Teaching a robot new skills used to require coding expertise. But a new generation of robots could potentially learn from just about anyone.

Engineers are designing robotic helpers that can “learn from demonstration.” This more natural training strategy enables a person to lead a robot through a task, typically in one of three ways: via remote control, such as operating a joystick to remotely maneuver a robot; by physically moving the robot through the motions; or by performing the task themselves while the robot watches and mimics.

Learning-by-doing robots usually train in just one of these three demonstration approaches. But MIT engineers have now developed a three-in-one training interface that allows a robot to learn a task through any of the three training methods. The interface is in the form of a handheld, sensor-equipped tool that can attach to many common collaborative robotic arms. A person can use the attachment to teach a robot to carry out a task by remotely controlling the robot, physically manipulating it, or demonstrating the task themselves — whichever style they prefer or best suits the task at hand.

The MIT team tested the new tool, which they call a “versatile demonstration interface,” on a standard collaborative robotic arm. Volunteers with manufacturing expertise used the interface to perform two manual tasks that are commonly carried out on factory floors.

The researchers say the new interface offers increased training flexibility that could expand the type of users and “teachers” who interact with robots. It may also enable robots to learn a wider set of skills. For instance, a person could remotely train a robot to handle toxic substances, while further down the production line another person could physically move the robot through the motions of boxing up a product, and at the end of the line, someone else could use the attachment to draw a company logo as the robot watches and learns to do the same.

“We are trying to create highly intelligent and skilled teammates that can effectively work with humans to get complex work done,” says Mike Hagenow, a postdoc at MIT in the Department of Aeronautics and Astronautics. “We believe flexible demonstration tools can help far beyond the manufacturing floor, in other domains where we hope to see increased robot adoption, such as home or caregiving settings.”

Hagenow will present a paper detailing the new interface, at the IEEE Intelligent Robots and Systems (IROS) conference in October. The paper’s MIT co-authors are Dimosthenis Kontogiorgos, a postdoc at the MIT Computer Science and Artificial Intelligence Lab (CSAIL); Yanwei Wang PhD ’25, who recently earned a doctorate in electrical engineering and computer science; and Julie Shah, MIT professor and head of the Department of Aeronautics and Astronautics.

Training together

Shah’s group at MIT designs robots that can work alongside humans in the workplace, in hospitals, and at home. A main focus of her research is developing systems that enable people to teach robots new tasks or skills “on the job,” as it were. Such systems would, for instance, help a factory floor worker quickly and naturally adjust a robot’s maneuvers to improve its task in the moment, rather than pausing to reprogram the robot’s software from scratch — a skill that a worker may not necessarily have.

The team’s new work builds on an emerging strategy in robot learning called “learning from demonstration,” or LfD, in which robots are designed to be trained in more natural, intuitive ways. In looking through the LfD literature, Hagenow and Shah found LfD training methods developed so far fall generally into the three main categories of teleoperation, kinesthetic training, and natural teaching.

One training method may work better than the other two for a particular person or task. Shah and Hagenow wondered whether they could design a tool that combines all three methods to enable a robot to learn more tasks from more people.

“If we could bring together these three different ways someone might want to interact with a robot, it may bring benefits for different tasks and different people,” Hagenow says.

Tasks at hand

With that goal in mind, the team engineered a new versatile demonstration interface (VDI). The interface is a handheld attachment that can fit onto the arm of a typical collaborative robotic arm. The attachment is equipped with a camera and markers that track the tool’s position and movements over time, along with force sensors to measure the amount of pressure applied during a given task.

When the interface is attached to a robot, the entire robot can be controlled remotely, and the interface’s camera records the robot’s movements, which the robot can use as training data to learn the task on its own. Similarly, a person can physically move the robot through a task, with the interface attached. The VDI can also be detached and physically held by a person to perform the desired task. The camera records the VDI’s motions, which the robot can also use to mimic the task when the VBI is reattached.

