Before a robot can perfect assembly, it needs to learn to play. The team behind SimToolReal @kushalk_ @tylerlum23 @leto__jean @KarenJLiu published another cool paper! Play2Perfect pretrains on diverse, task-agnostic play (grasp, reorient, reach, etc), then finetunes on sparse-reward assembly. Result: 33× sample efficiency vs. training from scratch, and zero-shot sim-to-real down to 0.5mm clearance. Peg insertion, screwing, multi-part assembly: all running at 60Hz, real speed, real hardware. And when a grasp slips, the policy doesn't stop, it recovers and keeps going. The Sharpa Wave responded present again ;) Project: play2perfect.github.io #Robotics #SharpaWave #Sharpa #EmbodiedAI #DexterousManipulation #RobotLearning

Proud to be part of the team behind CHORD, advancing dexterous robot learning from human demonstrations through contact-wrench guidance. Congratulations to the entire team on this exciting milestone! #Robotics #PhysicalAI #DexterousManipulation #RobotLearning

Proception Raises $11M Seed to Scale High-Dexterity Robotic Hands Following Tesla Lawsuit Settlement newnex.io/feed/proception-ra… #Robotics #HumanoidRobots #ArtificialIntelligence #AI #HumanoidAI #RobotHands #DexterousManipulation #Automation #DeepTech #StartupFunding #SeedFunding

Most robot hands can still only tell you “something is touching.” This one tells you exactly where, how hard, and in three dimensions — even when the force is just a drifting feather. 🩻1,000 sensing nodes. 🩻Biomimetic palm texture. 🩻Clean data on empty grasps. 🩻Wireless from the wrist. 🩻Time-synced with external vision. 🩻Every single contact point logged. The gap between a gripper that works in a controlled demo and hardware that can operate around people and variable objects is often this level of tactile resolution. If you’re building humanoids or fine manipulation systems, this is the spec you benchmark against. #HumanoidRobotics #DexterousManipulation #TactileSensing #PhysicalAI #Haptics #EdgeAI #RobotHands #shenzhenfoundry

How can robots learn dexterous manipulation from human demonstrations at scale? Excited to share CHORD: Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration. CHORD learns from human demos by focusing not only on where contact happens, but how that contact moves the object through force and torque guidance. This unified contact-wrench representation carries human manipulation skills across diverse behaviors, long-horizon tasks, whole-body embodiments, and real-world hardware. We evaluated CHORD on large-scale, long-horizon, contact-rich tasks paired with human demonstrations, spanning rigid, articulated, and multi-object manipulation. At scale: * 82.12% average success across 1,831 tasks * 90.77% whole-body manipulation success * 4,739 sim-ready dexterous manipulation benchmark * Transfer to real dexterous hands Project page: nvidia-isaac.github.io/video… Tech report: nvidia-isaac.github.io/video… Code will be released soon as part of Video to Data repo github.com/nvidia-isaac/vide…, our end-to-end pipeline for converting human demonstration videos into simulation-ready assets and physics-grounded robot training data. Huge thanks to amazing contributors: @zhu_xinghao , Zixi Liu, Shalin Jain, Chenran Li, Milad Noori, Huihua Zhao, John Welsh, @michaelv03, Wei Liu, @TingwuWang , Xingye (Dennis) Da, @zhengyiluo, Vishal Kulkarni, @sNaema, @yukez, @DrJimFan, @bowenwen_me, @danfei_xu, @SohaPouya, @Dr_YanChang. #Robotics #PhysicalAI #DexterousManipulation #RobotLearning #NVIDIA

