# What is true on Control? > Markdown twin of https://roboterminal.app/topics/control · https://roboterminal.app/topics/control.md ## On this layer - org — [Google](https://roboterminal.app/companies/google) (7) - org — [Agility](https://roboterminal.app/companies/agility) (5) - org — [Tesla](https://roboterminal.app/companies/tesla) (5) - org — [Figure](https://roboterminal.app/companies/figure) (4) - org — OpenAI (4) - org — [Unitree](https://roboterminal.app/companies/unitree) (4) - org — agentic video understanding (3) - org — [NVIDIA](https://roboterminal.app/companies/nvidia) (3) - org — Agibot (2) - org — [Apptronik](https://roboterminal.app/companies/apptronik) (2) - org — [Boston Dynamics](https://roboterminal.app/companies/boston-dynamics) (2) - org — [1x](https://roboterminal.app/companies/1x) (1) - org — AGIBOTofficial (1) - org — AGILINKai (1) - org — Amazon (1) - plant — amazon-warehouses (1) - org — Astribot (1) - org — [BMW](https://roboterminal.app/companies/bmw) (1) - org — Booster Robotics (1) - org — Diligent Robotics (1) - org — Disney Research (1) - org — DROID dataset robot interaction data (1) - org — E-Commerce Bench (1) - org — Embodied AI model (1) - org — episodes in RoboLab evaluation (1) - org — examples for adapting to new robotic embodiments. (1) - org — Flexion Robotics (1) - org — G1 humanoid grasp and lift task (1) - org — Galbot (1) - org — GalbotRobotics (1) - org — Gamma Robotics (1) - org — Generalist AI (1) - org — gold medals won at the World Humanoid Robot Games (1) - org — Gravis Robotics (1) - org — Lattice Semiconductor (1) - org — LimX Dynamics (1) - org — Long-horizon unseen tasks (1) - org — MagicLab (1) - org — ManusMeta (1) - org — Meta (1) - regulator — meti (1) - regulator — nedo (1) - org — Number of downloads of the Index platform. (1) - org — Perceptron (1) - org — Perceptron AI (1) - org — perceptroninc (1) - org — PiPER (1) - org — production facilities (1) - org — Qwen (1) - org — rallies (1) - org — Reflect V1.0 from Flexion Robotics. (1) - org — RoboCup 2025 (1) - org — ROBOTIS (1) - org — Science Robotics (1) - org — Seeed Studio (1) - org — Serve Robotics (1) - org — Shield AI (1) - org — [Skild AI](https://roboterminal.app/companies/skild) (1) - org — SpaceX (1) - plant — spartanburg (1) - org — speedup in generative performance (1) - org — Stretch (1) - org — success rate with few-shot learning (1) - org — success rate with one-shot physical prompting (1) - org — System 0 (1) - org — System 1 (1) - org — target action-loss (1) - org — TeleAI (1) - org — teleoperation reduction (1) - org — the future of humanoids in robotics. (1) - org — Total number of videos collected by Index. (1) - org — total views of the post. (1) - org — training video hours (1) - org — TRON 2 (1) - org — Zhejiang University (1) - org — ZiNovaLabs (1) - org — 北京人形机器人创新中心有限公司 (1) - org — 宇树科技 (1) ## Who captures - @smsehy (12) - Google (5) - OpenAI (4) - Agility (4) - Tesla (3) - NVIDIA (2) - @chris_j_paxton (2) - @stretchcloud (2) - Agibot (2) - Galbot (1) - @Scobleizer (1) - Shield AI (1) - ROBOTIS (1) - @RoboPapers (1) - TeleAI (1) - Seeed Studio (1) - MagicLab (1) - Disney Research (1) - Qwen (1) - Stretch (1) - @deepakpathak (1) - Astribot (1) - @binarybits (1) - @AppliedInt (1) - Zhejiang University (1) - @OperationsPLS (1) - ZiNovaLabs (1) - Perceptron AI (1) - Boston Dynamics (1) - Figure (1) - GalbotRobotics (1) - Eduardo Baptista,Ju-min Park (1) - @techniahqrobot (1) - Perceptron (1) - AGIBOTofficial (1) - https://x.com/ErenChenAI (1) - @dredgefactory (1) - @spaceandtech_ (1) - 北京人形机器人创新中心有限公司 (1) - Flexion Robotics (1) - Booster Robotics (1) - Generalist AI (1) - Skild AI (1) - Joseph Amigo, Rooholla Khorrambakht, Nicolas Mansard, Ludovic Righetti (1) - Kevin Black (1) - Edmond (1) - Diligent Robotics (1) ## Sourced numbers - **TRON 2:** 1 units - _"TRON 2 serves as a modular and extensible embodied robotic platform for multi-tool, multi-step tasks across large workspaces."_ - Source: [LimX Dynamics on X: "Together with ZINOVA's Tool Intelligence, TRON 2 takes on increasingly complex construction workflows. @ZiNovaLabs builds on TRON 2 to explore an innovative robotic configuration for construction, demonstrating key tasks in a scaled-down tilt-up construction workflow, includi… / X](https://x.com/chris_j_paxton/status/2095114381818253768) - **Gemini models' efficiency in video analysis:** 88 units - _"They can now analyze videos with better accuracy while using up to 88% fewer tokens."_ - Source: [Google DeepMind on X: "We’re bringing agentic video understanding to our latest Gemini models. They can now analyze videos with better accuracy while using up to 88% fewer tokens. 