To test the attachment’s usability, the team brought the interface, along with a collaborative robotic arm, to a local innovation center where manufacturing experts learn about and test technology that can improve factory-floor processes. The researchers set up an experiment where they asked volunteers at the center to use the robot and all three of the interface’s training methods to complete two common manufacturing tasks: press-fitting and molding. In press-fitting, the user trained the robot to press and fit pegs into holes, similar to many fastening tasks. For molding, a volunteer trained the robot to push and roll a rubbery, dough-like substance evenly around the surface of a center rod, similar to some thermomolding tasks.

For each of the two tasks, the volunteers were asked to use each of the three training methods, first teleoperating the robot using a joystick, then kinesthetically manipulating the robot, and finally, detaching the robot’s attachment and using it to “naturally” perform the task as the robot recorded the attachment’s force and movements.

The researchers found the volunteers generally preferred the natural method over teleoperation and kinesthetic training. The users, who were all experts in manufacturing, did offer scenarios in which each method might have advantages over the others. Teleoperation, for instance, may be preferable in training a robot to handle hazardous or toxic substances. Kinesthetic training could help workers adjust the positioning of a robot that is tasked with moving heavy packages. And natural teaching could be beneficial in demonstrating tasks that involve delicate and precise maneuvers.

“We imagine using our demonstration interface in flexible manufacturing environments where one robot might assist across a range of tasks that benefit from specific types of demonstrations,” says Hagenow, who plans to refine the attachment’s design based on user feedback and will use the new design to test robot learning. “We view this study as demonstrating how greater flexibility in collaborative robots can be achieved through interfaces that expand the ways that end-users interact with robots during teaching.”

This work was supported, in part, by the MIT Postdoctoral Fellowship Program for Engineering Excellence and the Wallenberg Foundation Postdoctoral Research Fellowship.

There’s nothing new about managing change. But the pace, complexity, and consequences of change are evolving in today’s workplace.  

Most organizations aren’t just managing change; they’re navigating major transformations to keep up with mergers, reorgs, new tech, retiring execs, and global instability. 

According to Gartner, half of all major change initiatives fail, and only 34% are considered a clear success. 

And it’s not just the logistics that get tricky—it’s the people part. 

We recently hosted an AMA (Ask Me Anything) with two of our in-house experts: Anne Maltese, VP of People Insights, and Rachel Hudson, Senior Insights Analyst.  

They pulled back the curtain on what it really takes to lead through change and how to build belief, not just compliance. 

Here’s what we learned: 

📺 Want to watch the full recording? Click here! >> 

What are effective ways to gather employee input during times of disruption? 

Many organizations hesitate to launch engagement surveys or gather feedback in the middle of a change. But that’s when listening matters most. 

“We would actually encourage organizations to go through with that survey because it generates such important insights and intelligence that can help navigate through change,” said Anne.  

She emphasized that feedback is intelligence, not just a performance metric. By collecting open-ended responses and asking targeted questions about how employees are experiencing change, you can uncover actionable insights before challenges become barriers. 

Pulse surveys are especially useful throughout a change timeline: 

Before the change: Are employees clear on what’s happening and why? 

During the change: Where are the pain points coming up? 

After the change: Is there renewed confidence in the future? 

“The timing of communication affects how employees perceive the change overall,” noted Rachel. “It also affects their own engagement and their desire to remain at their current organization.” 

How do you collect feedback during change without creating confusion or slowing momentum? 

Some leaders worry that gathering input mid-change will stir anxiety or slow things down. But the experts argued that not listening creates bigger issues. 

“Change is an opportunity for us to recenter our values, our purpose,” said Rachel. “It’s a chance for us to navigate through uncertainty by relying on some of those elements of our culture.” 

She shared a story about a public accounting firm undergoing rapid M&A growth. Rather than delay listening efforts, the company created an M&A pulse framework: short surveys on day 1, day 30, day 60, and day 90 for new employees. It revealed gaps in support, surfaced cultural mismatches, and helped refine onboarding processes across future acquisitions. 

“It does not take those employees very long to complete those short pulse surveys, but it’s become an invaluable tool for leaders,” said Rachel. 

What’s the best way to get managers bought into change—especially if past efforts have failed?

