Get the latest robotics and AI breakthroughs, the limits behind the headlines, and the papers worth your attention. One clear rundown in your inbox each morning.
Hide a red lid under one of three upturned mugs, shuffle them for half a minute, then ask a robot to lift the right one. Researchers at MIT and Harvard gave a general-purpose AI model the controls. The hard part was keeping track of the mug while the model took seconds to answer. A second group tried a different approach on eight physical tasks, including plugging in a charger. Its AI wrote and tested the program before the robot had to perform.
A general-purpose model using measuring tools and a second copy watching the cameras completed 22 of 25 physical tabletop trials. It picked the right mug in five of five shuffles, falling to two of five without the second observer.
Programs written by a coding agent completed 221 of 240 physical trials across eight tasks. People could guide the arms during development. The finished programs ran without the agent or a human operator.
GXO and Apptronik signed a letter of intent that could put up to 1,000 Apollo humanoids in warehouses over four years. The number depends on trials that begin in 2027.
A soft foam car part can bend as a robot tries to fit it into a slot. Mimic Robotics and BMW tested how much time a person had to spend guiding the robot once its software had learned from video. The distinction matters on a factory floor, where each new part or fixture may require another round of demonstrations.
When Simon Cowling dimmed the room around a robot arm, he measured an elevenfold drop in light. Anyone watching through the robot’s front camera would have barely noticed. That gap matters when judging what a robot can do. It also runs through a new exam for robot software, where giving a controller access to information it could never sense on a real machine changed the score.
Changing the shape of a mug or the light on a table can undo hours of robot practice. Two research groups tested different ways to make simulated practice carry over to real objects. A third team measured what a hand gains when it can feel contact. On a factory floor, Google DeepMind and Apptronik put a humanoid to work sorting metal brackets.
Recording a person steering a robot through a task, one attempt at a time, is slow. Much of the newest work asks how little of that a robot needs if it can lean on experience gathered elsewhere: people filmed doing chores, another robot’s recordings, or motion produced by software. NVIDIA’s new model made the largest claim this week. Two smaller studies show where borrowing helps and where it runs out. A third asks how a robot stays quick as the model guiding it grows.
A robot packing cans into a bin bumps something and stops. Does that end the attempt? In an Apple study, the answer changed how often the arm finished the job. Two other teams looked at decisions that come earlier: where to take hold of a chair, and how a robot without a hand can move a box at all.
A small walking robot gets pressed into the ground. A humanoid holds a bag while someone adds weight. In the first experiment, it helps the mechanism to give way. In the second, it helps the robot to push back. This weekend’s reading looks at how both teams got the response they wanted, and what happened when they put it to a physical test.
A cart blocks the way. If it holds an empty bin, a robot might push it aside. If it carries something that could topple, the same push could make a mess. Three studies from this week put navigation to a physical test, from choosing what to touch to following a light that keeps moving.
A robot reaches for a coffee machine and the pod clips the lid. A person can show it a better path, but what should it remember: the exact movement, or the reason for it? Three studies tackle that question from different angles. One teaches a robot when to reuse a correction, another looks for an early warning inside the controller, and a third changes where the robot appears to have been standing during practice.
A robot can learn to sit, grasp or push and still struggle to combine those skills into a useful job. Today's research makes that gap visible: simulated homes teach a humanoid to move through real spaces, touch signals improve contact, and broader practice helps a manipulation model generalize. A distributed physical benchmark adds another lesson: the strongest model depends on what is tested and how it is trained.
Robot progress depends on decisions at very different scales: which demonstrations to collect, when to change direction, and how quickly to pull away from contact. Three new studies connect those decisions to physical tests. In industry, a redesigned unloading robot puts maintenance at the center of its update. The common question is what lets a machine keep working when conditions stop matching the plan.
A robot needs more than a plan. It needs a body that can carry out the movements, sensors that reveal what happens on contact, and a reliable way to recognize whether the job is finished. Today's research tackles all three. Physical tests provide encouraging evidence, while a newly released collection of failed robot attempts shows why the details of evaluation deserve just as much attention as the headline score.