MIDAS Hand combines dexterous manipulation, tactile sensing, and low-cost hardware in an open-source robotic hand platform. The platform uses a 13 active 3 passive DoF anthropomorphic hand architecture and integrates tactile sensing through 283 total 3-axis taxels, enabling richer contact feedback for robot learning and manipulation research. With a low-cost build target of approximately $3k BOM cost, MIDAS Hand aims to make dexterous robotic hand development more accessible for researchers working on teleoperation, embodied AI, and humanoid robotics. For humanoid robotics, this is important because manipulation remains one of the hardest real-world deployment challenges. A humanoid robot needs more than motion: it needs to grasp, feel contact, adjust force, and handle object variation reliably. 🎥 via Midas Hand ℹ️ This content is shared for informational purposes only. All intellectual property rights belong to their respective owners. #HumanoidRobotics #MIDASHand #Robotics #EmbodiedAI #DexterousManipulation #RobotManipulation #TactileSensing #OpenSourceRobotics #RobotHand #PhysicalAI #Teleoperation #ImitationLearning #RobotLearning

#robotics #DexterousManipulation #VLM #3DGrounding #ZeroshotManipulation

Robotics Night in Seoul: the room is almost full 🇰🇷🤖 ~40 researchers are already confirmed for our July 8 Robotics Night at the RLWRLD lab, and ~70% of them are #ICML2026 authors. The rest are a deep network in robotics AI. To keep the room that dense, we're curating the last few seats carefully. 👇🏻 🤝 The room: ICML authors and presenters across VLA, world models, manipulation, and dexterity, in close conversation with the RLWRLD researchers who built RLDX-1. Small, dense, signal over noise. 🤖 Live RLDX-1 demos on real robot hands, our dexterity-first foundation model for true five-finger dexterity, running on the same floor where it was trained. 📍 July 8 (Wed), 7:30 PM · RLWRLD Lab, Gangnam, Seoul (2 blocks from COEX where ICML2026 is) 🎟️ rlwrld.co/icml Invite-only · very few seats left · selective from here on. If you're presenting at ICML or deep in robotics AI research, we'd love to have you, and we hope you'll understand if we can't fit everyone this time. 🙏🏻 Preview of what runs live that night 👉 youtube.com/watch?v=H90bt8S8… Here's our story 👉 youtube.com/watch?v=KRD9yMqP… Check out the RLDX-1 tech blog 👉 rlwrld.ai/rldx-1 #RLDX #RLWRLD #ICML2026 #PhysicalAI #Robotics #DexterousManipulation #RoboticsFoundationModel #VLA #WorldModel

📚 @saturdayrobotic Robotics & World Models Reading Club 15: Scaling Touch — Flexible Tactile Skin for Dexterous Manipulation | Los Altos 06/27 👉🏻RSVP: luma.com/7lts5ppf ​Tactile and visual perception are crucial for fine-grained human interactions with the environment. Developing similar multimodal sensing capabilities for robots can significantly enhance and expand their manipulation skills. This talk presents a scalable tactile stack that couples flexible, large-area tactile skin with multimodal perception and simulation-driven learning. (1) Hardware. I will first introduce a low-cost, flexible tactile “skin,” outline the associated design choices, explain why I value it over other sensors in different contexts, and describe how I integrate it into the system to ensure high-quality tactile data. (2) Learning. Vision and touch have distinct natures yet are both important for robot decision making; I will explain how we encode tactile and visual data so that both contribute effectively to the decision-making process. (3) Scaling up Tactile Data. I will present two directions: (i) using portable tactile devices to collect large-scale real-world tactile data and leveraging this dataset to enhance policy learning, and (ii) leveraging tactile simulation to increase policy robustness. We use a real-to-sim-to-real pipeline that calibrates a GPU-parallel tactile simulation and uses RL fine-tuning to let policies explore with the small corrective “wiggling” behaviors required for tight-fit bimanual assembly. Keynote Speaker: @binghao_huang, 3rd-year PhD student in Computer Science at @Columbia (advised by Prof. Yunzhu Li). Previously M.S. at @UCSanDiego (Prof. Xiaolong Wang) and @NVIDIA Seattle Robotics Lab. His work focuses on robot learning, dexterous manipulation, and multimodal perception. Hosted by @junfanzhu98 & @aurorafeng_01 📍 Los Altos (Downtown) 📅 Saturday, June 27, 2026 | 2:00 PM – 5:00 PM Agenda 2:00–2:30 PM — Doors open & social (food, beverages & UNLIMITED strawberries 🍓 — official Reading Club fruit!) 2:30–4:00 PM — Keynote by @binghao_huang 4:00–5:00 PM — Q&A open-floor roundtable (spotlight any paper or technical deep-dive) Previous sessions have brought together researchers & engineers from Boston Dynamics, Google DeepMind, NVIDIA, Stanford, UC Berkeley, Physical Intelligence, Tesla, Rhoda AI, Dyna, Generalist and leading Bay Area robotics startups. Join the Saturday Robotics Discord for updates, Zoom link & community: discord.gg/WH7DrTHRXK Follow @saturdayrobotic for more frontier robotics & world models content. Follow Luma calendar: luma.com/saturdayrobotic Come ready to discuss flexible tactile skin, dexterous manipulation, multimodal perception, sim-to-real pipelines, and scaling contact-rich intelligence. 👉🏻RSVP: luma.com/7lts5ppf #Robotics #WorldModels #EmbodiedAI #TactileSensing #DexterousManipulation #BayAreaRobotics #DeepTechWeek @deeptechvc