No change initiative can succeed without managers. But they’re often overwhelmed, skeptical, or burned out from previous changes that didn’t go well. 

“The manager’s job is hard and it’s probably harder than it ever has been,” said Anne. “Have empathy around that—because when we roll out change, it feels like there’s one more thing being added to their plate.”

That means: 

• Acknowledging the emotional toll of change 

• Explaining not just what’s changing, but why 

• Helping managers connect the dots for their teams 

• Equipping them with talking points, tools, and support 
  

“Create belief so managers are bought in and excited about where they may go, even though it is probably going to impact their team and disrupt it. And then, equip them with the tools to succeed through it,” said Anne. 

Rachel added that listening to managers early in the process can surface friction before it spreads. In one example, a firm saw that belief in the change dropped sharply between executives and mid-level leaders. That insight helped them focus their communication and coaching on where it was most needed. 

🔍 Read more about how to redirect disruption into belief and positive momentum in our 2025 HR Trends Report >> 

How do you create clarity and belief around change?

Even when the change is strategic, it can feel personal. And when people don’t understand what’s happening or how it affects them, they fill in the blanks with fear or skepticism. That’s why it’s critical to pivot disruption into belief.

“If everything around us is changing so quickly, is the way that we operate as a team keeping up with that?” Anne asked. 

Building belief starts with clear communication, specifically a few key questions: 

• Why is this change happening? 

• How does this impact me? 

• What support is available? 

When employees understand the reason for change and their role in it, they’re far more likely to move through it with resilience, not resistance. 

What’s the biggest barrier to successful change? 

“We have to listen to our employees to understand if they’re truly bought into the change or not,” said Rachel, “We’ve got to continue listening to understand what their challenges are.” 

Creating an open, two-way feedback loop is the key to navigating change and creating belief. Here’s how to make that happen: 

✔️ Acknowledge feedback and thank employees for sharing 
✔️ Act on what you hear—or explain why you’re not 
✔️ Share what’s changing and how feedback influenced decisions 
✔️ Repeat the cycle to build long-term trust 

Final Advice? 

“We have to get comfortable with not having a GPS for navigating change, but rather having a well-thought-out vision, confidence, and a plan along the way that’s agile,” said Anne. 

Don’t wait for the perfect plan. Instead, start where you are and listen, provide clarity, and believe in it. 

And above all, believe in your people’s ability to navigate what’s next with the right support behind them. 

Want to go deeper?

📈 Explore the 2025 Workplace Trends Report >> 

💡Check out our pulse survey software >>

💬 See how our Feedback tool works >>

📺 Watch the full AMA ⬇️

Let’s face it, laundry isn’t exactly thrilling. What if it could be easier, faster, and actually kind of satisfying?  With SmartThings, your Samsung washer and dryer get a serious upgrade. From real-time updates to remote control and energy savings, SmartThings makes laundry day feel less like a chore and more like a life hack.

Stay Connected to Every Load

SmartThings has your back (and basket), whether you’re on the couch or running errands, SmartThings keeps you in the loop. Get real-time notifications when a cycle starts, pauses, or finishes, so you’re never left wondering if the laundry’s done. If a load needs attention (like when it’s been sitting too long after drying), SmartThings will send you a gentle nudge before your clothes go from fresh to funky. It’s like having a laundry buddy who never forgets!

Customize Cycles to Fit Your Needs

Forget digging through manuals or pressing buttons at random. SmartThings makes it easy to tailor your washer and dryer settings, helping you choose the perfect cycle based on your load type, size, and fabric. Beyond choosing the temperature and spin intensity, select optimized cycles directly in the app based on your fabric type, load size, or soil level.

