, the shelves of over 300 convenience stores are being restocked by robots monitored and sometimes controlled by workers in the Philippines. Düsseldorf airport was slated to begin testing shuttles driven by remote workers in May. A startup in Atlanta is offering robot security guards operated by remote staff, and last summer, a surgeon in France performed a teleoperated procedure on a patient in India.

While offshoring teleoperated jobs to overseas workers hasn’t yet become routine, Mark Graham, professor of internet geography at the University of Oxford, suggests the technology is worth our attention because it might enable companies to expand on their well-established habit of outsourcing jobs to places where labor is cheaper.

The use of remote labor isn’t new, Graham told SingularityHub. But teleoperation extends the logic of outsourcing to tasks that were previously thought to be “stubbornly local.”

“The novelty is less about the existence of remote labor and more about the kinds of work that can now be pulled into a planetary labor market,” he said. “Once that happens you can expect the usual pressures around labor arbitrage, control, and fragmentation to follow.”

It’s not clear we’re ready for the consequences.

---

BuilderX Robotics is a global leader in teleoperation for heavy machinery and a good expression of the changes ahead. Shaolong Sui, a graduate of Stanford University with a degree in mechanical engineering, founded the company in 2018 as a response to labor shortages in the construction industry in Asia.

“A shortage of trained operators isn’t a problem only in developed countries,” he told me. “Young people here in China don’t want to do this work. It’s dusty and dangerous.”

Rather than focusing on full robotic autonomy, which many construction companies have pursued over the past decade, Sui identified teleoperation as a more realistic way to move operators from harsh environments to safer conditions. Making use of the proliferation of low-cost sensors and 5G at the time, Sui completed a prototype in 2019. Today, his company offers teleoperation for 14 different industrial machines, including excavators, loaders, and bull dozers.

In our conversation, it was clear he hopes to improve working conditions for manual laborers. I lost track of the number of times he mentioned removing operators from dangerous worksites. “These workers deserve a better life,” he said.

BuilderX’s workstations do seem to have transformed some of the punishing work of an industrial site into a more white-collar experience, complete with tea and coffee break rooms and toilets down the hall. Sui said his solution allows construction firms to hire senior citizens or people with disabilities who, thanks to the videogame-like interface, can now operate heavy machinery. In another video, a Japanese woman who pilots an excavator proudly shows off her complex nail art, something she claims she couldn’t maintain when she worked in the field.

“Not only is this a much safer workplace, but the lifestyle benefits are that you can sit in an air-conditioned space, enjoy your tea, and when you go home, you’re still clean,” Sui said.

There’s no doubt the approach is safer for frontline workers like those in Xinjiang. Evidence suggests that high levels of potassium dust exposure can cause chronic bronchitis. While pulling someone from dangerous work is a good thing and that should be taken seriously, Graham told me, it doesn’t necessarily mean they’re free from exploitation.

“A worker can be removed from the physical site and still be subjected to intense surveillance, deskilling, isolation, fragmented contracts, algorithmic management, and downward pressure on wages. In other words, the risk can move rather than disappear,” he said.

Sui and Graham both agree there are plenty of forces that might slow the pace of outsourcing. Currently, none of BuilderX’s customers offshore work to overseas operators. But that doesn’t appear to be a technology constraint, as recently demonstrated by an operator in Poland controlling an excavator over 4,000 miles away in Beijing. On the technical side, latency—the delay between operator and machine—and reliability will shape the rate at which firms can choose to offshore workers. But it’s more likely to be limited by regulatory constraints in the form of licensing, insurance, and safety requirements.

That said, Graham believes the biggest force driving work overseas will be the same one that’s pushed clerical and service work offshore; the relentless pursuit to increase profit and reduce cost.

“If firms can hire people in lower-wage labor markets to operate expensive equipment thousands of miles away, many of them will try,” he said.

---

Most debates about AI and robotics focus on job loss due to automation. There is relatively little discussion about the risk of offshoring teleoperated work as the technology comes online. This is partly due to the hype surrounding physical AI, a Silicon Valley buzzword describing a world where fully autonomous robots cut humans out of the loop. But Graham says that when machines arrive people tend to incorrectly assume humans disappear.

“In many cases, what gets described as automation is really a reorganization of labor. Work gets broken apart, moved around, and hidden from view,” he says.

As is the case with AI,  the robotics industry’s push toward full automation is still plenty reliant on a hidden system of faraway workers. Teleoperation provides training data for robots and is needed to help them deal with unexpected events. Consumer robotics startup 1X is selling a $20,000 humanoid that will sometimes need to be  controlled by remote staff. It’s not clear how often future robots cleaning dishes in San Francisco kitchens will be steered by gig workers in Mumbai.

Robotaxi company Waymo already relies on human agents to assist, though not literally drive, vehicles stuck in difficult scenarios. The firm recently disclosed for the first time that some of these agents are based in the Philippines. This information, surfaced during US congressional testimony, immediately raised questions of oversight for safety-critical work: For instance, should a worker in Manila be required to get a California driver’s license?

Amid an already combustible US political environment, teleoperation could raise the heat even higher. Fueled by fears of Americans losing jobs to people overseas, Wyndham Hotels and Resorts, the parent company of La Quinta, was last year forced to respond to anger over a viral video depicting workers allegedly in India remotely handling check-in at one of their Miami hotels. As Graham points out, people tend to care more about outsourcing when it’s no longer hidden in a back office.

But outrage alone, he says, rarely defeats a business model that saves money. Due to network effects surrounding training, infrastructure, and other business process optimization, outsourced labor also tends to cluster in specific areas. This may already be happening in the case of Waymo, which could soon see the rise of something like a “driving district” in Manila. In the future, other types of teleoperated work could follow suit, giving companies a ready-made destination to shop for low-cost labor.

For Graham, it’s urgent that we begin requiring certification from independent bodies, which can better scrutinize a company’s production networks. At Oxford he directs Fairwork, a project aiming to improve labor practices in digital supply chains.

---

I asked Sui how he thinks his customers may reorganize their operations around this new ability to remotely control their machinery.

“We’re working with traditional industries, and so it’s not just about adopting a new technology. There are significant management changes they will have to navigate. You could call this transformation friction because they will need time to digest this new capability step by step,” Sui said.

Despite the fact they could use the technology to outsource work across national borders, none of his customers are doing so just yet. Sui used open pit mines as an example. In this case, where fully developed towns with schools and hospitals have built up over decades, his customers still cluster their workforce next to the sites where they operate. Instead of driving into the mine, operators work from an office and go home clean at the end of a shift.

BuilderX has deployed its technology at more than 100 sites in China, Japan, and parts of Europe. It’s now expanding into new markets including South America and the Middle East. When asked whether he thinks his technology will be used for transnational outsourcing, there’s no hesitation. “Oh yes, I think this is coming in the very near future.”