🧵" / X](https://x.com/GoogleDeepMind/status/2094840179676660097) - **agentic video understanding:** $66 - _"reduces costs by up to 66%"_ - Source: [Introducing Agentic Video in Gemini](https://x.com/GoogleDeepMind/status/2094840182457422260) - **agentic video understanding:** 88 units - _"cuts token consumption by up to 88%"_ - Source: [Introducing Agentic Video in Gemini](https://x.com/GoogleDeepMind/status/2094840182457422260) - **agentic video understanding:** 7 units - _"boosts quality by up to 7%"_ - Source: [Introducing Agentic Video in Gemini](https://x.com/GoogleDeepMind/status/2094840182457422260) - **Embodied AI model:** 36,000,000,000 units - _"A 36B parameter model just blurred one of robotics’ biggest boundaries, the gap between seeing a scene and acting on it."_ - Source: [@techniahqrobot on X](https://x.com/techniahqrobot/status/2094550793743708256) - **the future of humanoids in robotics.:** 1 units - _"The robot revolution won’t be won by the humanoid with the best backflip."_ - Source: [@clavion95 on X](https://x.com/clavion95/status/2094380935999340836) - **Number of humanoids built by Figure.:** 1,000 units - _"has built more than 1,000 humanoids"_ - Source: [How Figure Became the Biggest Name in Robotics | XMAQUINA DAO](https://x.com/xmaquina/status/2094334389979373824) - **Number of BMW X3s produced with Figure's help.:** 30,000 units - _"contributed to the production of 30,000 BMW X3s."_ - Source: [How Figure Became the Biggest Name in Robotics | XMAQUINA DAO](https://x.com/xmaquina/status/2094334389979373824) - **Number of downloads of the Index platform.:** 264,000 units - _"Index had already reached 264,000 downloads across 108 countries"_ - Source: [How Figure Became the Biggest Name in Robotics | XMAQUINA DAO](https://x.com/xmaquina/status/2094334389979373824) - **Total number of videos collected by Index.:** 16,000,000 units - _"collected 16 million videos."_ - Source: [How Figure Became the Biggest Name in Robotics | XMAQUINA DAO](https://x.com/xmaquina/status/2094334389979373824) - **rallies:** 100 units - _"Galbot robots completed 100+ consecutive rallies at the World Humanoid Robot Games 2026 while tracking the ball, moving around the court and responding in real time."_ - Source: [@ctorobotics on X](https://x.com/ctorobotics/status/2094107883365335067) - **System 1:** 1 hrs - _"System 1 turns that into full-body joint targets at 200 Hz."_ - Source: [@techniahqrobot on X](https://x.com/techniahqrobot/status/2093111545462985101) - **System 0:** 1 hrs - _"System 0 runs at 1,000 Hz constantly adjusting balance, contact and coordination."_ - Source: [@techniahqrobot on X](https://x.com/techniahqrobot/status/2093111545462985101) - **teleoperation reduction:** 5884 hrs - _"cut the teleoperation needed to hit their action-loss target from 5,884 hours to 28."_ - Source: [@TheHumanoidHub on X](https://x.com/TheHumanoidHub/status/2092974952769048876) - **target action-loss:** 28 hrs - _"cut the teleoperation needed to hit their action-loss target from 5,884 hours to 28."_ - Source: [@TheHumanoidHub on X](https://x.com/TheHumanoidHub/status/2092974952769048876) - **gold medals won at the World Humanoid Robot Games:** 18 units - _"Congratulations to our partner @AGIBOTofficial on winning 18 gold medals and topping the medal table at the 2nd World Humanoid Robot Games."_ - Source: [MANUS™ on X: "Gold medals at the World Humanoid Robot Games! 🏆 Congratulations to our partner @AGIBOTofficial on winning 18 gold medals and topping the medal table at the 2nd World Humanoid Robot Games. Using @ManusMeta gloves for real-time teleoperation, the team's @AGILINKai OmniHand took first… / X](https://x.com/chris_j_paxton/status/2092967493618835900) - **total views of the post.:** 4,400 units - _"4.4KViews"_ - Source: [Eren Chen on X: "GRIT, a humanoid robotics lab in China demos its whole-body control under strong terrain disturbances during teleoperation. The robot keeps tracking the operator while stepping over obstacles and maintaining balance. Pretty robust." / X](https://x.com/ErenChenAI/status/2092835483114213783) - **Digit's operational hours:** 65000 hrs - _"Digit is now across nine customer sites with over 65,000 hours of operation."_ - Source: [@Coexisteven on X](https://x.com/Coexisteven/status/2092740012739850572) - **Gemini Robotics ER:** 2 units - _"I believe Gemini Robotics ER 2 is a clear example here."_ - Source: [@zhodonx on X](https://x.com/zhodonx/status/2092555239282843992) - **Unitree H2:** $29,900 - _"A 29900$ MACHINE IS DANCING ON A PAVEMENT AND NOT ONE PERSON WALKING PAST LOOKS UP."