Here are just a few examples of features and cycles:

• Activewear: Designed for jersey and moisture-wicking gym clothes
• Bedding: Designed for bulky sheets and comforters
• Baby Care: Gently sanitize clothes at a high temperature
• Fabric Specific Cycles: Wool, Denim, Delicates, a custom cycle based on the fabrics within
• Wrinkle Prevent: Optional setting to keep clothes wrinkle-free for up to three hours
• Damp Alert: Be notified for the optimal time to iron clothes right out of the dryer
• Eco-modes: Energy-saving mode that balances performance and efficiency
• Unemptied Laundry Alerts: We all forget clothes sometimes, but now you can be reminded up to 24 hours to remove your clothes from the washer or take them out for folding
• Sensor Dry: Automatically adjusts time based on moisture levels

You can even save your combinations, so your go-to routines are ready with one tap.

Prevent and Diagnose Issues Before They Disrupt Your Day

Your washer and dryer are smart, and with SmartThings, they practically think for themselves.  SmartThings makes troubleshooting easy, becoming a proactive experience. Not only can you select maintenance modes to help keep your washer and dryer clean, but SmartThings can also alert you to performance issues and guide you through self-diagnosis steps, often before you even realize there’s a problem. This helps prevent breakdowns and saves you time (and service calls).

Control Laundry From Anywhere, Anytime

Running late? Mid-binge watch on your favorite show? Cozy in bed? No problem.  Start, stop, or monitor your washer and dryer directly from your phone, and even schedule cycles to run when energy rates are lower or it’s simply more convenient. It’s smarter laundry on your terms, saving time, energy, and hassle.

Built-In Intelligence

SmartThings doesn’t just connect your appliances, it helps them work smarter together. For example, it can recommend optimal drying settings based on the type of wash cycle you just completed. Washed a load with Heavy Duty mode? SmartThings will recommend the best dryer settings to match. The result? Better fabric care and less guesswork.

It’s time to bring smarter care to your clothes—and a little more free time back in your day. Download the SmartThings app and connect your Samsung washer and dryer to unlock the full potential of your laundry room.

When ChatGPT or Gemini give what seems to be an expert response to your burning questions, you may not realize how much information it relies on to give that reply. Like other popular generative artificial intelligence (AI) models, these chatbots rely on backbone systems called foundation models that train on billions, or even trillions, of data points.

In a similar vein, engineers are hoping to build foundation models that train a range of robots on new skills like picking up, moving, and putting down objects in places like homes and factories. The problem is that it’s difficult to collect and transfer instructional data across robotic systems. You could teach your system by teleoperating the hardware step-by-step using technology like virtual reality (VR), but that can be time-consuming. Training on videos from the internet is less instructive, since the clips don’t provide a step-by-step, specialized task walk-through for particular robots.

A simulation-driven approach called “PhysicsGen” from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Robotics and AI Institute customizes robot training data to help robots find the most efficient movements for a task. The system can multiply a few dozen VR demonstrations into nearly 3,000 simulations per machine. These high-quality instructions are then mapped to the precise configurations of mechanical companions like robotic arms and hands. 

PhysicsGen creates data that generalize to specific robots and condition via a three-step process. First, a VR headset tracks how humans manipulate objects like blocks using their hands. These interactions are mapped in a 3D physics simulator at the same time, visualizing the key points of our hands as small spheres that mirror our gestures. For example, if you flipped a toy over, you’d see 3D shapes representing different parts of your hands rotating a virtual version of that object.

The pipeline then remaps these points to a 3D model of the setup of a specific machine (like a robotic arm), moving them to the precise “joints” where a system twists and turns. Finally, PhysicsGen uses trajectory optimization — essentially simulating the most efficient motions to complete a task — so the robot knows the best ways to do things like repositioning a box.

Each simulation is a detailed training data point that walks a robot through potential ways to handle objects. When implemented into a policy (or the action plan that the robot follows), the machine has a variety of ways to approach a task, and can try out different motions if one doesn’t work.

“We’re creating robot-specific data without needing humans to re-record specialized demonstrations for each machine,” says Lujie Yang, an MIT PhD student in electrical engineering and computer science and CSAIL affiliate who is the lead author of a new paper introducing the project. “We’re scaling up the data in an autonomous and efficient way, making task instructions useful to a wider range of machines.”