The post Companies Could Soon Staff ‘Stubbornly Local’ Jobs With Workers 4,000 Miles Away appeared first on SingularityHub.

Physical AI—robots working autonomously alongside people in factories, warehouses, hospitals, and homes—is arriving faster than most expected. Traditional...

Physical AI—robots working autonomously alongside people in factories, warehouses, hospitals, and homes—is arriving faster than most expected. Traditional safety which was built for structured environments can not work anymore as the spaces become more unstructured and robots move out of cages. AI-driven safety is the key. Marking a major milestone in the arrival of physical AI…

Source

In 2018, Amazon brought me in as the lead UX Sound Designer for Astro, its first consumer home robot. Astro used cameras and other sensors to map and navigate your home and workplace, and could proactively patrol, check up on loved ones, and transport small items using its built-in cargo bin. While there was a well-defined feature set and form factor, initially there was no character direction. In fact, even before Astro had a name, there were two main questions—was it simply Alexa on wheels, or was it a robot with its own character?

The Astro team was divided. One option was to focus on Alexa, and treat the mobile robot simply as an added utility. Along with the majority of the UX team, I argued for Astro to not focus on Alexa. Our belief was that a thing that moves through your home and turns toward you with intent can never be just an appliance. People would ascribe character to it whether we wanted them to or not, and so the only question was whether we shaped that character or let it happen by accident.

Ultimately, Astro became Astro rather than Alexa, and user testing backed up our decision. People didn’t see the robot as Alexa. They saw it as its own character, and that’s what they wanted it to be. Alexa on the device felt somewhat strange and creepy, but building Astro its own voice was too slow and expensive in 2018. So, we settled on Alexa as a supporting character that handled any actual talking, while Astro was the main character, communicating as much as it could without words, through sound, motion, and facial expressions.

I had been brought on to the Astro team to define the robot’s sound design language and voice. But there was no one to flesh out the robot’s actual character. You cannot make a single real decision about a character without defining it first. Every choice about how Astro moved, sounded, paused, or reacted was a character choice, and those choices required all disciplines working together. As sound lead, I was weaving together sound, motion, and character, and how they played together inside each story moment. The animators, who programmed Astro’s motion and facial expressions, were extraordinary at what they did, but the emotional arc they were animating came from the sound (and therefore character) work first. So I stepped into that role, which is where my real work started. What I learned about building character for robots applies to nearly everything being built in embodied AI right now.

Character Is a Design System

Developing a character for Astro meant answering questions that had never been asked about a product at Amazon: What is the emotional range of this robot’s baseline state? How does this robot communicate uncertainty without eroding trust? Where is the line between being expressive and annoying? What are the vulnerabilities of this device’s character?

These are design questions. They have real answers, and every team working on the product has to build from them. For example, Astro’s emotional range was designed to be relatively small at first. We never wanted Astro to get too sad or too angry. It could play sad, but would snap out of it quickly and end the reaction on a high note to keep things positive.

Character leaks out of every seam and can create a disjointed experience if not defined correctly. Even if it’s just animation timing that’s slightly off, or a response that’s technically correct but contextually tone-deaf, users feel every one of these inconsistencies, even if they can’t name them. Watch what happens at the beginning and end of this Sing sequence:

Astro goes from nothing, into the emotional moment, and then lands back on nothing. No buildup, no cooldown, no sense that the feeling came from somewhere or had anywhere to go. I pushed hard for better character stitching, the transitions in and out of expressive moments that make a performance feel continuous rather than assembled, but it never got implemented. The moment itself works. But without the stitching, it reads as a clip playing on a robot rather than coming from within the robot character itself.

Story and Sound at the Beginning

We had decided that Astro would have no spoken dialogue, but it had something that functioned the same way: a vocabulary of sounds, tones, and rhythms that acted as its voice. This vocabulary became the leading output of the character’s personality. The robot’s motion and facial expressions were built around it.

Astro’s wake-up sequence is a great example. Waking wasn’t just a boot animation on the screen; it was an entire performance. Slow and humble at first, the robot oriented itself quietly, then stretched its screen, checked its wheels, and finally, with an upward gesture toward its telescoping mast, it popped it up slightly, and did a little dance of joy. Sound, motion, and eyes hit every beat together in full choreography.

The character’s output in that sequence was first written as a story. Astro is waking up in its new home for the first time. Its main aspiration is to be part of a family, so this is the moment it has been waiting for, this is its purpose. Being the responsible character that it is, it wants to make sure everything is good to go before it introduces itself and starts learning its new home.

This narrative came first because it drove every other decision that we made. After the story was written, sound gave that story a metaphorical voice: the excited tones, the pacing as it checked its wheels, and the bright melodic phrase as Astro looked up at its new family for the first time and introduced itself. Once the sound was laid down, the animation team did their thing with motion and facial expressions, taking cues from the emotional arc the sound had established. Motion didn’t lead—it followed the feeling of the story and the sounds, the same way an animator follows a recorded vocal take.

That wake-up sequence became one of the most-discussed moments in early user testing. People described it as “alive.” What they were responding to wasn’t any single element. It was all three channels (sound, motion, and facial expressions) expressing the same defined character in harmony.

Context Is Where Character Becomes Real

The most compelling characters are defined not by a fixed disposition but by how they respond to their environments and the people in them. They’re still recognizably themselves even as they adapt. This is what I call contextual character. A robot living in a home doesn’t occupy a single emotional state. It moves through rooms with different energy, encounters people in different moods, operates at different times of day, and responds to an endless range of social situations it was never explicitly designed for.

We got close to a contextual character output with Astro’s sound. When a specific piece of environmental context was fed in, the system adapted beautifully, and Astro felt completely alive. But every state like this was still a prediction we made by hand—a situation we had to imagine in advance and design a response for. A random home throws more situations at a robot than anyone can possibly predict, so there was always a longer tail of moments the system was never prepared for.

The difference between a product people describe as “smart” and one they describe as “aware” often comes down to this. Smartness is capability. Awareness is context. Presence is character. And character is always in reaction to the people around it, to its environment, to its own evolving state. That’s what makes it feel like something is emotionally present with you.

This is where AI changes the game for character design in ways that go well beyond what was possible with Astro. AI-driven adaptation doesn’t require the contextual predictions that we relied on. It learns the specific rhythms, preferences, and emotional context of the people it lives and works with. The character doesn’t just respond to context. It grows into it.

What Industry Is Missing

The character and soul of the impending wave of embodied AI products appears to almost always be an afterthought. And character defined late is character defined by default. It becomes the sum of a thousand small decisions made by different people thinking about anything but character. People project character onto devices whether you plan for it or not, especially if those devices move—a robot that moves is already a character. If nobody has designed this character, the result will be products that feel like nothing, or worse, feel confusing and not trustworthy. Technically impressive, but lifeless.