_ - Source: [@dredgefactory on X](https://x.com/dredgefactory/status/2092395639384539542) - **entry models of Unitree H2:** $. - _"Entry models go for 13500$."_ - Source: [@dredgefactory on X](https://x.com/dredgefactory/status/2092395639384539542) - **production facilities:** 1 units - _"on a humanoid robot already working in production facilities."_ - Source: [Agility on X: "We're hiring a Senior AI Software Engineer, Reinforcement Learning. Develop and deploy RL policies for locomotion, whole-body control, and manipulation — on a humanoid robot already working in production facilities. Build with us: https://t.co/b2Gs1xW7st #Agility" / X](https://x.com/agilityrobotics/status/2092309910793130488) - **Unitree G1 humanoid robot:** 1 units - _"The Unitree G1 humanoid robot can drive a go-kart, controlling the steering wheel and pedals around an indoor track."_ - Source: [@spaceandtech_ on X](https://x.com/spaceandtech_/status/2092234492266361018) - **Reflect V1.0 from Flexion Robotics.:** 0 hrs - _"A robotics intelligence platform designed to help robots complete complex tasks autonomously without a human operator."_ - Source: [@spaceandtech_ on X](https://x.com/spaceandtech_/status/2090437376766312589) - **RoboCup 2025:** 2,025 units - _"facilitating their victory at real world competitions such as the RoboCup 2025."_ - Source: [Booster Robotics on X: "Excited to see our work featured in Science Robotics. This research explores a new vision-driven controller for humanoid soccer, tested on Booster Robotics’ humanoid robots in real-world competitive settings. From research to the field, we’re pushing humanoid soccer forwa… / X](https://x.com/axisrobotics/status/2091846027422978139) - **success rate with one-shot physical prompting:** 59 units - _"Experiments across 10 diverse tasks show 59% average success with one-shot physical prompting, straight from pretraining."_ - Source: [Generalist on X: "Or when fine-tuned to place a block into a bowl, it can clear obstacles (like a piece of paper covering the bowl) to complete the task, despite that not being in the demonstrations." / X](https://x.com/humanoidsdaily/status/2090545339480613045) - **success rate with few-shot learning:** 83 units - _"With few-shot learning, performance rises to 83% via 10 gradient steps on 5 minutes of data per task."_ - Source: [Generalist on X: "Or when fine-tuned to place a block into a bowl, it can clear obstacles (like a piece of paper covering the bowl) to complete the task, despite that not being in the demonstrations." / X](https://x.com/humanoidsdaily/status/2090545339480613045) - **Long-horizon unseen tasks:** 10 units - _"The tasks run for up to ten minutes, span dozens of manipulation steps, and are driven by a single visual demonstration."_ - Source: [Introducing S1: In-Context Learning for Robotics | Skild AI](https://x.com/SkildAI/status/2092300864904126685) - **training video hours:** 2,202 units - _"2,202 h filtered multi-embodiment training video"_ - Source: [Hydra-0: Action Flow for Generalist World Modeling and Control | NVIDIA Isaac](https://x.com/NVIDIARobotics/status/2094515571501015339) - **episodes in RoboLab evaluation:** 300 units - _"5 policies × 6 tasks · 300 episodes"_ - Source: [Hydra-0: Action Flow for Generalist World Modeling and Control | NVIDIA Isaac](https://x.com/NVIDIARobotics/status/2094515571501015339) - **speedup in generative performance:** 16 units - _"16.0× generation-only speedup after few-step distillation"_ - Source: [Hydra-0: Action Flow for Generalist World Modeling and Control | NVIDIA Isaac](https://x.com/NVIDIARobotics/status/2094515571501015339) - **examples for adapting to new robotic embodiments.:** 200 units - _"we can now adapt to new bi-arm robot embodiments with just a few hours of adaptation time, typically with less than 200 examples."_ - Source: [Gemini Robotics 2 brings whole body intelligence to robots — Google DeepMind](https://x.com/SkillupAi/status/2093896499465945235) - **G1 humanoid grasp and lift task:** 10 units - _"G1 humanoid · grasp & lift · ten successes in a row"_ - Source: [Coupled Local and Global World Models for Efficient First Order RL](https://coupled-global-local-wm-rl.pages.dev/) - **DROID dataset robot interaction data:** 62 hrs - _"Meta reports using 62 hours of robot interaction data from the DROID dataset for this stage."