Excited to see WUJI as part of the @NVIDIA Isaac Teleop ecosystem. Wuji Glove captures human hand motion. Wuji Hand brings it into dexterous robot execution. Looking forward to exploring what comes next with NVIDIA and the broader Physical AI ecosystem. #WujiTech #NVIDIA #WujiHand #WujiHand2 #DexterousHand #Robotics #PhysicalAI #DexterousManipulation

Robots need to feel the world to operate in it. Most manipulation policies today are tactile-blind. They either cannot interpret high-frequency tactile signals or treat them as a static channel. And the field lacks enough touch-rich datasets to train tactile-reactive policies at scale. T-Rex was built to answer both. @Dantong_Niu and team, advised by @DrJimFan, @drfeifei, @JitendraMalikCV, @pabbeel @trevordarrell have tested whether a robot policy can react to high-frequency tactile signals the way human hands do, without giving up the generalization power of modern VLAs. The result: 65% average success rate across 12 real-world tasks. 30 absolute points over the strongest baseline. In one year, tactile VLAs have gone from promising to outperforming non-tactile baselines like pi0.5 on dexterous tasks. #Robotics #SharpaWave #Sharpa #EmbodiedAI #DexterousManipulation #TactileSensing #RobotLearning Project link: tactile-rex.github.io/

We can use videos from the internet to teach robots! Do as I Do, from @bhawna_paliwal_ , @HarithejaE , and Willian Liang at UC Berkeley — advised by @pabbeel, @notmahi, and @JitendraMalikCV, used an algorithm that reconstructs hand-object interactions from monocular RGB video and retargets them into real, executable trajectories for multi-fingered dexterous hands. Just using "low quality" video footage of humans doing tasks. No sensors. The Sharpa Wave robot hand being anthropomorphic, it matches human kinematics. Not only that works, but at fast speed, too! Congrats to the team, that's super exciting! Project: do-as-i-do.com/ #Robotics #SharpaWave #Sharpa #EmbodiedAI #DexterousManipulation #RobotLearning

🚀 Calling for Keynotes, Panelists & Lightning Talks 🥂 Saturday Robotics x SF Deep Tech Week Happy Hour 06/25 | Robotics & World Models Reading Club 14 👉🏻 RSVP: luma.com/l1g9c2l1 As part of @saturdayrobotic Deep Tech Week Summit (June 2026), we're bringing together robotics researchers, founders, investors, and builders during SF Deep Tech Week for an evening of discussions on the future of embodied AI and robotics. 📅 June 25, 2026 ⏰ 5:30 PM – 9:30 PM 📍 San Francisco We're currently looking for speakers, panelists, and lightning talk presenters interested in sharing insights on: • World Models • Robotics Frontiers: Industry and Academia • Dexterous Manipulation, Cross-Embodiment • Video Generation, Simulation Researchers, startup founders, industry practitioners, and investors are all welcome. If you'd like to be a lightning talk speaker or panelist, please message @junfanzhu98 or 📧 junfanzhu98@gmail.com Include: • Name Affiliation • Lightning Talk Abstract, or Proposed Panel Discussion Topics 👉🏻 RSVP: luma.com/l1g9c2l1 Looking forward to bringing together the robotics and embodied AI community for an evening of technical discussion, networking, and collaboration. #Robotics #EmbodiedAI #WorldModels #PhysicalAI #HumanoidRobots #DexterousManipulation #DeepTechWeek #ArtificialIntelligence #MachineLearning #Startup