We did not get this fully right with Astro. So many things were moving in parallel that character was rarely treated as a utility, and it made sense why. When you are building a first-of-its-kind product, the things that are the loudest are the ones that break, the deadlines, the costs, the features a customer can point to on a box. Character is quieter than all of that. It’s easy to assume it can come later. On a team as large as the Amazon Astro team, it’s lucky to get any idea onto the road map when it is competing with a hundred others that all feel more urgent in the moment. None of this came from people not caring. It came from character being the kind of thing that is hard to prioritize until you see what its absence costs you.

My Asks to Product Leaders

If you are building a product that will share physical or conversational space with people, three things are worth considering:

Define character before you define interactions. You need a defensible character with enough emotional logic to answer hard questions consistently. Find answers to character questions early, and have every discipline build from the same foundation.

Build story and sound into the character pipeline, not the production pipeline. Story and sound developed alongside character definition has the chance to inform motion, expression, and interaction logic. This requires a different kind of collaboration, and a different kind of hire.

Design for adaptation, not just consistency. A consistent character is necessary, but the products that will matter most in people’s lives are the ones that deepen through use. The infrastructure to support that is more and more accessible, but the design thinking to take advantage of it is still rare.

An expanded version of this story is available on Medium.

On 19 April 2026, the Honor Lightning humanoid robot ran a half-marathon in 50 minutes and 26 seconds, beating the human world record by 7 minutes and the best robot time from 2025 by almost 2 hours.

How did Honor do it? Is there some magical technology or technique that unlocked this performance? How did the company beat the significantly better-known Unitree (which reportedly had to supply its robot with an ice backpack to try and complete the race without overheating)? My doctoral thesis involved building and controlling hopping and running robots, and since then I’ve tried to design and build efficient commercial legged robots, giving me a decent idea of the constraints involved. In this article, we take a look at the fundamental underlying constraints to try and answer these questions.

The Physics of Running

Running consists of alternating phases of a leg pushing against the ground (“stance phase”) and the body flying through the air (“aerial phase”). In the aerial phase, the body falls due to gravity, losing vertical momentum. The leg in stance phase pushes against the ground to redirect the vertical momentum upward, while the other leg swings forward to reposition for the next foothold.

Electric motors use energy to produce torque—the higher the torque, the more energy is lost as heat. Adding a gear train after the motor amplifies its torque and reduces its speed. A large reduction helps with torque production, but since the rotor of the motor itself has to spin faster, it becomes very sluggish at accelerating its output. This is obviously bad for the swing phase described above. These competing effects mean that for a particular motor, there is usually a sweet spot for the gear ratio:

The power consumed by a robot leg is minimized at an optimal gear ratio (30:1 in this example).Avik De/Datawrapper

How Honor Did It

While the Lightning’s motor specifications are not published, the hip and knee motors roughly have a 110-to-150-millimeter outer diameter. For an approximate set of motor parameters, I looked to the ILM115x25 motor due to its relevant size and detailed specifications.

We can use a simple physics model to estimate the power consumption for running at 7 meters per second (the Lightning’s average half-marathon speed) as gear ratio varies:

The light blue curve shows how to pick the optimal gearing (45:1). The dark blue curve shows how much heat will be produced in the knee motor, ~150W for the optimal gearing.Avik De/Datawrapper

We see that the drivetrain is not magical: with a gear ratio chosen for this task (we’ll return to this below), the approximate robot power consumption would be a very reasonable 400 watts.

However, the dissipated knee power ( typically the main thermal limiting factor) is approximately 150 W. This is almost an unavoidable consequence—running at human speeds with a humanoid-size robot will inevitably generate this amount of heat! Over a prolonged period, keeping the motor from overheating would be a challenge, but the Lightning has a trick up its sleeve:

According to Honor, the liquid-cooling pipes penetrate deep into the motors like capillaries. The high-power liquid pump has a heat-exchange flow rate of more than 4 liters per minute. Each of the four drive motors in the lower limbs is equipped with an independent liquid-cooling circuit.

Liquid cooling is not new, but it’s definitely not a commodity. It has shown up in research periodically, and on the commercial side Apptronik tried it for a few of its prototypes but (to my knowledge) does not use it on its main Apollo platform. Basic air-convection-based cooling would not continuously be able to extract 150 W out of the knee motor, and so the cooling technology is a key enabler of this type of performance.

Why Others Couldn’t Compete

Why did Honor’s competitors, including more established and widely shipped humanoids such as from Unitree or Agibot, not compete as well?

We can use the same model to generate an equivalent energetics plot for walking at 1.5 m/s, a much more modest but potentially more common activity for a commercial humanoid robot:

The solid and dashed light blue lines show a running-optimized design, while green lines show a walking-optimized design. The optimal ratio for walking is much lower (30:1 vs. 45:1). However, the power dissipated in the knee motor while running [dark blue] is much higher at 30:1 vs. 45:1—the price to pay for running with a walking-optimized design.Avik De/Datawrapper

The plot adds a new green curve for the walking power, and the optimal gearing is significantly different!

Let’s say you design your robot to excel at the normal walking task and choose the green design with 30:1 gearing. The knee motor power to run a half marathon is over 300 W (red arrow), more than two times what we had with the running-optimized design. It wouldn’t be so surprising to need ice packs!

Conversely, visually following the green curve shows that the running-optimized robot wastes more power for walking. Using larger motors sized for running increases the weight of the robot and wastes power when it is standing or walking. The larger motors also pose practical issues like bumping into objects while operating in homes or factories.

Closing Thoughts

Honor’s half-marathon performance was an impressive engineering effort and result. It didn’t need any magical leaps in technology, but the deployment of the capillary motor cooling solution is a notable advance without which this running pace would have been unsustainable. The cooling, weight optimization, and robustness advances may well be useful for more practical purposes like carrying heavy payloads down the line.

The Honor Lighting robot [right] has much larger motors driving its legs than the Unitree H1 robot, making it a more efficient runner but a less efficient walker.Left: Wei Zhiyang/Zhejiang Daily Press Group/VCG/Getty Images; Right: VCG/Getty Images

However, the Lightning is not as well-suited to other tasks as a robot designed for greater versatility. Engineering is always characterized by trade-offs, and making the correct ones separates good products from great ones. With consistently improving AI language models, this very human skill is becoming the most valuable one an engineer can have.

The news coverage seemed to overly focus on the fact that the human half-marathon record had been broken by a robot. Machines and humans have very different capabilities and constraints, so why should we ever have expected the half-marathon time for a robot and human to be related? As in Deep Blue’s 1997 defeat of Garry Kasparov in chess, where it couldn’t physically move the pieces, the Honor robot’s capabilities are much narrower than a human running elbow to elbow with other runners while visually navigating the course without GPS. Comparing the robot runner to a human runner is just an apples-to-oranges comparison, which only risks diminishing Honor’s engineering achievement on one hand and human athletic achievement on the other.

