Zip Robotic

Category: Humanoids

Humanoid robots are the most watched and least proven category in robotics. This is where we track the machines built in roughly human shape — Atlas, Digit, Optimus, Figure, UBTECH’s Walker line and the fast-moving Chinese challengers — and, more importantly, what they are actually being asked to do. Most humanoid deployments today are parts logistics, sequencing and tote handling: repetitive work that demands two hands and awkward grasps but never touches a moving assembly line. The gap between that and full component assembly is where the real engineering story lives. We report the specifics — payload, runtime, charge ratio, unit counts, factory capacity, order books — and we flag the difference between a stated production target and a robot doing paid work. Expect coverage of training methods (teleoperation, reinforcement learning in simulation, human demonstration capture), the data-flywheel claims every programme now makes, and the throughput question almost nobody answers: how many hours of demonstration produce one reliably autonomous task.

  • Robotics Recap: CSIRO Seagrass USV, Korea Clears Humanoids, Gemini Teaches Apollo and Symbotic Buys cellumation

    Robotics Recap: CSIRO Seagrass USV, Korea Clears Humanoids, Gemini Teaches Apollo and Symbotic Buys cellumation

    By Zip Robotic · October 14, 2026

    Four stories from October 11–13, one theme: robots under murky water, on shipyard floors, learning from video, and buying European sortation. CSIRO and partners are towing a camera vehicle behind an uncrewed boat to map seagrass where divers and clear water fail. South Korea cleared 20 Robros bipedal humanoids for live factory tests beside workers, including a Hyundai shipyard. Google DeepMind’s Gemini 4 Argon watched a human play cornhole, wrote its own sim, and put seven straight shots on Apptronik’s Apollo. And Symbotic bought Bremen’s cellumation for the celluveyor sortation deck. Here is what happened and why it matters.

    CSIRO tows a camera under murky water for seagrass

    CSIRO published a partner release on October 13 on trials of a towed underwater vehicle with CQUniversity’s Coastal Marine Ecosystems Research Centre and the Great Barrier Reef Foundation. The tethered system is built to collect high-definition imagery and environmental data just above the seabed in turbid coastal water, where traditional survey methods struggle.

    CSIRO Principal Research Engineer Dr Torsten Merz describes a robotic pair: an uncrewed surface vessel and a towed underwater vehicle. Images are recorded and processed on board the USV and sent to users by radio link; AI-generated analysis is meant to speed seagrass monitoring and assessment. CMERC Director Professor Emma Jackson said researchers can position the camera just above the seabed and tow it over long distances while collecting georeferenced imagery and data. Field work includes Gladstone deployments. In intertidal areas, the TUV can be paired with aerial drone surveys for ground-truthing without walking long distances across sensitive habitat. A final project report is expected later this year. Scaling SeaGrow funding comes from the Australian Government’s Reef Trust and the Great Barrier Reef Foundation.

    Why it matters: Marine science still loses coverage in brown water. A USV that tows eyes along the seabed is a practical autonomy story—restoration and carbon-storing meadows, not just warships.

    Korea clears 20 Robros humanoids for factory floors next to people

    Seoul Economic Daily reported on October 13 that South Korea’s Ministry of Trade, Industry and Energy granted a regulatory sandbox testing exemption to Robros after the sixth Industrial Convergence Regulatory Sandbox Review Committee meeting of 2026. Twenty AI-equipped bipedal humanoids will work at Nepes, Sungwoo Hitech, HD Hyundai Samho and Delivery Lab, in spaces shared with or adjacent to human workers.

    Task mix: cleaning contaminants from circular semiconductor packaging components at Nepes; positioning auto body parts at Sungwoo Hitech; stacking scaffolding brackets that secure elevated work platforms to a ship’s hull at HD Hyundai Samho; moving refrigerated logistics packaging at Delivery Lab. Safety rules written for fenced, stationary industrial robots did not fit mobile humanoids. The government approved the test on the condition that Employment and Labor risk assessments and risk-reduction measures are carried out; the data is meant to inform new safety standards for wider industrial adoption. Trade Minister Kim Jung-kwan said regulation struggles to keep up with AI and that institutional bottlenecks need to come down fast.