Robots need to make decisions at several speeds: choosing a route through a long task, correcting an arm movement, and responding when their body shifts. Three new papers explore those different problems. A separate industry update asks how a robot should respond when the person giving instructions changes their mind. The evidence ranges from simplified simulations to physical manipulation trials, and those distinctions matter.
Currents disturb a robot's grip. Crowds turn an open route into a moving obstacle course. A cable changes shape as it is handled. The work below examines how robots respond to those conditions, while a proposed industry metric asks how much useful work they actually deliver. Together, these examples show why the setting, the comparison and the definition of success belong beside every headline result.
A robot can copy a hand movement and miss the contact that makes it work. It can finish one step and fail to notice that the result has come undone. Today's research makes those gaps easier to see, with tactile demonstrations, explicit checks during long tasks, and a drawing benchmark that exposes weak instruction following. Outside the lab, residential parking robots face competing requests, while Agility prepares to finance its next stage.
A robot’s abilities depend on more than the model choosing its next movement. Tool design determines what it can feel. A simulator determines what it can learn. Warehouse and laboratory software determine whether its actions fit into useful work. Today’s research and announcements examine those connections, from a touch-sensitive cooking tool to a multiyear distribution-center expansion.
A moving hand, a swinging opening and a returned parcel all challenge the assumption that a robot’s surroundings will stay predictable. Today’s rundown looks at assistance that follows a person, control that anticipates motion, and two industrial projects trying to make flexible automation commercially useful. Each has a different distance left to travel from promising evidence to dependable service.
A robot that misses the last few millimeters needs a different fix from one that never starts moving. Two arms can also execute the right motions at the wrong times. Today’s papers examine these distinct failure modes, while industrial announcements show what it takes to turn autonomous movement and inspection into continuing operations.
A mug briefly touching its plate can count as a successful task—even if the robot immediately lifts it away again. Today’s research examines what happens beyond that first success: maintaining contact force, carrying simulated learning into physical tasks, and checking whether the result holds. In warehouses, GXO’s planned expansion of Digit offers a different test: repeating useful work across more sites.
A useful robot needs to know more than what movement looks right. It needs the command that produces a firm grasp, the force that reveals a stuck handle, and the operating rule that closes an otherwise clear aisle. Today’s papers examine those missing inputs—and show why providing them does not eliminate the need to check the outcome.
A reliable robot needs more than a detailed picture. It must recognize a familiar place after things move, distinguish uncertain ground from safe ground, and understand contact when a hand blocks the view. These studies expose where better sensing helps and where the remaining uncertainty still demands caution.
The next useful robot action often depends on something the camera can no longer see. An object moved, a step was completed, or a flexible thread changed shape during a grasp. Today’s selection explores how robots preserve that context—and how new training facilities and datasets could help them learn decisions as well as movements.
Robots need to recognize what contact means, notice when work has gone off course, and choose movements that fit their surroundings. Three new papers make progress on those problems. On the industry side, Formic’s funding and a robotics integration update show how much of deployment still depends on financing, maintenance and connecting the pieces.
A robot needs more than a plausible next move. It needs to anticipate what contact will do, recover when a task goes wrong, and fit into a system that keeps work moving. Today’s research tackles those problems from three directions, while new industry announcements put more attention on the software and support behind deployment.
What helps a robot learn more efficiently—and what survives outside simulation? Today’s research tests better camera views, a simpler demonstration glove and learned navigation on an industrial mobile robot. The results show useful gains alongside stubborn limits in grasping, reliability and evaluation.
Robots encounter situations their demonstrations did not prepare them for: a folded cloth goes wrong, a pedestrian appears from behind a wall, or a narrow passage demands a change in posture. Three new papers examine ways to handle those moments. Beyond the lab, forestry automation is expanding and a rover has begun its journey toward Phobos.
A robot can find a tight opening through changes in its own motion. Remembering where objects belong can help it restore a room, but picking them up remains difficult. Today’s research also tackles a less visible problem: how long a moving robot should spend planning before it needs fresh feedback.
Robots need to respond to information that changes as they move: pressure at a fingertip, a person blocking the camera, or a pull on an arm. This edition examines three approaches to those problems, with evidence ranging from controlled physical trials to simulation and demonstrations. In construction, Origin is taking a related challenge, maintaining useful contact with a wall, into customer deployments.