📚 @saturdayrobotic Robotics & World Models Reading Club 17: Soft Tactile-Centric Multimodal Intelligence Toward Safe and Dexterous Manipulation — San Francisco 07/11 👉🏻RSVP: luma.com/e53zawq2 Keynote: Quan Luu, Postdoctoral Researcher @LifeAtPurdue ​As robots transition from structured industrial settings to unstructured environments, they are required to interact with humans and objects in a safe and effective manner. However, achieving robust and safe operation remains a major challenge due to the limited understanding of physical contact. In this seminar, I present my research on advancing embodied robot intelligence through tactile-centric multimodal sensing, perception, and learning. I first introduce the design of soft sensorized robotic components that integrate tactile feedback with proximity and visual sensing to capture rich physical interaction signals. I then demonstrate how these capabilities are integrated into learning and control frameworks to enable reactive manipulation and contact-rich behaviors. Together, this work illustrates how the integration of soft sensorized robot bodies with multimodal perception and control enables safe and adaptive robot behavior while improving overall contact-rich manipulation performance. Pre-Readings: • ManiFeel preprint & project: arxiv.org/pdf/2505.18472 | zhengtongxu.github.io/manife… • Vision-Based Proximity and Tactile Sensing for Robot Arms: Design, Perception, and Control. IEEE T-RO, 2025 • Simulation, Learning, and Application of Vision-Based Tactile Sensing at Large Scale. IEEE T-RO, 2023 • Learning Tactile-Aware Quadrupedal Loco-Manipulation Policies. arXiv:2604.27224v2 • CONTACT: CONtact-aware TACTile Learning for Robotic Disassembly. arXiv:2603.08560v1 Location: San Francisco (Downtown) Date & Time: Saturday, July 11, 2026 | 2:00 PM – 5:00 PM Hosts: @junfanzhu98 & @aurorafeng_01 Agenda 2:00 PM – 2:30 PM: Doors open & social 🍓 Food, beverages & UNLIMITED strawberries (official Reading Club fruit!) 2:30 PM – 4:00 PM: Keynote by Quan Luu 4:00 PM – 5:00 PM: Q&A open-floor roundtable (10–20 min per topic) — spotlight any paper or technical deep-dive you want to discuss Past sessions have brought together researchers & engineers from Boston Dynamics, Google DeepMind, NVIDIA, Stanford, UC Berkeley, Physical Intelligence, Tesla, Rhoda AI, Dyna, Generalist and leading Bay Area robotics startups. Spots are limited — please arrive by 2:00 PM for check-in. Keynote starts promptly at 2:30 PM. Join the Saturday Robotics Discord for RSVP, updates & community: discord.gg/WH7DrTHRXK Follow @saturdayrobotic for more frontier robotics & world models content. Come ready to discuss soft tactile sensing, multimodal perception, contact-rich control, safe dexterous manipulation, and the path to reliable embodied intelligence in the real world! 👉🏻RSVP: luma.com/e53zawq2 #Robotics #WorldModels #EmbodiedAI #TactileSensing #DexterousManipulation #SafeRobotics #ContactRich #SFTech