    Why it matters: This is a live regulatory path for humanoids sharing floors with people—and one of the four sites is a shipyard stacking hull scaffolding. That is manufacturing autonomy with a marine-adjacent footprint.

    Gemini 4 Argon teaches Apollo cornhole from one video

    Google launched Gemini 4 Argon on October 13. In the same post, Google says Argon scores 87% on the Embodied Reasoning (ERQA) benchmark using pure reasoning. To show robotics skill transfer, Google describes an internal test: Argon watched a raw video of a human playing cornhole, mapped the environment’s spatial coordinates, calculated the whole-body joint movements required, autonomously built the simulation code, and transferred the behavior to Apptronik’s Apollo humanoid. In a real-world trial, Apollo sank seven consecutive shots. Google calls the pipeline “Video-to-Sim-to-Real” and says it can compress weeks of manual simulation modeling into a few hours. A companion Google Developers Blog post the same day walks through Argon workflows across robot control, Real2Sim, physical understanding and self-improvement.

    Why it matters: If ordinary video becomes a training ground because the model writes the sim itself, the long tail of robot skills stops needing a hand-built world for every new task.

    Symbotic buys cellumation and the celluveyor

    Symbotic Inc. announced on October 13 that it has acquired cellumation GmbH of Bremen, Germany, creator of the celluveyor—a patented, software-driven sortation platform. The celluveyor is made of hundreds of independently controlled omnidirectional cells; each cell can move an item in any direction, so the surface decides where products should go while moving them. Symbotic says the tech can deliver more throughput and handle a wider product mix in a fraction of the space traditional conveyors need, and that it is a key enabler for denser inbound and outbound robotic cells.

    cellumation will keep its name and Bremen headquarters, serving its existing global customers while Symbotic accelerates European expansion. Co-founders Dr.-Ing. Hendrik Thamer (CEO) and Dr.-Ing. Claudio Uriarte (CTO) remain with the company. Symbotic Chairman and CEO Rick Cohen tied the deal to prior acquisitions of ARMS Innovations and Fox Robotics and said celluveyor will be sold both as a standalone product and integrated into Symbotic systems. Financial terms were not disclosed.

    Why it matters: A major U.S. warehouse robotics public company is buying European omnidirectional sortation hardware—and keeping the Bremen team as a product company, not just an IP tuck-in.

    The takeaway

    Strip the press language and the stretch says this: under turbid water, a USV+TUV stack is trying to see seagrass at scale; on Korean factory and shipyard floors, regulators just opened a shared-space humanoid trial; in the lab, a frontier model wrote its own sim from a backyard game video and put shots on a humanoid; in the warehouse, Symbotic paid for a denser sortation deck out of Bremen. Watch for CSIRO’s year-end TUV performance report, how Korea’s sandbox data rewrites robot safety rules, whether Video-to-Sim-to-Real shows up outside demo sports, and how fast celluveyor lands inside Symbotic cells versus staying a standalone European product.

    Sources

  • Agility Robotics Clears SEC Step Toward Nasdaq Listing as “AGLT”; Shareholder Vote Set for Nov. 2

    Agility Robotics Clears SEC Step Toward Nasdaq Listing as “AGLT”; Shareholder Vote Set for Nov. 2

    Agility Robotics Digit humanoid holding a grey tote
    Agility’s Digit humanoid. Photo: Agility Robotics press materials

    SALEM, Ore. — Agility Robotics, the maker of the Digit humanoid robot, said the SEC declared effective on Oct. 13 the Form S-4 registration statement it filed jointly with Churchill Capital Corp XI (Nasdaq: CCXI). That clears the way for a shareholder vote on their merger.