Generating so many instructional trajectories for robots could eventually help engineers build a massive dataset to guide machines like robotic arms and dexterous hands. For example, the pipeline might help two robotic arms collaborate on picking up warehouse items and placing them in the right boxes for deliveries. The system may also guide two robots to work together in a household on tasks like putting away cups.

PhysicsGen’s potential also extends to converting data designed for older robots or different environments into useful instructions for new machines. “Despite being collected for a specific type of robot, we can revive these prior datasets to make them more generally useful,” adds Yang.

Addition by multiplication

PhysicsGen turned just 24 human demonstrations into thousands of simulated ones, helping both digital and real-world robots reorient objects.

Yang and her colleagues first tested their pipeline in a virtual experiment where a floating robotic hand needed to rotate a block into a target position. The digital robot executed the task at a rate of 81 percent accuracy by training on PhysicGen’s massive dataset, a 60 percent improvement from a baseline that only learned from human demonstrations.

The researchers also found that PhysicsGen could improve how virtual robotic arms collaborate to manipulate objects. Their system created extra training data that helped two pairs of robots successfully accomplish tasks as much as 30 percent more often than a purely human-taught baseline.

In an experiment with a pair of real-world robotic arms, the researchers observed similar improvements as the machines teamed up to flip a large box into its designated position. When the robots deviated from the intended trajectory or mishandled the object, they were able to recover mid-task by referencing alternative trajectories from their library of instructional data.

Senior author Russ Tedrake, who is the Toyota Professor of Electrical Engineering and Computer Science, Aeronautics and Astronautics, and Mechanical Engineering at MIT, adds that this imitation-guided data generation technique combines the strengths of human demonstration with the power of robot motion planning algorithms.

“Even a single demonstration from a human can make the motion planning problem much easier,” says Tedrake, who is also a senior vice president of large behavior models at the Toyota Research Institute and CSAIL principal investigator. “In the future, perhaps the foundation models will be able to provide this information, and this type of data generation technique will provide a type of post-training recipe for that model.”

The future of PhysicsGen

Soon, PhysicsGen may be extended to a new frontier: diversifying the tasks a machine can execute.

“We’d like to use PhysicsGen to teach a robot to pour water when it’s only been trained to put away dishes, for example,” says Yang. “Our pipeline doesn’t just generate dynamically feasible motions for familiar tasks; it also has the potential of creating a diverse library of physical interactions that we believe can serve as building blocks for accomplishing entirely new tasks a human hasn’t demonstrated.”

Creating lots of widely applicable training data may eventually help build a foundation model for robots, though MIT researchers caution that this is a somewhat distant goal. The CSAIL-led team is investigating how PhysicsGen can harness vast, unstructured resources — like internet videos — as seeds for simulation. The goal: transform everyday visual content into rich, robot-ready data that could teach machines to perform tasks no one explicitly showed them.

Yang and her colleagues also aim to make PhysicsGen even more useful for robots with diverse shapes and configurations in the future. To make that happen, they plan to leverage datasets with demonstrations of real robots, capturing how robotic joints move instead of human ones.

The researchers also plan to incorporate reinforcement learning, where an AI system learns by trial and error, to make PhysicsGen expand its dataset beyond human-provided examples. They may augment their pipeline with advanced perception techniques to help a robot perceive and interpret their environment visually, allowing the machine to analyze and adapt to the complexities of the physical world.

For now, PhysicsGen shows how AI can help us teach different robots to manipulate objects within the same category, particularly rigid ones. The pipeline may soon help robots find the best ways to handle soft items (like fruits) and deformable ones (like clay), but those interactions aren’t easy to simulate yet.

Yang and Tedrake wrote the paper with two CSAIL colleagues: co-lead author and MIT PhD student Hyung Ju “Terry” Suh SM ’22 and MIT PhD student Bernhard Paus Græsdal. Robotics and AI Institute researchers Tong Zhao ’22, MEng ’23, Tarik Kelestemur, Jiuguang Wang, and Tao Pang PhD ’23 are also authors. Their work was supported by the Robotics and AI Institute and Amazon.

The researchers recently presented their work at the Robotics: Science and Systems conference.