_ - Source: [🤖🍨 Sundae Robotics 06: V-JEPA 2 & Predicting Physical Intelligence · Luma](https://luma.com/5h9owhri) ## Pulse - [@SawyerMerritt on X](https://x.com/SawyerMerritt/status/2095993244945457239) I've now done a total of 3 hours riding around in @Tesla’s Cybercab and spent a total of $92.51. That travel time would have cost me $200 with Ubers. My longest ride has been ~40 minutes. I legitimate… - [@GalbotRobotics on X](https://x.com/GalbotRobotics/status/2095982381307969568) Galbot ET1 — the world’s first autonomous learning-capable agentic humanoid robot — is now available for pre-order on https://t.co/92OEbTIoiT! A Native Agent for the Physical World, ET1 is built to se… - [@Scobleizer on X](https://x.com/Scobleizer/status/2095953650921472452) This is the first time I've seen a user interface for robots like this. I'll be at @dimensionalos in San Francisco tonight to learn more. But imagine five years from now. You have a pair of glasses on… - [@NVIDIARobotics on X](https://x.com/NVIDIARobotics/status/2095950021636046876) Interested in getting hands-on with Newton? The newly released Newton Learning Path will help you set up a ready-to-run environment, dive into Newton abstractions, and show you how to build your first… - [@tchsignal on X](https://x.com/tchsignal/status/2095922412751880596) Researchers Linked Thousands of Wiki Agents to OpenAI Researchers analyzing public wiki activity attributed 3,103 AI agents to systems linked with OpenAI, documenting 14,666 edits across 4,584 pages b… - [@spaceandtech_ on X](https://x.com/spaceandtech_/status/2095914090481017283) Shield AI unveiled X-BAT, an autonomous jet aircraft with vertical takeoff and landing. It can reach 50,000 feet and fly 2,000 nautical miles. Powered by Hivemind AI, it can perform complex missions a… - [@techniahqrobot on X](https://x.com/techniahqrobot/status/2095906198994239540) ROBOTIS is turning its AI Sapiens K1 humanoid into a real training platform for the next generation of robotics engineers. Through Open Humanoid GYM, student teams build motions in simulation and tran… - [@chris_j_paxton on X](https://x.com/chris_j_paxton/status/2095865736975515725) This: "You don't have to post-train ChatGPT on every user" is exactly what I think robotics has been missing and why every "chatGPT moment" for robotics has rung a bit hollow. we're at a really exciti… - [@chris_j_paxton on X](https://x.com/chris_j_paxton/status/2095854947938058250) Learn contact-rich humanoid manipulation policies, purely within a world model. This is usually not tractable, because you need a very large model to get the contact dynamics right -- instead, @Jspham… - [@RoboPapers on X](https://x.com/RoboPapers/status/2095854394667393218) Reinforcement learning has unlocked tremendous gains in broader AI and humanoid robot whole body control, but still has yet to deliver strong results for robot manipulation due to the difficulty of ca… - [@BitsWattsDesk on X](https://x.com/BitsWattsDesk/status/2095852633496195313) The humanoid hand debate is focused on the wrong bottleneck. The usual argument is about where to put the motor. Tendon-driven hands keep the actuators upstream and pull the fingers with cables. Tesla… - [@ErenChenAI on X](https://x.com/ErenChenAI/status/2095846181922329012) TeleAI × Gamma Robotics unveiled NEXUS, a perceptive behavior foundation model for humanoids. The idea: take motions learned on flat ground and adapt them in real time to complex terrain without losin… - [@seeedstudio on X](https://x.com/seeedstudio/status/2095844325406179508) What does it take to teach a robot arm to work on its own? With #SOARM101 + @LeRobotHF + ACT, we walk through the full imitation learning loop: calibration → teleoperation → data collection → training… - [@techniahqrobot on X](https://x.com/techniahqrobot/status/2095834100842000580) This humanoid is getting smoother one movement at a time. MagicLab’s MagicBot X1 is being trained on choreography, with individual movements refined repeatedly before being connected into a complete s… - [@ctorobotics on X](https://x.com/ctorobotics/status/2095806576175018399) Disney was exploring robotic design long before the current robotics boom. 