    The deal in numbers
    Nov. 2, 2026 Churchill XI extraordinary general meeting to vote on the merger (record date Sept. 14)
    AGLT Expected Nasdaq ticker after closing; close expected November 2026
    $620M+ Expected gross proceeds, assuming no redemptions
    ~$424M Cash in Churchill XI’s trust account
    ~$200M Common-stock PIPE led by Foxconn
    $300M+ Committed Digit 5 orders, subject to contractual milestones and specs

    What Agility brings to market

    • 65,000+ hours of real-world operation for earlier Digit generations.
    • Up to 10,000 robots a year: the stated design capacity of its RoboFab factory in Salem, Ore.
    • 9 committed customer facility deployments today, with a goal of up to 25 by year-end 2027.
    • Digit 5 early-access availability targeted for early 2027.
    Agility Robotics Digit humanoid robot, front view
    Digit, front view. Photo: Agility Robotics press materials

    Who’s using it

    Named customers include Schaeffler, GXO and Toyota Motor Manufacturing Canada, which signed a Robot-as-a-Service deal after a pilot. Strategic backers listed by the company include DCVC, NVIDIA, SoftBank Vision Fund 2, Schaeffler, Foxconn, Abico and Playground Global.

    Illustration of a generic humanoid robot carrying a tote in a warehouse
    Tote-moving in logistics is the classic humanoid job. Illustration: Zip Robotic (generic robot, not Digit)

    Agility says the combined company would be the only U.S.-listed pure-play humanoid company with proven, active commercial deployments. (Company claim.)

    What could still change

    The deal still needs Churchill XI shareholder approval and other customary closing conditions. Shareholder redemptions could reduce the cash raised.

    Agility Robotics logo
    Logo: Agility Robotics press materials

    Source: Agility Robotics press release, Oct. 13, 2026

  • Boston Dynamics Opens Atlas Training Plant in Georgia Ahead of 25,000-Robot Hyundai Rollout

    Boston Dynamics Opens Atlas Training Plant in Georgia Ahead of 25,000-Robot Hyundai Rollout

    SAVANNAH, Ga. — Boston Dynamics has opened the Robotics Metaplant Application Center, a permanent Atlas training facility inside Hyundai Motor Group’s Metaplant America campus in Georgia. The company announced the opening on 21 September, describing the site as the proving ground for a deployment that Hyundai has said will eventually put 25,000 Atlas humanoids to work across Hyundai Motor and Kia plants worldwide.

    Why it matters: a factory that manufactures robot behaviour

    RMAC is not a production line. Boston Dynamics calls it a “Robot Behavior Factory” — real automotive parts, real fixtures and real workcells, staffed by operators whose job is to generate training data rather than vehicles. Atlas learns there by three routes: teleoperation, reinforcement learning in simulation, and handheld Universal Manipulation Interface devices that capture human demonstrations without a robot in the loop.

    The first tasks are deliberately unglamorous. Atlas is being trained on parts logistics and sequencing — picking components and placing them in assembly order — work that demands bimanual handling and awkward grasps but does not touch the moving line. Boston Dynamics has said component assembly itself is a 2030 target, and that it will begin exploring aerospace, semiconductor, logistics, food and beverage and life-sciences use cases in 2027.

    The numbers behind it are the real signal. A second RMAC building launching next year will expand capacity roughly tenfold. A planned U.S. manufacturing facility is sized to build up to 30,000 robots a year. Boston Dynamics is relocating staff from its Waltham, Massachusetts headquarters to Savannah and hiring locally, while separately planning a $100 million Waltham expansion that the company projects will add 1,250 jobs by 2033. Taken together, that is a company building the supply chain for a humanoid fleet before the fleet has a proven job.

    “Together with Hyundai Motor Group, we are pioneering physical AI at enterprise scale… RMAC reinforces our shared ambition to create a future where robots amplify human potential by making work safer and more productive.”