LinkerBot’s robotic hand demonstrates a key challenge in humanoid robotics: dexterous manipulation. In this video, the hand removes a nut-like component by rotating it with its fingers. This may look simple at first, but it requires coordinated finger motion, precise contact control, grip adjustment, and stable force application. For humanoid robots, mobility gets much of the attention, but hands are where many real-world tasks become possible. Assembly, maintenance, tool handling, and object manipulation all depend on this level of fine motor control. 🎥 via LinkerBot ℹ️ This content is shared for informational purposes only. All intellectual property rights belong to their respective owners. #LinkerBot #RoboticHand #DexterousManipulation #HumanoidRobot #HumanoidRobotics #Robotics #EmbodiedAI #RobotManipulation #Automation #IndustrialRobotics #AI #FutureOfWork

#ICRA2026 highlights: - @leto__jean and the @NVIDIARobotics team featured the Sharpa Wave in their SimToolReal and EgoScale talks 🙏 - We caught up with researchers and partners from around the world - North handed out Austrian chocolates 🍫 - There were many kids in the audience. Austria starts teaching robotics early 👀 See you at RSS! #ICRA2026 #AIRobotics #Robotics #IEEE #DexterousManipulation #TactileAI #Vienna #SharpaNorth #SharpaWave #DexterousHand

Robotics Night is coming to Seoul 🇰🇷🤖 Presenting at #ICML2026? Deep into robotics AI? Come spend an evening with fellow researchers at RLWRLD's Seoul research lab on July 8: live RLDX-1 demos on real robot hands, drinks, and casual talk with the people building the model. 👇🏻 🤝 Who you'll meet: ICML authors and presenters across VLA, world models, manipulation, and dexterity, mingling with the RLWRLD researchers who built RLDX-1 🤖 Live RLDX-1 demos on real robot hands, our dexterity-first foundation model for true five-finger dexterity 📍 July 8 (Wed), 7:30 PM · RLWRLD Lab, Gangnam, Seoul (2 blocks from COEX where ICML2026 is) 🎟️ Invite-only, seats are limited Want in? Find someone from RLWRLD at ICML, or DM @junh0ch0 (Jacey) and we'll get you on the list. 👀 Preview of what runs live that night 👉 youtube.com/watch?v=H90bt8S8… Here's our story 👉 youtube.com/watch?v=KRD9yMqP… Check out the RLDX-1 tech blog 👉 rlwrld.ai/rldx-1 #RLDX #RLWRLD #ICML2026 #PhysicalAI #Robotics #DexterousManipulation #RoboticsFoundationModel #VLA #WorldModel

More data isn't always better. New research shows consistency may be the secret to robot dexterity. bit.ly/4vrLX8z #RobotLearning #DexterousManipulation #RoboticsAI

During ICRA 2026, we hosted a salon bringing together researchers, founders, and industry partners. Our founder, Yunzhe Pan, shared the story behind Wuji Tech. The conversation moved beyond just our product, extending to data, training systems, Sim-to-Real, and commercialization in embodied AI. While the questions varied, they all focus on one truth: what it takes to make embodied intelligence work in the real world. Thank you to everyone who joined and shared their perspectives. #ICRA2026 #Robotics #EmbodiedAI #WujiTech #WujiHand #DexterousaHand #DexterousManipulation

Touch alone isn’t enough. 🖐️ For robotics, tactile intelligence truly levels up when touch gains spatial meaning. At #ICRA2026, we dove into the core concept behind SaTA: Spatially-anchored Tactile Awareness for robust, dexterous manipulation. Read it here: arxiv.org/html/2510.14647v1. The challenge is fundamental: a robot shouldn’t just register a touch, it needs to understand exactly where that contact occurs relative to its fingers, joints, and overall hand structure. This is the missing link that turns raw data into precise, real-time adjustments during manipulation. Why does this matter? Because the most complex part of any manipulation task happens when vision is at its least reliable, that final millimeter before insertion, sliding, gripping, or fine-tuning. At Sharpa, this is exactly why we’re building tactile hands and tactile AI in tandem. 🚀 #Sharpa #Robotics #EmbodiedAI #TactileIntelligence #ICRA2026 #DexterousManipulation 📷