🤖 This research shows how Disney Research worked on computational methods to optimize robotic mechanisms and motion. The int… - [@smsehy on X](https://x.com/smsehy/status/2095804818472194100) 47 minutes watching a dot matrix printer spit out forms at a dealership earlier this year. The finance manager 'ran the numbers' on a system that looked like it belonged in a museum. I work daily on s… - [@stretchcloud on X](https://x.com/stretchcloud/status/2095768833437184166) The hardest thing to benchmark is not intelligence. It is judgment over a full year. E-Commerce Bench, released this week by the Qwen team, is the first benchmark that runs an LLM agent through a full… - [@smsehy on X](https://x.com/smsehy/status/2095757175851479448) Utilizing digital twins to systematically augment rare failure edge cases accelerates reinforcement learning policy stability without risking physical robot hardware damage. https://t.co/I5C3BaTXT8 - [@smsehy on X](https://x.com/smsehy/status/2095757058952036843) Automotive Software Defined Vehicle (SDV) Architectures / SDV transitions succeed when OEMs decouple software release cycles from physical vehicle hardware refresh timelines through standardized abstr… - [@smsehy on X](https://x.com/smsehy/status/2095756852197998844) Pre-certified microkernels provide the foundational determinism needed to ensure safety-critical vehicle displays and control loops never freeze during high-load background compute tasks. https://t.co… - [@smsehy on X](https://x.com/smsehy/status/2095756668961456574) Sim-to-real pipelines allow developers to test vision-language-action policies in synthetic environments, but production deployment still requires handling real-world joint backlash and mechanical the… - [@smsehy on X](https://x.com/smsehy/status/2095755292466434056) 製造現場のデジタルツインとフィジカルAIの統合において最も重要な課題は、既存の産業用PLCとリアルタイム通信プロトコルの決定論的な同期を維持し、レイテンシによる生産ライン停止を防ぐことです。 https://t.co/OJRyEbCb2z - [@smsehy on X](https://x.com/smsehy/status/2095753582708670826) Self-collapsing mechanical kinematics simplify logistics and freight transport, but packaging complex folding joints into structural limbs increases mechanical backlash that control algorithms must co… - [@smsehy on X](https://x.com/smsehy/status/2095753525162901511) Open-source teleoperation arms running carbon-fiber reinforced structures dramatically lower the cost of gathering high-quality physical imitation datasets, accelerating policy training for industrial… - [@stretchcloud on X](https://x.com/stretchcloud/status/2095739885772554382) Reef is one of the most ambitious open-source AI infrastructure projects I have seen this year. ~300 GitHub stars in two days. The core idea is genuinely different from anything else in the space: mos… - [@smsehy on X](https://x.com/smsehy/status/2095712146147733971) Training reinforcement learning on cached latent embeddings solves policy training throughput. The critical step for automotive manufacturing remains hard reliability optimization to eliminate rare ed… - [@smsehy on X](https://x.com/smsehy/status/2095711383677768133) Crowdsourcing simulated trajectories accelerates high-level spatial priors. The engineering hurdle remains capturing high-frequency joint torque and tactile force vectors that cannot be generated with… - [@smsehy on X](https://x.com/smsehy/status/2095711246079389881) Simulating visual environments generates kinematic diversity quickly. The persistent physical wall remains non-rigid contact mechanics and micro-slip telemetry, where synthetic physics engines diverge… - [@smsehy on X](https://x.com/smsehy/status/2095711187992477703) Neural policies plan trajectories, but classical feedback control is what prevents high-inertia industrial arms from oscillating when handling dynamic loads. Eliminating classical PID loops on factory… - [@CapitalSqueez on X](https://x.com/CapitalSqueez/status/2095709673253138717) $CCXI Jeff Bezos just followed Chris Paxton. Paxton is one of the sharpest minds in embodied AI — currently at Agility Robotics (Digit), previously Meta and NVIDIA. He lives and breathes the hard prob… - [@stretchcloud on X](https://x.com/stretchcloud/status/2095700123464733012) The thing I keep noticing across agentic frameworks in 2026: resumability is now the reliability primitive everyone is building toward. Genkit Go 1.13 ships it properly. A Generate call that fails at … - [@techniahqrobot on X](https://x.com/techniahqrobot/status/2095698231455813708) A big win for the robotics community AGIBOT just open sourced one of its most valuable real world datasets yet. @AGIBOTofficial has open-sourced AGIBOT WORLD 2026 Theme 3, a real-world dataset designe… - [@DrJimFan on X](https://x.com/DrJimFan/status/2095696882844463382) Good old days at OpenAI in 2016: an agent stares at screen pixels, moves a mouse, and books a flight on United. We called it World of Bits, inside OpenAI Universe. 