    Zack Jackowski, Chief Product & Technology Officer, Boston Dynamics

    The open question is throughput. Every humanoid programme now claims a data flywheel; almost none has published how many hours of collected demonstration translate into one reliably autonomous task. RMAC is Boston Dynamics’ answer to that question, and it will be judged on how quickly Atlas moves from sequencing bins to touching the line.

    Sources

  • Agility Unveils Digit 5 With 50-Pound Lift and a $300 Million Order Book

    Agility Unveils Digit 5 With 50-Pound Lift and a $300 Million Order Book

    SALEM, Ore. — Agility Robotics has unveiled Digit 5, the fifth generation of its industrial humanoid, with a 40% payload increase to 50 lb (22.7 kg), reach extended to 7.2 feet, and a 90-minute battery that recharges in 9 minutes. That 10:1 run-to-charge ratio is the headline engineering claim: Agility says it yields more than 20 hours of work per 24-hour day.

    The order book and the income statement

    Agility says it holds more than $300 million in multi-year customer orders as of May 2026, including one commitment for 1,000 robots over three years. Against that, the company reported $1.78 million in net sales for 2025 and an operating loss of $140.2 million. The gap between a signed order book and recognised revenue is the central number in humanoid robotics right now, and Digit 5 is the machine meant to close it. Early access begins in the first half of 2027, with general availability by the end of 2027 across North America, the EU and the UK.

    The hardware changes are aimed squarely at that transition. Digit 4’s backwards “ostrich” legs are gone, replaced with human-like knees and proprietary cycloidal actuators built for heavy lifting. The robot weighs 284 lb and stands 5 feet 11 inches. End-effectors are now swappable on ISO-standard flanges.

    The more consequential change is safety. Agility says Digit 5 is the first humanoid to pass an independent OSHA field evaluation, and the company contributed to ANSI/A3 TR R15.108 and ISO 25785-1, the first international safety standard for humanoids. A separate safety controller and 360-degree human detection let the robot steer around people, stop, or sit down, with visual and audio cues signalling intent. In practice that means working without a cage — which is what actually determines whether a humanoid can be dropped into an existing facility or requires rebuilding one around it.

    “Digit 5 is removing a major barrier to scaling humanoid robots in industrial environments.”

    Peggy Johnson, CEO, Agility Robotics

    Manufacturing runs through RoboFab in Salem, Oregon, which Agility has said can build up to 10,000 robots a year. That capacity figure, the order book and the 20-hour uptime claim are all company-stated and not independently verified. The OSHA evaluation and the standards work are the parts with outside parties attached.

    Sources

  • The Coming Decade of Home Robotics: What to Expect

    The Coming Decade of Home Robotics: What to Expect

    ANALYSIS — Every few years someone declares that the home robot has finally arrived. Usually they are wrong. But the ground is genuinely shifting: cheaper sensors, capable AI, and real manufacturing scale are converging at the same time. Here is what the next decade of home robotics will actually deliver, measured against what the industry is currently spending and shipping.

    The money is now real, and it is going into brains

    The clearest signal is not a product launch — it is a compute bill. Figure has committed to up to 100,000 Nvidia GPUs in a $3.5 billion deal with Nscale, with stated intent to scale past $6 billion, all of it to train Helix, the model that drives its humanoids. Nobody spends that on actuators. They spend it on perception and reasoning.

    That is the whole story of this decade in one line item. The mechanical parts of robotics have existed since the 1980s. What was missing was a brain flexible enough to handle a cluttered, unpredictable room. The body was never the bottleneck.

    From single-task gadgets to general manipulation

    The robots already in homes — vacuums, mowers, pool cleaners — each do exactly one thing. The frontier is general-purpose manipulation: picking up, carrying and handling everyday objects the machine has never seen before. That capability is what turns a gadget into a helper, and it is the single hardest problem in the field.