Quick glossary for readers new to VLA/WAM terminology VLA Vision-Language-Action model: a robot policy that starts from a pretrained VLM backbone and adapts it...

Quick glossary for readers new to VLA/WAM terminology VLA Vision-Language-Action model: a robot policy that starts from a pretrained VLM backbone and adapts it to generate actions from visual observations and language instructions. Large-scale VLM pretraining is a core part of the recipe. See Pi-0 and GR00T N1. WAM World-Action Model: a policy that starts from a pretrained world-model or video…

Source

This article is part of our exclusive IEEE Journal Watch series in partnership with IEEE Xplore.

As robots advance in terms of dexterity and other physical capabilities, it becomes more likely that humans may find themselves working alongside them. If that happens, how will robots’ emotional capabilities need to advance for them to successfully work with people?

In a recent study, researchers trained collaborative robots to read human emotions by not only accounting for facial expressions, but also contextual factors in the interactions as well. Through experiments with 40 volunteers, the researchers then evaluated how a robot’s ability to read human emotions and adjust its behavior in turn impacted a human’s perception of the robot and its capabilities as the two collaborated on tasks. The results—which show that the emotional capabilities of robots only go so far with humans—were published 18 May in IEEE Robotics and Automation Letters.

Seung Chan Hong led the study as part of his undergraduate thesis while studying at Monash University, in Melbourne, Australia. He notes that, while there has been a lot of hype in the advancing physical abilities of robots, this is only one piece of the puzzle. “We need to also innovate when it comes to them actually interacting with humans, not just their physical capabilities,” he says.

This prompted him to dig deeper into the emotional aspects of human-robot interactions. First, Hong and his co-authors decided to train a robot to read human emotions using a vision language model (VLM), which is similar to large language models (LLMs) such as ChatGPT, but which can also take visual inputs.

Training VLMs for Human Emotion Recognition

To evaluate their VLM, which used Gemini 2.5, the researchers had volunteers watch videos of robots handing over objects to humans—with varying degrees of success—and describe the emotions the humans were expressing. Importantly, the volunteers labeling these videos were able to take into account more context in these interactions, rather than reporting solely on the facial expressions of the humans in the video. For example, a person pausing to think with a furrowed brow may simply be concentrating on their task at hand and not necessarily be angry. Contextual factors such as drumming their fingers, pursing their lips, or other behaviors can point to the real cause of a person’s furrowed brow.

The researchers then compared their VLM to a conventional AI system that relies on standard facial analysis and object tracking that is used in human-robot interactions. They found that the VLM outperformed the traditional approach. On a scale from 0 (no similarity in meaning to the emotion identified by the human volunteers) to 1 (a perfect match in meaning), the conventional AI system achieved a score of 0.77. In comparison, the VLM achieved a score of 0.86.

Hong says, “I think [the VLM] was able to align with what human observers were seeing a lot better, because it wasn’t just looking at the person’s face for a brief amount of time, but seeing the whole scene—where the person was and what they were doing, and how they were interacting with the robot.”

In a second experiment, the research team asked 40 volunteers to interact with a robot using their VLM—but purposefully programmed the robot to make an error. The robot then had to offer either an emotionally adaptive apology that accounted for the human’s perceived response to the mistake or a pre-scripted spoken apology.

Participants overwhelmingly preferred the emotionally adaptive response, with 31 out of 40 people favoring this approach over a boilerplate apology.

However, their survey responses underscored how this emotional adaptivity was far less important than the robot’s functionality. After collaborating with a robot that failed in its task, many participants ranked their trust in the robot as lower, regardless of how it apologized for its mistake. “A personalized apology acts as a social lubricant, but it cannot repair the trust lost by the robot failing its physical task,” Hong says.

Interestingly, the VLM classified the emotions of its human partners similarly to human volunteers who observed an interaction from a third-party perspective. But when the VLM’s assessments were measured against humans’ self-reported emotions during the second experiment—the most accurate descriptions of their true emotions—its ability to accurately predict emotions dropped significantly.

“While the VLM is a good observer of outward social cues, it isn’t a mind reader,” Hong says. “It matched third-person human observers well, but it didn’t always align with the users‘ internal, self-reported feelings.”

Together, these results show that robots are not perfect at reading human emotions. So while people might appreciate their efforts, they still ultimately will want competent co-workers.

This story was updated on 15 June 2026 to correct where the research was conducted and clarify that the researchers evaluated the performance of a pre-trained model.

An examination of how socially assistive wellness robots could support the seven dimensions of senior wellness, and how a framework can measure their autonomy.

What Attendees will Learn

1. Why the senior care crisis exceeds incremental automation. Demographic pressure, workforce shortages, and a daily wellness-programming gap all strain traditional care models.
2. What defines a wellness robot as a category. The seven ICAA wellness dimensions and eight properties separate these robots from companion and medical devices.
3. How autonomy can be measured with CRAS. This six-level scale, modeled on the SAEJ3016 driving standard, evaluates four care dimensions.
4. What maps the road to full autonomy. The paper examines technical capabilities, clinical evidence, and a three-phase roadmap toward the early 2030s.

As AI agents move from the digital world to the physical environment, they can readily use NVIDIA Jetson to accelerate real-world deployment with optimized...

As AI agents move from the digital world to the physical environment, they can readily use NVIDIA Jetson to accelerate real-world deployment with optimized memory and performance. NVIDIA JetPack 7.2 directly supports one-command deployment of NVIDIA NemoClaw, an open source stack that adds privacy and security controls to OpenClaw. It introduces NVIDIA agent skills for Jetson—Jetson device…

Source

Developing autonomous vehicle (AV) policies requires bridging an important gap between training and deployment. Vision-language-action (VLA) models that can...

Developing autonomous vehicle (AV) policies requires bridging an important gap between training and deployment. Vision-language-action (VLA) models that can reason over more complex driving scenes and produce richer intermediate reasoning are predominantly trained in open-loop, where model outputs are directly compared to ground-truth behaviors without considering their effect on the environment.

Source

💾

Physical AI systems must understand the real world before they can act within it. Robots, autonomous vehicles, and smart spaces need to understand what's...

Physical AI systems must understand the real world before they can act within it. Robots, autonomous vehicles, and smart spaces need to understand what’s happening in their world, predict what’s likely to happen next, and generate actions for specific environments, embodiments, and tasks. NVIDIA Cosmos 3 is a frontier foundation model for physical AI that combines physical reasoning…

Source

When a group of academics started making open-source robotics hardware, a generation of roboticists got years of their lives back. Now, the bigger challenge is getting robots to think—and that’s starting to be open sourced too.