10 yrs later, Astra is reincarnated … - [@stretchcloud on X](https://x.com/stretchcloud/status/2095665142730256633) The harness problem is getting its own framework category. Tardigrade ships today: an agent harness built as typed state machine components over an immutable event log. The framing is React for harnes… - [@rimtoln on X](https://x.com/rimtoln/status/2095628517103071435) GPT-6 ASTRA ISN'T A PATCH. IT'S A GENERATION FLIP. openai just shipped the model they call a generational leap past gpt-5.6 sol not better chat better computer use · coding · cyber · science ▹ why thi… - [@deepakpathak on X](https://x.com/deepakpathak/status/2095626632430240118) You don't have to post-train ChatGPT on every user. If you did, it would never have taken off. Yet this is exactly how robotics works today For robots to take off, they need to learn in-context. Great… - [@techniahqrobot on X](https://x.com/techniahqrobot/status/2095609621180232193) GPT-6 Astra is here, and it might be one of the most important AI releases yet. OpenAI says the model hits 98% on FrontierMath Tier 4, 99.9% on ARC-AGI 3 and a perfect 100% on ExploitBench. It also sh… - [@XRoboHub on X](https://x.com/XRoboHub/status/2095588510950727820) Robots can’t stop while the model thinks. In a high-speed throw, even one pause can kill the momentum. Astribot released SmoothRL for online RL during async inference. S1 keeps moving as the model com… - [@spaceandtech_ on X](https://x.com/spaceandtech_/status/2095587174804750669) AGIBOT has officially open-sourced AGIBOT WORLD 2026 Theme 3: Reinforcement Learning, a real-world embodied AI dataset collected across expert demonstrations, autonomous policy rollouts, and human-in-… - [@binarybits on X](https://x.com/binarybits/status/2095577988007911472) This is a great illustration of why training robots manipulation tasks in simulation (middle clip) doesn't work very well. From Kai's excellent new piece on robot data. https://t.co/2ysIIvThKK https:/… - [@AppliedInt on X](https://x.com/AppliedInt/status/2095569678685049061) At this year’s Agentic AI Summit hosted by @BerkeleyRDI, our Chief Scientist, @Wei_ZHAN_ shared some of the cutting edge research he has been leading in the physical AI space. As the industry races to… - [@techniahqrobot on X](https://x.com/techniahqrobot/status/2095562223582060581) Zhejiang University just pushed long-horizon robot manipulation forward with HINT. HINT helps Vision-Language-Action models keep track of the human’s original intent across long tasks instead of losin… - [@OperationsPLS on X](https://x.com/OperationsPLS/status/2095425493021712790) The control question gets harder as AI moves from digital to physical. In robotics, control is not just governance — it is real-time safety architecture. Graceful degradation and audit trails become o… - [LimX Dynamics on X: "Together with ZINOVA's Tool Intelligence, TRON 2 takes on increasingly complex construction workflows. @ZiNovaLabs builds on TRON 2 to explore an innovative robotic configuration for construction, demonstrating key tasks in a scaled-down tilt-up construction workflow, includi… / X](https://x.com/chris_j_paxton/status/2095114381818253768) Post Log in Sign up Post LimX Dynamics on X: "Together with ZINOVA's Tool Intelligence, TRON 2 takes on increasingly complex construction workflows. @ZiNovaLabs builds on TRON 2 to explore an innovati… - [Google DeepMind on X: "We’re bringing agentic video understanding to our latest Gemini models. They can now analyze videos with better accuracy while using up to 88% fewer tokens. 🧵" / X](https://x.com/GoogleDeepMind/status/2094840179676660097) Post Log in Sign up Post Google DeepMind on X: "We’re bringing agentic video understanding to our latest Gemini models. They can now analyze videos with better accuracy while using up to 88% fewer tok… - [Introducing Agentic Video in Gemini](https://x.com/GoogleDeepMind/status/2094840182457422260) Introducing agentic video understanding with Gemini Sep 01, 2026 \| 7 min read - x.com - Facebook - LinkedIn - Mail - Copy link Our new agentic feature for video analysis cuts token consumption by up … - [@techniahqrobot on X](https://x.com/techniahqrobot/status/2094550793743708256) A 36B parameter model just blurred one of robotics’ biggest boundaries, the gap between seeing a scene and acting on it. Perceptron AI has released Isaac 0.5, an open-weight Embodied AI model designed… - [@clavion95 on X](https://x.com/clavion95/status/2094380935999340836) THIS ISN’T A ROBOT LEARNING TO DANCE. IT’S A ROBOT LEARNING HOW TO CONTROL ITS ENTIRE BODY. Walk. Run. Crawl. Roll. Handstand. Cartwheel. Then get back up and keep moving. Boston Dynamics trained Atla… - [How Figure Became the Biggest Name in Robotics | XMAQUINA DAO](https://x.com/xmaquina/status/2094334389979373824) Genesis Auction Wave 2! Launches June 24 Get DEUS homeDAO Portal How Figure Became the Biggest Name in Robotics Color theme: Four years, three generations of humanoids, a $39 billion valuation and now… - [@ctorobotics on X](https://x.com/ctorobotics/status/2094107883365335067) Humanoid robots just took tennis to another level. 