    Manufacturing scale arrived first in China

    Capability means nothing without the ability to build. The second World Humanoid Robot Games drew 666 teams from 16 countries fielding 2,056 humanoids — triple the prior year. Days earlier, the World Robot Conference opened in Beijing with 150 product debuts. And the public markets have noticed: Unitree’s Shanghai listing rose nearly sixfold on debut.

    What will not happen yet

    Honesty matters in a field this hyped. A robot that folds laundry, cooks dinner and minds the kids is not arriving this decade. Even the most aggressive commercial timeline on record is modest: Tesla has told analysts that Optimus sales could start in late 2027, with the Gen 3 design finalized and a line going into Fremont. That is a starting gun, not a finish line.

    Progress will look incremental and unglamorous. A robot that reliably does three useful things beats a prototype that impressively fails at thirty. The winners will earn trust one dependable task at a time.

    Why this decade is different

    Three curves are crossing at once: the cost of capable hardware is falling, AI capability is rising fast, and the manufacturing base to build at volume finally exists. When those align, adoption stops being linear. The companies laying groundwork now — in perception, safety and real-world reliability — are the ones that will define the decade.

    Zip Robotic covers robotics, automation and the companies building them. Read the latest.

  • Figure Lines Up 100,000 Nvidia GPUs in $3.5B Nscale Compute Deal

    Figure Lines Up 100,000 Nvidia GPUs in $3.5B Nscale Compute Deal

    Figure has signed a strategic partnership with Nscale for up to 100,000 GPUs on Nvidia’s Vera Rubin platform to train Helix, the AI model that drives its humanoid robots. The initial commitment is $3.5 billion, with stated intent to scale past $6 billion. First deployment is targeted for the second half of 2027 in Barstow, Texas.

    Why a robot company needs a frontier-lab GPU budget

    Figure’s argument is that humanoid intelligence is now a data-and-compute problem, not a hardware problem. The company says its Index dataset is generating 35 minutes of robot data every second from deployed machines, and that training on it at scale is the bottleneck. A 100,000-GPU cluster puts Figure’s compute in the same league as major AI labs.

    Nscale is also making a strategic investment in Figure, and the two companies say they’ll explore putting Figure humanoids to work in Nscale’s own data-center supply chain — the kind of closed-loop deal that has become a pattern in physical AI.

    “The physical AI flywheel that will accelerate the path from models to robots.”

    Jensen Huang, Nvidia CEO, on the partnership

    Sources

  • Beijing’s Robot Olympics Triples in Size With 2,056 Humanoids

    Beijing’s Robot Olympics Triples in Size With 2,056 Humanoids

    BEIJING — The second World Humanoid Robot Games wrapped up this week at the National Speed Skating Oval — the “Ice Ribbon” built for the 2022 Winter Olympics — and the numbers tell the story of how fast this field is moving. Organizers reported 666 teams from 16 countries fielding 2,056 humanoid robots across 51 events, up from roughly 280 teams and 500 robots at the inaugural games in August 2025. That’s a 138% jump in participation in a single year.

    Less spectacle, more work

    The 100m dash, football and boxing bouts that went viral last year were all back. But the bigger change was the addition of 21 scenario-based events designed to test skills companies will actually pay for: industrial assembly, hotel service, emergency rescue and warehouse logistics. Thirty events remained pure competition; in total the games ran 1,301 individual matches.

    Of the 666 teams, 641 were Chinese and 25 came from overseas — a reminder that while the event bills itself as a world championship, it is first and foremost a showcase for China’s domestic humanoid industry, which now counts Unitree, UBTech, AgiBot and dozens of smaller players.

    Open benchmarks to follow

    Organizers say full performance datasets from the games will be released as open benchmarks, which would give researchers outside China a rare, standardized look at how these machines perform under identical conditions.

    One claim we’re not repeating: a secondary site reported a sub-Bolt 9.32-second 100m. We couldn’t corroborate it with a primary source, so treat it as unconfirmed.