The shift is still early, but companies including Hugging Face, Nvidia, and Alibaba have all made significant bets on open-source robotics in the last two years, releasing tools and models aimed at the higher-level work of getting robots to reason, decide, and act.

The open source movement that accelerated other AI applications is now being applied to the problem of making robots smarter. If these attempts to bring AI to robotics with open-source platforms succeed, the barrier to building a capable robot could fall as fast as the barrier to building an AI application did.

The world ROS built

Open-source robotics software has been around since the mid-1990s, with early projects like Carnegie Mellon University’s Inter-Process Communication package and the Player Project in the early 2000s laying the groundwork. But these were often tied to specific research groups, and the field remained fragmented.

The Robot Operating System, ROS, changed that when it made its debut in 2007. By bundling tools and attracting more users, it became the de facto standard. The story of open-source robotics, in many ways, starts there.

Despite its name, ROS is not actually an operating system. Rather, it is a software framework that sits on top of Linux and handles robotic fundamentals like moving data between components, talking to hardware, building maps, planning paths, and supporting developer tools, such as data logging and visualization. Before ROS, every robotics team wrote that infrastructure themselves. It often took a year or two before a lab could get to the research it actually cared about.

Brian Gerkey, who helped build ROS in the mid-2000s, says he was drawn to the project because of how much open source had already changed the world, pointing out that nearly the entire internet is built on it.

“I’m a tool builder, and I like to share everything as openly as I possibly can, because I think that’s where we get the most impact out of what we build,” says Gerkey, board chair of Open Robotics and now CTO at Intrinsic, a robotics and AI unit of Google.

As it was developing, the AI community largely took the same approach, sharing research, models, and data openly, and the field accelerated faster than almost anyone predicted. Now some of those same advancements are arriving in robotics.

Open-source AI for robotics

Computer vision, once a hard problem, has advanced dramatically in just a few years, says Spencer Huang, Nvidia’s director of product for robotics. What once required significant expertise can now be done in a few lines of code. Simulation tools have become accurate enough to be useful for training, and access to the tooling that once required a specialized lab is now widely available, much of it open source.

“To get into robotics, you no longer need a Ph.D.,” he says. The result is a much larger pool of people who can contribute, and the field is starting to look less like a specialized discipline and more like a platform that anyone can build on.

Nvidia has built out an open-source robotics stack that covers the full development pipeline. Its Cosmos world models generate synthetic training data and simulate physical environments. Its GR00T models give robots the ability to reason through and execute complex tasks. And its Isaac frameworks handle the orchestration that ties training, simulation, and deployment together. Not everyone needs to train the robots from scratch, Huang says, and most people probably shouldn’t.

“If you gate pre-training, the field just never grows,” he says. “We should be able to provide a high-quality, state-of-the-art pre-trained model that anyone can go and take and fine tune for their own purposes.”

All of Nvidia’s open-source models live on Hugging Face, the open-source AI platform that has become the default place to share models and datasets. Hugging Face launched LeRobot, a community platform for robotics AI, in May 2024. Since its launch, the number of robotics datasets on the platform grew from 1,145 at the end of 2024 to more than 58,000 today, making it the single largest dataset category on the hub.

Hugging Face has also moved into hardware, acquiring robotics company Pollen Robotics. The acquisition came from a realization that software alone was not enough, according to Clement Delangue, Hugging Face’s CEO. The goal, as with the software, was to bring more people in.

The contributors to LeRobot include the biggest names in the industry, academic labs, and hobbyists building robots in their spare time. For instance, earlier this year, Alibaba released RynnBrain, an open-source foundation model for physical AI that the company claims outperforms comparable offerings from Google and Nvidia on benchmarks. That diversity of projects, Delangue says, is important.

“It is not just one model or one dataset or one hardware,” he says. “It is a lot of small contributions that everyone can be part of.”

Commercial incentives muddle the field

The stakes, Delangue says, go beyond convenience. A world where only a few proprietary systems control the robots in people’s homes is a concerning one. “Having robots at home that you don’t really understand, that you don’t really control, that a few people in Silicon Valley control is a scary thought,” he says. “Open source gives an alternative path.”

But getting there is not straightforward. The open sourcing happening now looks different from what produced ROS, which emerged largely from academics pooling their work with no commercial stake in the outcome. The biggest contributors today are companies with clear business reasons to want more people building on their platforms. That’s not necessarily a bad thing, says Bill Smart, a professor at Oregon State University, in Corvallis, who was part of the early open-source robotics community. But the incentives are worth being aware of.

He also worries that the lowered barrier to entry has a downside. Researchers coming from AI without a robotics background are sometimes solving problems the field already solved. A newcomer might spend a week training a neural network to move a robot’s hand from one point to another, unaware that the same task can be accomplished with a few lines of code using decades-old techniques. The incentives are not always pointing in the same direction as the progress.

Smart is not without hope though. Whatever the motives behind the open sourcing, he says, the effect is real. More people are in the field than ever before, the tools are genuinely easier to use, and the community is bigger and more diverse than anything that existed when ROS was getting started.

“Anyone can make a robot move now,” he says. “As an old tech guy, that makes me happy and sad, because I’m no longer special.”

Over the next few decades, billions of autonomous, AI-powered robots will work alongside people in factories, perform tedious tasks in warehouses, care for the elderly, assist in unsafe disaster areas, deliver packages and food to our doorsteps, and eventually help out in our homes. Some will look like us, and many won’t. What is certain is that regardless of form factor, robots will all rely heavily on AI in order to deliver real-world value.

In 2025, total investments in robotics companies reached a record US $40.7 billion, accounting for 9 percent of all venture funding. The multibillion dollar question therefore is this: What will it take for AI-powered robots to begin to have a serious economic impact? Many of today’s robotics and AI companies are making bold claims, such as that humanoid robots will soon be coming into our homes, but there’s still a big gap between promise and reality.

The promise of robots that live and work alongside us has been the stuff of science fiction for a very long time. And while many programmers have tried to make that promise a reality, the physical world is just too complicated for traditional computer programs to handle the endless complexity it presents. Thanks to AI, robots are no longer being programmed—instead, they learn to operate in the real world. With enough practice, they can learn to perceive and understand the world around them, reason about that world, and use that reason and understanding to perform tasks that are useful, reliable, and safe.

The two of us have worked at the forefront of AI and robotics for the last decade, as a Professor in Robotics at Oregon State University and Co-Founder of Agility Robotics, and as former CEO of the Everyday Robots moonshot at Google X. Our experience deploying AI-powered robots in real-world settings has given us a perspective on where AI can be used to great benefit in complex robotic systems in the near term and where we are still on the frontier of science fiction. We believe AI will enable an inflection point in robotics advances, but that it will be through the well-engineered application of coordinated systems of different AI tools rather than a single ChatGPT-style breakthrough.