🎾🤖 Galbot robots completed 100+ consecutive rallies at the World Humanoid Robot Games 2026 while tracking the ball, moving around the court and res… - [kasper on X: "Elon Musk was asked when Tesla Optimus could become better than the best human surgeons. His argument is that a robot would not learn like one doctor. Every Optimus surgeon could share what every other unit had seen, including rare complications that a human might encounter only once… / X](https://x.com/HumanoidsHQ/status/2094325624177397929) Post Log in Sign up Post kasper on X: "Elon Musk was asked when Tesla Optimus could become better than the best human surgeons. His argument is that a robot would not learn like one doctor. Every Opti… - [Gemini Robotics 2 brings whole body intelligence to robots - YouTube](https://x.com/ScrumVenturesJP/status/2093534278378553445) Error 401 (Bad Request)!!1 401. That’s an error. The server cannot process the request because it is malformed. It should not be retried. That’s all we know. Back Skip navigation Search Search with yo… - [China’s record robotic strides show the limits of human speed | Reuters](https://x.com/pstAsiatech/status/2093730835132268862) Skip to main content Exclusive news, data and analytics for financial market professionalsLearn more aboutRefinitiv More Videos 0 seconds of 0 secondsVolume 0% Press shift question mark to access a li… - [@techniahqrobot on X](https://x.com/techniahqrobot/status/2093111545462985101) Most people watch Figure 03 walk and look at the legs. But a lot of the interesting work is happening underneath. Figure’s Helix 02 uses three control layers. System 2 understands the scene the instru… - [@TheHumanoidHub on X](https://x.com/TheHumanoidHub/status/2092974952769048876) Perceptron's Isaac 0.5 is a 36B open-weight embodied foundation model with only 2.5B active per token. The model - Perception, reasoning, and control all read from one shared backbone, so it makes vis… - [MANUS™ on X: "Gold medals at the World Humanoid Robot Games! 🏆 Congratulations to our partner @AGIBOTofficial on winning 18 gold medals and topping the medal table at the 2nd World Humanoid Robot Games. Using @ManusMeta gloves for real-time teleoperation, the team's @AGILINKai OmniHand took first… / X](https://x.com/chris_j_paxton/status/2092967493618835900) Post Log in Sign up Post MANUS™ on X: "Gold medals at the World Humanoid Robot Games! 🏆 Congratulations to our partner @AGIBOTofficial on winning 18 gold medals and topping the medal table at the 2nd… - [Eren Chen on X: "GRIT, a humanoid robotics lab in China demos its whole-body control under strong terrain disturbances during teleoperation. The robot keeps tracking the operator while stepping over obstacles and maintaining balance. Pretty robust." / X](https://x.com/ErenChenAI/status/2092835483114213783) Post Log in Sign up Post Eren Chen on X: "GRIT, a humanoid robotics lab in China demos its whole-body control under strong terrain disturbances during teleoperation. The robot keeps tracking the opera… - [@Coexisteven on X](https://x.com/Coexisteven/status/2092740012739850572) 3/4 🤖 Robotics / Physical AI Layer Agility Robotics shared a video of Digit’s whole-body range of motion being stress-tested in a workout class (every joint in sync for timing, velocity, and balance … - [Agility on X: "Whole-body range of motion, stress-tested by a workout class. Every joint in sync — timing, velocity, balance. The same control Digit uses on a real warehouse floor. #Agility #DigitRobot" / X](https://x.com/agilityrobotics/status/2092704763892937082) Post Log in Sign up Post Agility on X: "Whole-body range of motion, stress-tested by a workout class. Every joint in sync — timing, velocity, balance. The same control Digit uses on a real warehouse f… - [@zhodonx on X](https://x.com/zhodonx/status/2092555239282843992) I’ve said before that I think Google & DeepMind are playing a longer game with models. This is still a firm stance. Because a lot of the time, i think people look at Google’s model strategy too narrow… - [@dredgefactory on X](https://x.com/dredgefactory/status/2092395639384539542) A 29900$ MACHINE IS DANCING ON A PAVEMENT AND NOT ONE PERSON WALKING PAST LOOKS UP. 29900$ is a Unitree H2, the class this thing sits in. Entry models go for 13500$. Every beat throws its centre of ma… - [Agility on X: "We're hiring a Senior AI Software Engineer, Reinforcement