A useful robot needs more than a good view of the present. It must remember earlier events, discover physical properties that cameras cannot reveal, and change its response when contact goes wrong. Three research results show progress on those abilities, while a construction robot offers a concrete example of automation already doing repetitive work.
Moving an object is only part of useful robot behavior. A robot also needs to keep it supported, recognize an interaction heading toward failure, and follow instructions about how the job should be done. Today’s papers examine those problems, with evidence ranging from human-guided physical trials to a simulation benchmark for personal preferences.
Reliable robots need more than a good first guess. They need to feel resistance, correct small errors and adapt when their body changes. Three new papers test those abilities on physical hardware. In industry, faster battery replacement and more dependable network connections address two practical reasons autonomous machines stop working.
A robot’s intelligence has to survive contact, delays and changes to its hardware. Today’s research examines all three: using an arm as more than a gripper carrier, keeping reasoning from holding up movement, and measuring how small changes to a robot’s setup affect success. Two commercial announcements show how companies want to make these capabilities easier to access.
Getting a robot to work reliably often means adapting to the place, remembering what has already happened, and learning from the right parts of its experience. This edition examines three approaches to those problems, with physical results that show both useful progress and narrow limits.
A robot can choose a sensible action and still fail because its camera image is stale, an object is misplaced, or the ground beneath it differs from its map. Three new papers examine those everyday sources of unreliability. An Arctic expedition offers a separate look at what specialized robots already make possible outside the lab.
More simulation can give robots broader experience, but the useful question is what survives contact with hardware. This edition looks at choosing better practice, transferring mobile manipulation to real rooms, and preserving humanlike walking without losing control. A live returns-handling deployment and a new world-model preview show where those ideas meet commercial ambition.
A robot can look capable until it meets the awkward object placement, crowded passage or instruction it should refuse. Today’s research examines those difficult cases: directing training toward failures, coordinating movement without giving up a safe stop, and measuring how language models respond to physical hazards. In industry, RobCo sets a commercial launch date while Rockwell focuses on connecting robots to the rest of the factory.
Reliable robots need more than a good destination or a plausible-looking scene. They need to respond when contact changes their motion, model the shapes that can block a path, and know when an otherwise clear route is off limits. Today’s research tackles those practical constraints, alongside a logistics dataset that preserves operational failures and a funded study of assistance for older adults.
A robot can choose the right tool and still fail to use it. A person can spot a mistake and still struggle to take control smoothly. This edition examines those gaps, along with navigation agents that retain useful experience and a new research partnership connecting robotics with logistics. The common question is how promising capabilities hold up through a complete task.
Getting robots into useful service takes several kinds of progress: affordable training data, coordinated movement and hardware that can survive repeated use. Today’s selections connect those problems, from translating human hand motions to monitoring forests. A new simulation announcement also asks how much preparation can happen before a machine reaches its next site.
A useful robot needs to recover when a task goes wrong and avoid collisions with its arms and carried objects, not just its fingertips. Today’s research tests ways to improve both. Industry announcements extend the same practical questions to factory safety systems and future orbital laboratories.
A robot carrying a box with a person needs to give way without losing its grip. A robot learning a complex job needs to practice the steps that actually fail. Today’s research examines both problems, while new industry demonstrations shift attention toward completing whole workflows.
Generated video can broaden what a humanoid learns. Human corrections can improve a trained robot’s weakest skills. A single physical probe can help predict how a material will move. Today’s papers show progress on all three, alongside an audit explaining why impressive benchmark scores need closer inspection.
Human demonstrations can teach coordinated movement. Touch can reveal contact that cameras miss. Failed attempts can guide more useful practice in simulation. Today’s research puts numbers behind all three approaches, while a new industry collaboration asks how to keep robot actions within human-set permissions.
A robot hand can secure an object without seeing it. A humanoid can slow down before a staircase. A manipulation model can learn from future scenes without generating a video for every move. Today’s papers show how these ideas translate into physical demonstrations, with important limits on what the numbers prove.
A robot arm can use its own structure to support a box. A mobile robot can use a camera across the room to plan its route. This weekend’s selections show how those approaches work, where they fail and how much equipment they still need.