As the excitement around AI is matched only by the uncertainty of what will be possible, here are five hard truths that will define AI in robotics.

1. The YouTube-to-Reality Gap Is Real

For years, we have been seeing videos on YouTube with humanoid robots performing amazing moves on everything from a dance floor to an obstacle course. The inside knowledge in robotics is to “never trust a YouTube robot video.” The gap between real robots that can perform real work in unstructured human environments and carefully scripted and edited robot performances remains significant. The latest performance to get a lot of attention was a martial arts show featuring Unitree humanoid robots performing with children at the Chinese 2026 Spring Festival Gala. While impressive, this falls into a long lineage of tightly scripted robotic performances, where everything has been carefully choreographed and planned in advance. The low-level controls, synchronization, and choreography were stunning, yet the Spring Gala robot performance showed a level of autonomy and intelligence much closer to industrial robots building cars in a factory than something that will show up in your living room any time soon.

Seeing these kinds of demos nevertheless raises questions about where robotics really is. If robots can perform kung fu moves and do backflips and dance, why aren’t they also showing up on factory floors yet? And why can’t they do the dishes in my home after dinner? The simple answer is this: Making AI-powered robots capable of performing general tasks in varied human environments is still really hard. While impressive technological feats like those at the Spring Festival may make it look like we could be very close, the use of AI in these demos is only for low-level motor control (to keep the robots from falling over) and therefore is only a small part of the solution for robots to be general purpose in the real, unstructured spaces where we humans live and work.

2. Data Is An Unsolved Challenge

Large Language Models (LLMs) like OpenAI’s ChatGPT and Anthropic’s Claude were initially trained on an internet-scale database of text. The world woke up one day in late 2022 to ChatGPT demonstrating that AI computers could suddenly “speak” to us in prose or verse and about seemingly any topic. LLMs have turned out to generalize well and are now able to take multimodal input (text, images, video) and produce multimodal output. Importantly, the corpus of training data was both enormous and human-generated, which are characteristics that form the gold standard for AI training.

The fastest path to robots as part of everyday life may emerge through a range of robot forms performing increasingly sophisticated applications and employing a range of AI tools.Agility Robotics

Giving AI a body (in the form of a robot), so that it can engage with people in the physical world, continues to be a very difficult and broadly unsolved problem. AI models for general-purpose robotics must simultaneously satisfy multiple, often conflicting, physical, geometric, and temporal limitations while operating in unstructured, dynamic environments. In order to generalize, robot models need to be trained on data gathered in a high-dimensional configuration space, where “dimensions” represent text, lighting conditions, degrees of freedom, joint limits, velocities, force, and safety boundaries, just to mention a few. Importantly, this must be good data—it must contain many examples from what amounts to an infinite number of possible configurations in the physical world.

Since there are very few existing sources of data like this, approaches like teleoperation, video analysis, motion capture of humans, and self-exploration in simulation and in the real world are all seen as important ways to collect data. It’s a herculean task. For example, at Everyday Robots at Google X, we ran 240 million robot instances in our simulator over the course of 2022 to collect training data, mostly to train a trash-sorting model. Similar amounts of data will be needed for every skill to get to a similar level of capability, which is not yet human level.

3. There Will Be No Single Robot AI

We are far away from a moment where a single AI model might allow general-purpose robots to live and work alongside us.

General-purpose robots can have wheels or legs. They can have one, two, three, or more arms. Some have propellers and can fly, while others may be designed to operate under water. Some will drive on busy roads. The physical world is infinitely varied and complex. And then there are all the people and other animals that will be surrounding the robots. How do you train a model to operate a robot safely and reliably in all of these settings? The simple answer is: You don’t. At least not for quite some time.

We believe the winning AI architecture leading to the next big breakthroughs in general-purpose robotics will be “agentic AI” for robots, which are high-level coordinating models that can reason, plan, use tools, and learn from outcomes to execute complex tasks with limited supervision. Agentic, high-level models running on robots will invoke a system of specialized ones for different types of tasks. We will likely soon see multiple robots collaborating and coordinating with each other through their onboard agentic AI models.

AI tools are unlocking new and powerful capabilities in robotics, which in turn will enable new solutions and new markets. It’s encouraging to see these new models being made broadly available, some even as open-source solutions. This availability is akin to what happened with the internet: Real progress occurred when it became ubiquitous. We anticipate an inevitable democratization of complex behaviors in robotics with wide access to these AI tools and technologies.

4. Hardware Is Still Very Hard

Robots are complex systems with many parts that all need to work together with great precision. For a robot to be useful and safe, every part of it must be coordinated, from its perception systems to the computer controlling it, all the way down to its individual actuators.

Actuators—that is, the motors and gears—are a good example of an important part of the robot where what got us here won’t get us there. The actuators used at scale by most industrial robots will not work for robots that will operate in human environments. If these robots accidentally collide with an obstacle, the resulting impacts are harsh, forces are high, and things break. Humans don’t move in this way. We are far more compliant in how we interact with the world, and we’re constantly making contact with our environment and using that contact to help us accomplish things.

Consider the challenge of inserting a key in a lock: Humans typically don’t do this by aligning the key perfectly with the keyhole. Instead, we just feel for the edge of the keyhole and jiggle the key in. Robots need to be able to operate in novel ways to achieve comparable capabilities by using a new class of actuators that are sensitive to force and able to have a compliant interaction with the environment. While these kinds of actuators do exist, they are not yet generally available at scale for robot systems designed to operate around people.

5. Real Value Comes From “Easy” Tasks

There’s a big difference between tasks that look impressive and real-world tasks that provide value. Robotics is a perfect example of Moravec’s paradox, which states that tasks that are hard for humans are easy for computers (like multiplying two big numbers), and tasks easy for humans (like a toddler’s movements) are extremely difficult for computers and robots.

Serving customers is an unforgiving reality check, because customers only care about solving the real problems they have. If we are to deploy AI-based robot solutions, they must outperform the way things are currently done while demonstrating reliable performance metrics and safety. Agility Robotics’ early work to deploy our humanoid robot Digit in customer locations led to the realization that our first obstacle was safety: Robots that balance and manipulate objects in human spaces bring new types of risk to the workplace. In the first humanoid deployments, physical barriers were necessary, and Agility kicked off a multi-year engineering effort to solve the safety challenge, touching nearly every aspect of robot design and relying heavily on new AI-based approaches to human detection and behavior control.

Everyday Robots at Google deployed robots in 2019 that worked autonomously in office buildings doing chores like cleaning cafe tables and sorting trash. We quickly learned how “messy” and difficult the real world is for a robot. This experience informed the architecture and deployment of our AI systems while also gathering real-world data that could be combined with simulation data for training and improving models.