    Sources

  • Tesla Tells JPMorgan Optimus Sales Could Start in Late 2027

    Tesla Tells JPMorgan Optimus Sales Could Start in Late 2027

    FREMONT, Calif. — At a JPMorgan-hosted tour of its Fremont factory, Tesla told analysts that the design of Optimus Gen 3 is finalized, its supply chain is “essentially locked in,” and a production line is being installed in the facility that until earlier this year built the Model S and Model X.

    The headline: external commercial sales of Optimus could begin “as early as” the second half of 2027. Tesla repeated its long-term capacity goals of 1 million units a year at Fremont and 10 million in Texas.

    The context

    Electrek, which covered the tour, notes that the Gen 3 reveal has slipped repeatedly and that Elon Musk has acknowledged no Optimus units are yet doing useful work inside Tesla. The Model S/X line was torn down in April to make room — a real, expensive commitment — but “as early as” is doing a lot of work in that sentence.

    For comparison: Unitree shipped more than 5,500 humanoids in 2025 and Figure has deployed units with paying customers. Tesla’s bet is that when it does ship, it ships at automotive scale. That has never been done in robotics.

    Sources

  • Unitree Soars Nearly Sixfold in Blockbuster Shanghai IPO Debut

    Unitree Soars Nearly Sixfold in Blockbuster Shanghai IPO Debut

    SHANGHAI — Unitree Robotics, the Hangzhou company whose dancing and backflipping robots have become the public face of Chinese humanoids, listed on Shanghai’s STAR Market today under ticker 688836 — and promptly delivered one of the wildest debuts in the exchange’s history.

    Priced at 150.8 yuan, the stock opened at 1,100 yuan and closed at 883.87 yuan, up roughly 486%. The offering raised about $900 million for a 10% stake. Depending on whose math you use, that values the company somewhere between $50 billion (Reuters) and $66 billion (SCMP and Fortune) — far above any US humanoid rival.

    A real business underneath the hype

    Unlike most robotics IPO candidates, Unitree is profitable. Filings show 2025 revenue of 1.699 billion yuan and net profit of 590 million yuan, with humanoids now making up 51.78% of sales. The company shipped more than 5,500 humanoid units in 2025 — a volume no Western company has publicly come close to.

    The catch

    Three weeks before the listing, the US FCC added foreign-made mobile robots over 2 kg to its Covered List, effectively banning imports of new Unitree models into the United States on national-security grounds. The market clearly didn’t care today. Whether it matters over the next five years is the real question for shareholders.

    Sources

  • DeepMind’s Gemini Robotics 2 Brings Whole-Body Control to Humanoids

    DeepMind’s Gemini Robotics 2 Brings Whole-Body Control to Humanoids

    Google DeepMind has released Gemini Robotics 2, a family of three models that gives robots whole-body control, multi-minute task planning and the ability to coordinate with other robots. It’s the most significant update to Google’s robot “brain” since the original Gemini Robotics launched, and it lands as every humanoid company on earth is racing to build or buy exactly this kind of model.

    The three models

    • Gemini Robotics 2 (VLA) — the vision-language-action model that turns instructions and camera input into motor commands. Early access.
    • Gemini Robotics-ER 2 — the embodied-reasoning model for planning and spatial understanding. Available now in Google AI Studio.
    • On-device variant — runs locally on the robot for low-latency control. Early access.

    Demos ran on Apptronik’s Apollo 2 humanoid, Franka’s Duo gripper and Sharpa Wave dexterous hands, and DeepMind says the models can adapt to a new robot body in hours rather than weeks. Reported success rates included 76.3% on a shelf-pickup task, 89.6% on insertion and 92% on unscrewing light bulbs.

    Safety as a benchmark

    Alongside the models, DeepMind introduced ASIMOV-Agentic, a safety benchmark for agentic robots. In demonstrations, robots refused commands judged unsafe and asked a human for help when uncertain — behavior that will matter enormously once these systems are operating around people rather than in labs.

    Sources