AgileX Robotics

@AgilexRobotics

Leading Mobile Robot, Robotic Arm, Unmanned System & Embodied AI Data Solution Provider 📮Contact us: [email protected]

70 Urmărește2.9K Urmăritori436 Postări
  1. AgileX Robotics@AgilexRobotics
    Introducing Our 7-DoF Robotic Arm - NERO:  Unlock Human-Like Dexterity for Your Robotics Research🤖 It delivers seamless obstacle avoidance and detour ability. 🌐 📩 Sales@agilex.ai #AgileXRobotics #NERO
    Descarcă
    225239760.3K
  2. AgileX Robotics@AgilexRobotics
    Postări @AgilexRobotics
    what you wanna see Lookie do?!
    100115
  3. AgileX Robotics@AgilexRobotics
    🏆#IROS2026 championship-winning mobile manipulation solution is now available! AgileX PiPER-X × GENISOM M1 combines end-to-end autonomy, integrated coordination, and open interfaces in one complete workflow. 📢 Demo coming soon. #MobileManipulation #Robotics
    Descarcă
    014324
  4. AgileX Robotics@AgilexRobotics
    Pick an apple with PiPER!🍎 Together with WeGo Robotics, we brought #PiPER robotic arms to the Physical AI Challenge 2026 in South Korea — putting robotics into the hands of developers to build and experiment. Learning happens by doing! #PhysicalAI #Robotics
    Descarcă
    12101K
  5. AgileX Robotics@AgilexRobotics
    Thanks to physical AI researchers, PiPER can get a brain🥹 #vla #vlm #physicalAI #robotics
    Alexander @acrosson
    Papers to watch: UniWAM The idea: stop separating "understand the world", "predict what happens next" and "act" Instead their UniWAM combines a VLM-based physical reasoner + video world model + action policy in one architecture. The model was trained on: - robot demos - human egocentric video - VQA data Results - achieved SOTA across several benchmarks: 99.2% LIBERO 92.6% LIBERO-Plus 68.3% RoboTwin Clean2Rand UniWAM The part I find most interesting: human + robot co-training appears to follow a log-linear scaling trend. Another datapoint that human video may matter a lot for scaling robot foundation models. project page:
    004909
  6. Alexander✓@acrosson
    Papers to watch: UniWAM The idea: stop separating "understand the world", "predict what happens next" and "act" Instead their UniWAM combines a VLM-based physical reasoner + video world model + action policy in one architecture. The model was trained on: - robot demos - human egocentric video - VQA data Results - achieved SOTA across several benchmarks: 99.2% LIBERO 92.6% LIBERO-Plus 68.3% RoboTwin Clean2Rand UniWAM The part I find most interesting: human + robot co-training appears to follow a log-linear scaling trend. Another datapoint that human video may matter a lot for scaling robot foundation models. project page:
    Descarcă
    131416013.8K
  7. AgileX Robotics@AgilexRobotics
    1st place of #IROS 2026 LRC in the fully autonomous category! Congrats to the team from #NTU, Singapore! With AgileX #PiPER-X + M1 from @GenisomAI, they built a highly flexible mobile manipulation solution. #roboticarm #quadruped #robotics
    Genisom AI @GenisomAI
    🏆 IROS 2026 LRC championship highlights! Nanyang Technological University took 1st place in the fully autonomous category with GENISOM M1. Watch the highlights—and special thanks to @AgilexRobotics for its robotic arm support! 👏 #GENISOMAI #IROS2026
    018591
  8. Genisom AI@GenisomAI
    🏆 IROS 2026 LRC championship highlights! Nanyang Technological University took 1st place in the fully autonomous category with GENISOM M1. Watch the highlights—and special thanks to @AgilexRobotics for its robotic arm support! 👏 #GENISOMAI #IROS2026
    Descarcă
    124652
  9. AgileX Robotics@AgilexRobotics
    All set at #IROS2026, Pittsburgh! From bimanual manipulation to teleoperation data collection. 📍Meet us at Booth #307
    Descarcă
    0215871
  10. AgileX Robotics@AgilexRobotics
    Forget leaderboards — put the models on a real robot and let them fight it out👇 Based on our #PiPER. #vla #physicalai
    Marian Pogran @MarianPogran
    @typesafeai Jev vs. GPT-6 Astra 🤖 on a real robotic task @AgilexRobotics : Task: “Put the red cube in the box.” 🔴 → 📦 ⚡ Jev 27s vs. Astra 1m 11s 💰 Jev much cheaper The arm was limited to just 10% speed for safety — at full speed, Jev’s advantage would be even more significant.
    07405.8K
  11. Marian Pogran✓@MarianPogran
    Postări @typesafeai
    @typesafeai Jev vs. GPT-6 Astra 🤖 on a real robotic task @AgilexRobotics : Task: “Put the red cube in the box.” 🔴 → 📦 ⚡ Jev 27s vs. Astra 1m 11s 💰 Jev much cheaper The arm was limited to just 10% speed for safety — at full speed, Jev’s advantage would be even more significant.
    Descarcă
    192928528.8K