This focus on creating a product to meet specific customer needs and deploying robots in real-world settings is the only way to inform the structure of the AI tools and infrastructure for near-term utility on a path towards long-term broader capability and generality. There will be no “aha” moment, no silver bullet algorithm, and no volume of data sufficient to produce a general-purpose robot without extensive real-world experience.

AI Robots Are Coming, One Step at a Time

As we look to the future, there is no doubt that the world is bringing AI into the physical world through robots. We are at the beginning of a “Cambrian explosion“ of useful, intelligent machines. We believe AI is not one tool, but a huge frontier of technical approaches that is unlocking new capabilities so powerful, they will define our economy moving forward. This will happen not in one single definitive moment, but as an ongoing set of small and large breakthroughs, where AI-driven robots begin to provide real value in a few tasks, and then a few more, with impacts unfolding across numerous $100 billion-plus markets that will dramatically improve the quality of our lives.

Electronic waste is moving up on regulatory agendas in 2026. New European waste-shipment rules, expanded recycling fees on products with non-removable batteries in California, and an e-waste import ban in Malaysia, for example, are all increasing pressure to recover more value before electronics are shredded or exported.

The world is projected to generate 82 million tonnes of e-waste annually by 2030, according to the United Nations’ most recent Global E-Waste Monitor report in 2024. The report estimated that current e-waste management captures less than a third of the recoverable metal value contained in discarded electronics.

For recyclers, much of that lost value is a consequence of what happens before a circuit board ever reaches a smelter or shredder. Boards contain a mixture of components such as memory chips, processors, magnets, and capacitors, as well as valuable raw materials such as copper, aluminum, tantalum, and precious metals. Conventional recycling often mixes everything into bulk streams and destroys components that might otherwise be reused.

Tuurny, a startup based in San Francisco, is developing an automated system to remove and separate reusable chips from circuit boards before the remaining material is shredded. In April, the company announced it had designed a robotic system, called Nantul, to identify and extract RAM integrated circuits, claiming each machine can recover 300 intact RAM ICs per hour.

Sina Ghashghaei, Tuurny’s founder, says the company is preparing its first field deployment with dozens of machines through a six-figure deal with Areera, a television recycler in the United Kingdom, which processes 1,500 tonnes of televisions per month. The deployment is planned for early 2027.

Tuurny’s first target is recovering RAM ICs and other chips used in legacy systems where replacement components can be difficult to source. Ghashghaei says the company is talking with a few legacy chip suppliers and pursuing potential agreements to supply aluminum and copper recovered from circuit boards to smelters and refiners. He declined to identify the companies involved.

Robots for Automated RAM Recovery

Traditional electronics recycling often begins by shredding boards and sorting the mixed output afterward. Tuurny aims to do the opposite: Identify and remove components first, sort them by model or material, then reroute the recovered items to testing labs for potential reuse as new chips or to refiners and smelters for further processing.

Nantul comprises three robotic systems in one. The first is an arm to continuously feed the component-removal robots, paired with two tabletop machines similar to 3D printers or computer numerical control (CNC) machines. A neural network identifies and catalogs components, then searches the internet for manufacturers’ thermal-profile specifications. Nantul uses those specifications to employ a combination of suction, controlled heat, computer vision, and robotic controls to remove chips while minimizing damage. Recovered items are then sorted by model number in material-specific groups.

“We’re creating a new supply chain from old feedstock that didn’t exist before,” Ghashghaei says, adding that manual recovery is expensive and difficult to scale.

Tuurny’s recovery system includes a computer vision system that identifies specific RAM components to assess them for recovery.Tuurny

Minghui Zheng, an associate professor of mechanical engineering at Texas A&M University, in College Station, who studies robotic disassembly and electronics recycling systems, says Tuurny’s approach appears technically feasible, especially when focused on the narrow, valuable target of recovering RAM from more controlled e-waste streams.

“RAM is a good starting point because it has relatively high reuse value and is more standardized than many other electronic parts,” Zheng says. The harder challenge, however, is removing chips “without heat, mechanical, or electrical damage, and making sure it still works reliably afterward.”

Used circuit boards can vary by layout, markings, age, contamination, solder condition, or prior damage. A robot has to identify the correct component, choose a removal strategy, apply heat locally, lift the part cleanly, and preserve enough information about the part for downstream testing and resale.

E-Waste Recycling Strategies

Ghashghaei says Tuurny is building small modular machines using off-the-shelf parts, custom controls, and Nvidia Jetson Nano hardware. The company is trying to keep costs down by reducing hardware complexity to arrive at a price point far below centralized industrial equipment used at large facilities. He says the biggest challenge from an engineering perspective has been developing the autonomous computer vision and robotic control.

Last year, the four-person startup received a NASA-funded grant to support an AI-powered repair assistant for printed circuit boards that used computer vision and a custom large language model (LLM) to guide technicians.

Ghashghaei says Tuurny pivoted from board repair to e-waste processing after concluding that discarded electronics represented a larger market amid growing interest in the U.S. around on-shoring capacity for critical minerals and rare earths. The pivot also positions Tuurny to potentially address supply chain concerns around legacy chips for systems in telecom, aerospace, defense, and other industries where equipment remains in service long after chips leave mainstream production.

In practice, Zheng says the main challenge in making robotic disassembly of electronics commercially viable is ensuring it’s adaptable enough to handle the large variability in e-waste while keeping costs reasonable.

“Every electronic product is different, and used boards may be damaged, dirty, or arranged differently. The robot must be able to find the right parts, remove them carefully, and avoid damaging them in real time, which creates major challenges for robotic perception, decision-making, planning, and manipulation,” Zheng says. “Economically, the recovered parts should be valuable enough to justify the costs of the robot, sensing, testing, maintenance, labor, and scaling up the process.”

For smelters and refiners, the question may be whether Tuurny can supply predictable material streams at commercial volumes. Ghashghaei acknowledged that Tuurny’s scaling efforts could run into its own supply chain constraints in trying to acquire enough components to build more robots.

Zheng called Tuurny’s approach promising but still early. “For now, it is more realistic as a targeted recovery strategy for valuable components like RAM,” Zheng says. “The key question is whether the robotic disassembly technology can work reliably, affordably, and at scale.”

For years, the field of robotics has used the terms “dull, dirty, and dangerous” (DDD) to describe the types of tasks or jobs where robots might be useful—by doing work that’s undesirable for people. A classic example of a DDD job is one of “repetitive physical labor on a steaming hot factory floor involving heavy machinery that threatens life and limb.”

But determining which human activities fit into these categories is not as straightforward as it seems. What exactly is a “dull” task, and who makes that assumption? Is “dirty” work just about needing to wash your hands afterwards, or is there also an aspect of social stigma? What data can we rely on to classify jobs as “dangerous?” Our recent work (which was not dull at all) tackles these questions and proposes a framework to help roboticists understand the job context for our technology.