Learning. Develop and deploy RL policies for locomotion, whole-body control, and manipulation — on a humanoid robot already working in production facilities. Build with us: https://t.co/b2Gs1xW7st #Agility" / X](https://x.com/agilityrobotics/status/2092309910793130488) Post Log in Sign up Post Agility on X: "We're hiring a Senior AI Software Engineer, Reinforcement Learning. Develop and deploy RL policies for locomotion, whole-body control, and manipulation — on a h… - [@spaceandtech_ on X](https://x.com/spaceandtech_/status/2092234492266361018) The Unitree G1 humanoid robot can drive a go-kart, controlling the steering wheel and pedals around an indoor track. It can handle tight corners and even perform controlled drifts. Developed with Symb… - [中国机器人“跑赢”博尔特，这意味着什么？ - 纽约时报中文网](https://x.com/RFAChinese/status/2092672676141654233) 中国 - 中文中 - 中英双语双语 - 英文 英 YAN ZHUANG2026年8月25日 Achmad Ibrahim/Associated Press 2009年，尤塞恩·博尔特在柏林世界田径锦标赛上创造了9.58秒的男子 100米短跑世界纪录。据中国官方媒体报道，上周六，由中国公司北京人形机器人创新中心有限公司(X-Humanoid)开发的一款人形机器人以0.19秒的优势打破了该纪录。这台机… - [@spaceandtech_ on X](https://x.com/spaceandtech_/status/2090437376766312589) Humanoid robots often struggle with tasks that involve many steps and require them to recover from mistakes. Flexion Robotics developed Reflect V1.0, a robotics intelligence platform designed to help … - [Booster Robotics on X: "Excited to see our work featured in Science Robotics. This research explores a new vision-driven controller for humanoid soccer, tested on Booster Robotics’ humanoid robots in real-world competitive settings. From research to the field, we’re pushing humanoid soccer forwa… / X](https://x.com/axisrobotics/status/2091846027422978139) Post Log in Sign up Post Booster Robotics on X: "Excited to see our work featured in Science Robotics. This research explores a new vision-driven controller for humanoid soccer, tested on Booster Robo… - [Generalist on X: "Or when fine-tuned to place a block into a bowl, it can clear obstacles (like a piece of paper covering the bowl) to complete the task, despite that not being in the demonstrations." / X](https://x.com/humanoidsdaily/status/2090545339480613045) Post Log in Sign up Post Generalist on X: "Or when fine-tuned to place a block into a bowl, it can clear obstacles (like a piece of paper covering the bowl) to complete the task, despite that not bein… - [Introducing S1: In-Context Learning for Robotics | Skild AI](https://x.com/SkildAI/status/2092300864904126685) 0:00 / 0:00 1× Introducing S1: In-Context Learning for Robotics Unseen tasks10-minute horizonsOne video promptNo post-training 13-minute read Contents Introduction Why In-Context Learning for Robotics… - [Hydra-0: Action Flow for Generalist World Modeling and Control | NVIDIA Isaac](https://x.com/NVIDIARobotics/status/2094515571501015339) Overview video Figure 1: Action flow as a shared control interface. Top: Hydra-0 learns from diverse interaction videos featuring egocentric human demonstrations, handheld UMI grippers, bimanual robot… - [Gemini Robotics 2 brings whole body intelligence to robots — Google DeepMind](https://x.com/SkillupAi/status/2093896499465945235) Skip to main content July 30, 2026 Models Gemini Robotics 2 brings whole body intelligence to robots Carolina Parada Share Your browser does not support the video tag. From feet to fingertips — we are… - [Coupled Local and Global World Models for Efficient First Order RL](https://coupled-global-local-wm-rl.pages.dev/) Real-world tasks solved zero-shot by policies trained entirely inside our learned world models: Push-T with a tabletop manipulator (left), Ego-Centric Grasp and Lift with a G1 humanoid (centre), and E… - [π0: A Vision-Language-Action Flow Model for](https://arxiv.org/pdf/2410.24164) π0: A Vision-Language-Action Flow Model for General Robot Control Physical Intelligence Kevin Black, Noah Brown, Danny Driess, Adnan Esmail, Michael Equi, Chelsea Finn, Niccolo Fusai, Lachy Groom, Kar… - [🤖🍨 Sundae Robotics 06: V-JEPA 2 & Predicting Physical Intelligence · Luma](https://luma.com/5h9owhri) Hosted By Edmond Jono Hart James (Jingxi) Xu Mene Mazarakis Angela Zhang Manfredi Bernardi Adam 134 Went Akshobhya Gupta, Hannah Tsui and 132 others Contact the Host Report Event AI 🤖🍨 Sundae Roboti… - [RoboBrief: Daily Robotics News, Humanoid Robots & AI Automation](https://robobrief.tech/) Daily robotics intelligence The global robotics briefing desk Your daily robotics intelligence briefing — US, China, India & beyond. Breaking news, analysis, and insights on the global robotics revolu… --- Source: Roboterminal · https://roboterminal.app/topics/control.md