Useful robots need more than a successful move. They need time to react, energy to keep working and a way to adapt a task to a different scene. This weekend’s research selections examine those constraints. A spacecraft mission also shows how a hardware fault can exhaust the resources needed to finish the job.
A slight calibration error, a slipping tool or a foothold disappearing from view can undo an otherwise capable robot. Today’s research tests ways to handle those problems. Deployment announcements from a theme park and university campuses show where robots are meeting people, while a recovery benchmark asks what happens after a task goes wrong.
A human correction can teach a robot more than a movement to copy. Today’s papers explore how to use that feedback, fit unfamiliar parts together, and cross from land into water with one enclosed mechanism. A new benchmark also tests how closely simulated performance follows what a physical robot can do.
A robot’s reliability depends on more than recognizing the next task. It needs useful training data, control that adapts to changing terrain, and a way to recover before a mistake becomes damage. Today’s research tackles those problems, while new software releases and a major camera acquisition could shape the tools behind future deployments.
A robot can struggle before training even starts: the human teaching it may find the task hard to demonstrate. Today’s papers tackle that problem, predict what fingers will feel, and transfer simulated assembly skills to physical hardware. Industry updates show where those skills could meet factory and retail work.
A useful robot has to choose a good next move, apply enough force, and leave room to finish the job. Today’s papers test those decisions on real hardware and in simulation. A new warehouse announcement adds a named customer site, while leaving the robot’s sustained productivity an open question.
Rough trails, thin obstacles, buried roots, and bubbles all change what a robot needs to understand. Today’s research shows how those details shape performance, from predicting a rough ride to learning underwater manipulation. Faraday Future’s latest launch also puts the gap between product availability and dependable field performance in focus.
A robot needs to know when a step is finished, how an object will move, and whether its predictions match reality. This weekend’s catch-up looks at those gaps through three recent studies, a precision optics lab, and a robot built for fast physical interaction.
A robot can succeed in training and struggle when the parts, surroundings, or task history change. Today’s research tests ways to close that gap, from simulated construction work to navigation lessons collected with a walker. Figure also reports household trials that put humanoid generalization to a concrete test.
Peeling a cucumber and picking a ripe berry both require careful contact. Today’s research tests how robots sense pressure, handle delicate objects, and reuse computation during repetitive work. A portable rescue robot and new funding for robot chips show two other routes toward machines that work beyond the lab.
A robot reaching for a moving bottle needs to know where it is going. Today’s research tests how recent motion and predictions of the future improve robot actions. There is also a new humanoid announcement, with a useful distinction between demonstrated performance and the capabilities still under development.
A useful robot needs to remember what happened, stay upright when conditions change, and feel objects slipping through its fingers. Today’s papers test those abilities on physical machines. An industrial robot launch and a new dexterity benchmark show how the supporting hardware and evaluation tools are developing.
An excavator shapes a full-size embankment, while a robot hand uses touch to handle small objects. Another controller keeps working when its camera view changes. Today’s research shows where learned skills survive physical tests, and where narrow trials still leave open questions.
Human videos can teach robots useful movements, but the details still matter: what to avoid, which object to move, and when to stop. Today’s papers test those questions with converted video, greenhouse experiments, and a memory-guided controller. Industry updates show how the same challenges reach factory floors and warehouse fleets.
A humanoid keeps walking through partial camera failure. A ground robot borrows a drone’s view above tall grass. From failure detection to factory welding, today’s developments test how robots handle imperfect conditions.
A robot hand starts writing after 18 seconds of calibration, and a shared exoskeleton speeds up human demonstrations. A new action model cuts the pauses between robot movements. Today’s research tackles the time it takes to teach and run useful skills, while industry announcements put the focus on factory work and delivery.
A folded shirt can look wrong even when a robot finishes the task. Sand can give way under a perfectly planned step. Today’s research puts those physical details into robot training and evaluation, while new deployments show how automation reaches existing workplaces.
A clear path on a floor plan can still leave a robot's shoulders stuck. Today's research examines how robots fit through clutter, turn camera views into useful motion, and capture the touch signals behind skilled hand movements. New industry announcements show where those ideas could meet practical deployment.
Get a closer look at what helps robots finish delicate tasks, hand objects over smoothly, and act without extra reasoning overhead. Then see what the latest manufacturing and industry announcements actually establish.