First, we did an empirical analysis of robotics publications between 1980 and 2024 that mention DDD and found that only 2.7 percent define DDD and only 8.7 percent provide examples of tasks or jobs. The definitions vary, and many of the examples aren’t particularly specific (for example, “industrial manufacturing,” “home care”). Next, we reviewed the social science literature in anthropology, economics, political science, psychology, and sociology to develop better definitions for “dull,” “dirty,” and “dangerous” work. Again, while it might seem intuitive which tasks to put into these buckets, it turns out that there are some underlying social, economic, and cultural factors that matter.

Dangerous Work: Occupations or tasks that result in injury or risk of harm

It’s possible to measure the danger of a task or job by using reported information. There are administrative records and surveys that provide numbers on occupational injury rates and hazardous risk factors. While that seems straightforward, it’s important to understand how this data was collected, reported, and verified.

First, occupational injuries tend to be underreported, with some studies estimating up to 70 percent of cases missing in administrative databases. Second, injuries and risk factors are rarely disaggregated by characteristics like gender, migration status, formal/informal employment, and work activities. For example, because most personal protective equipment—such as masks, vests, and gloves—are sized for men, women in dangerous work environments face increased safety risks.

These caveats are an opportunity for robotics to be helpful. If we went out and looked for it, we could probably find some less obviously dangerous work where robotics might be an important intervention, not to mention some groups that are disproportionately affected and would benefit from more workplace safety.

Dirty Work: Occupations or tasks that are physically, socially, or morally tainted

Colloquially, most people might think of dirty work as involving physical dirtiness, such as trash removal, cleaning, or dealing with hazardous substances. But social science literature makes clear that dirty work is also about stigma. Socially tainted jobs are often servile or involve interacting with stigmatized groups (for example, correctional officers), and morally tainted jobs include tasks that people commonly perceive as sinful, deceptive, or otherwise defying norms of civility (like a stripper or a collection agent).

“Dirty work” is a social construct that can vary across time (like tattoo industry stigma in the United States) and culture (such as nursing in the U.S. versus in Bangladesh). One way to measure whether work is “dirty” is by using the closely related concept of occupational prestige, captured through quantitative surveys where people rank jobs. Another way to measure it is through qualitative data, like ethnographies and interviews. Similar to “dangerous,” we see some hidden opportunities for robotics in “dirty” work. But one of our more interesting takeaways from the data is that a lower-ranked job can be something that the workers themselves enjoy or find immense pride and meaning in. If we care about what tasks are truly undesirable, understanding this worker perspective is important.

Dull Work: Occupations or tasks that are repetitive and lacking in autonomy

When it comes to defining dull work, what matters most is workers’ own experiences. Outsiders can make a lot of false assumptions about what tasks have value and meaning. Sometimes things that seem boring or routine create the right conditions for developing skills and competence, such as the concentration needed for woodworking, or for socializing and support, when tasks are done alongside others. Instead of assuming that repetitive work is negative, it’s important to examine qualitative data on how people experience the work and what purpose it serves for them.

DDD: An actionable framework

In our paper, we propose a framework to help the robotics community explore how automation impacts individual jobs. For each term—dull, dirty, and dangerous—the framework gathers key pieces of information to reflect on what physical or social aspects of the task are, in fact, DDD. Worker perspective is an important part of all three considerations. The framework also emphasizes awareness of context—meaning the physical and social environment of an occupation and industry that can influence the DDD nature of a task. Our corresponding worksheet suggests existing data sources to draw on and encourages us to seek out multiple perspectives and consider potential sources of bias in the information.

What makes tasks dull, dirty, or dangerous depends on the perspective of the humans doing those tasks.RAI

Let’s take, for example, the waste and recycling industry. The world generates over 2 billion tonnes of waste annually, and this figure is expected to rise to nearly 4 billion tonnes by 2050. Intuitively, trash collection seems like a job that hits all the Ds. Going through our worksheet, we confirm that globally, workers in this industry face significant health hazards (dangerous), and waste collection is ranked as a low-status job (dirty), although interestingly, many workers take pride in providing this essential service.

The job is also repetitive, but there are aspects that make it not dull. Specifically, workers cite the day-to-day interaction with their coworkers (which includes extensive insider vocabulary, work hacks, and mutual aid groups) and task variety as two of the most enjoyable aspects of the job. Task variety includes inspecting their vehicle and equipment, driving their truck, coordinating with crew members, lifting bins and bags, detecting incorrect sorting of waste, and unloading at the end destination.

This finding matters because some types of robotic solutions will eliminate the parts of the job that workers most appreciate. For instance, the National Institute for Occupational Safety and Health (NIOSH) recommends the adoption of automated side loader trucks and collision avoidance systems. This innovation increases safety, which is great, but it also results in a sole worker operating a joystick in a cab, surrounded by sensor and camera surveillance.

Instead, we should challenge ourselves to think of solutions that make jobs safer without making them terrible in a different way. To do this, we need to understand all aspects of what makes a job dull, dirty, or dangerous (or not). Our framework aims to facilitate this understanding.

Finally, it’s important to note that DDD is only one of many possible approaches to classify what work might be better served by robots. There are lots of ways we could think about which types of tasks or jobs to automate (for example, economic impact or environmental sustainability). Given the popularity of DDD in robotics, we chose this common phrase as a starting point. We would love to see more work in this space, whether it’s data collection on DDD itself or the creation of other frameworks.

At RAI, we believe that the fusion of robotics and social sciences opens a whole new world of information, perspectives, opportunities, and value. It fosters a culture of curiosity and mutual learning, and allows us to create actionable tools for anyone in robotics who cares about societal impact.

Dull, Dirty, Dangerous: Understanding the Past, Present, and Future of a Key Motivation for Robotics, by Nozomi Nakajima, Pedro Reynolds-Cuéllar, Caitrin Lynch, and Kate Darling from the RAI Institute, was presented at the 21st ACM/IEEE International Conference on Human-Robot Interaction (HRI) in Edinburgh, Scotland.

This presentation highlights recent efforts at the Johns Hopkins Applied Physics Laboratory to advance agentic AI for collaborative robotic teams. It begins by framing the core challenges of enabling autonomy, coordination, and adaptability across heterogeneous systems, then introduces a scalable architecture designed to support agentic behaviors in multi-robot environments. The talk concludes with key challenges encountered and practical lessons learned from ongoing research and development.

Key learnings

• Provides an introduction to LLM-based AI Agents
• Describes an approach to applying LLM-based AI Agents to robotic teams
• Provides demonstrations of the approach running in hardware with a heterogeneous team of robots
• Presents lessons learned and future work in this area