David Sánchez
@roboticshaper
Conformando el futuro con robótica inteligente 🦾
Here, we must mention the Protoclone, the android prototype launched by the Polish company Clone Robotics in February of this year. Protoclone features a polymer skeleton that mimics the 206 bones of a human. Encasing the skeleton is a humanoid artificial muscle system:…
Amazing artificial muscles The UNIST team in South Korea has developed a new type of artificial muscle that can lift over 4,000 times its own weight. It’s not only highly flexible — with a strain of 86%, more than twice that of human muscle — but also incredibly strong, with an…
Autonomous Trains - Coming Soon to a Station Near You forbes.com/sites/sabbirra… #AutonomousTrains #AutonomousVehicles #RailAutonomy
New episode: Spencer Huang is a Product Lead for @NVIDIARobotics, focusing on open-source simulation frameworks, synthetic data generation, and robot autonomy. Spencer breaks down RL breakthroughs unlocked by hardware, open-source simulation, synthetic data flywheels, the…
Carolina Parada says cross-embodiment transfer in Gemini Robotics happened much sooner than expected; different robot types learning from each other will be incredibly valuable.
Enjoyed writing this article about the State of Home PCB Manufacturing for @Hacksterio hackster.io/news/pcb-frida… h/t @stephen_hawes_ @voltera_io @BugejaCarl
Runaway AI spending renews bubble fears The massive tech companies powering the economy have already committed $400 billion to artificial intelligence projects this year, prompting expert opinions to diverge: Will this spending fuel unprecedented growth, or lead to an AI bubble?…
Now we can have self-refinement for VLAs in the real world (with the aid of a big VLM)! VLM critiques VLA rollouts and iteratively refines the commands to make it perform better.
LLMs have shown a remarkable ability to “self-refine” and learn from their mistakes via in-context learning. But in robotics, most methods are single-shot. How can we bring inference-time adaptation to robot learning? A 🧵:
By merging sensing, analytics, and autonomy across interconnected devices, the AIoT paradigm shifts from mere data collection to intelligent action, opening new directions in how systems perceive, interpret, and respond to their environments. Microblog by @antgrasso
How Leaders Can (And Must) Keep Up With Industry 4.0 rfidjournal.com/expert-views/h… #Industry40 #RFID #IndustrialIoT
How can we create a single navigation policy that works for different robots in diverse environments AND can reach navigation goals with high precision? Happy to share our new paper, "VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable…
Most VLAs have no memory. MemER is a scalable method for giving VLAs long-term visual memory. Key ideas: - relevant info is in a small # of frames: store just a few key frames - manage & use memory at high level of abstraction, with a HL policy Paper: jen-pan.github.io/memer/
Robots need memory to handle complex, multi-step tasks. Can we design an effective method for this? We propose MemER, a hierarchical VLA policy that learns what visual frames to remember across multiple long-horizon tasks, enabling memory-aware manipulation. (1/5)
Humanoid strength check: BAAI researchers successfully trained a Unitree G1 to pull a 1,400 kg car. This impressive power demonstration falls under the THOR project, aiming for "Toward Human-level whOle-body Reaction." It’s a solid showcase of the G1's actuator torque and…
VLAs are great, but most lack long-term memory humans use for everyday tasks. This is a critical gap for solving complex, long-horizon problems. Introducing MemER: Scaling Up Memory for Robot Control via Experience Retrieval. A thread 🧵 (1/8)
Coco Robotics taps UCLA professor to lead new physical AI research lab | TechCrunch techcrunch.com/2025/10/14/coc… #PhysicalAI #Robotics #DeliveryRobots
Supplier relationship management (SRM) is the process of managing and optimizing the interactions and relationships with suppliers. What advice do you have on supplier management? #SupplierManagement #SRM #Procurement #SupplyChain everythingsupplychain.com/supplier-relat…
In a @UNLincoln lab, engineer Eric Markvicka and his team are teaching robots to heal themselves—developing electronic skin that senses, bleeds, and repairs like living tissue: asme.org/topics-resourc…
San Sebastián acogerá el Congreso de Fabricación Avanzada y Máquina Herramienta mundocompresor.com/noticias-de-ev… #FabricaciónAvanzada #máquinaherramienta
Sateliot and Nordic Enable First 5G IoT Link from LEO Satellites iotbusinessnews.com/2025/10/08/sat… #IoTPartnerships #SatelliteIoT
Unlock precise 3D object editing with NANO3D! This training-free framework offers coherent, mask-free edits for game, animation, and robotics content. It even preserves unedited regions perfectly.
The age of AI-powered humanoids is here—see how smart robots are leaving factories for your living room. 🤖 Meet your assistant: medium.com/the-ai-entrepr…
United States Trends
- 1. Jayden Daniels 24.7K posts
- 2. #RomanEmpireByBangChan 8,515 posts
- 3. ROMAN EMPIRE OUT NOW 7,787 posts
- 4. jungkook 598K posts
- 5. Dan Quinn 7,022 posts
- 6. Perle Labs 5,216 posts
- 7. #River 7,336 posts
- 8. Seahawks 38.6K posts
- 9. Sam Darnold 15.2K posts
- 10. Commanders 50.3K posts
- 11. #MondayMotivation 24.7K posts
- 12. Jake LaRavia 5,930 posts
- 13. #RaiseHail 8,834 posts
- 14. #STARDOM 4,444 posts
- 15. 60 Minutes 76.2K posts
- 16. Bronny 15.2K posts
- 17. Godzilla 43.6K posts
- 18. Marcus Smart 3,601 posts
- 19. Jovic 1,089 posts
- 20. Hayes 12.7K posts
Something went wrong.
Something went wrong.