Get hands-on with #PiPER-X at #RSS2026 🤖
Lightweight 6-DoF robotic arm with a highly dexterous spherical wrist for advanced #manipulation and #robotics R&D in constrained spaces.
±0.1mm repeatability • 1.5kg payload • ROS & SDK ready
📍ICC Sydney | Booth B2 | July 13–17
Congrats!👏 @sairlab_org & Robotics Institute @CarnegieMellon introduced #neurosymbolic learning for robotics long-horizon task planning, achieving lower failure rate in complex environments.
Thanks for choosing #PiPER 6-DoF robotic arm for validation!
🔗full link in comments
48 hours. Real robots. Real prototypes.
Build with AgileX #NERO 7-DoF #humanoid robotic arm at the Physical AI Hackathon!
📍Hong Kong Science Park, Aug 2–5
🏆 HK$300K prize pool
🤝 Mentors & investors
💼 Fast-track to 500 tech companies
#PhysicalAI#Robotics#Hackathon
Experience #teleoperation in action at #RSS2026!
Meet our #NERO Teleoperation Set — featuring 7-DoF humanoid arms, Universal Master Arm, and Dual-Arm Stand — built for real-world data collection and robot learning.
📍 ICC Sydney |🎪 Booth B2 |⌛ July 13-17
@RoboticsSciSys
Congrats to the TSAIL team at @Tsinghua_Uni on PACT!
Aligning diffusion policies with physical constraints, PACT achieves 31% fewer safety violations and 30.7% higher task success 👉ethan-iai.github.io/pact/
Proud that our #CobotMagic supported validation!
#Robotics#EmbodiedAI
Learn more about COBOT MAGIC! Based on Mobile ALOHA architecture, it's a mobile dual-arm teleoperation platform for embodied AI research and education 👉global.agilex.ai/products/co…
Meet our SCOUT MINI (Mecanum Wheels) — omnidirectional mobile robot ideal for agile navigation and robotics development:
🔄 Mecanum-wheel drive for 360° omni movement
🧗 10° climbing on rough terrain
⚡️ 1.5 m/s max speed
#AgileXRobotics#ScoutMini#ROS#Robotics#EmbodiedAI
Force sensing without expensive sensors? 🧠🦾
The team at @CMU_Robotics is pushing boundaries with FACTR 2, unlocking native force awareness on standard commodity hardware with <10 mins of training data.
Website: jasonjzliu.com/factr2/
Paper: arxiv.org/abs/2606.12406
Force is arguably the most overlooked ingredient in modern robot learning.
Introducing FACTR 2: it turns *any* commodity robot into a force-aware system with no force sensors required.
Train a tiny force network in <1min with <10mins of data and drop it into any existing teleop pipelines:
✅ Free force sensing for both the robot and the operator arm
✅ Makes demos higher-quality → fewer of them needed.
✅ A new force-aware learning algorithm (FIRST) uses those recovered forces to figure out which parts of a demo actually matter, making learning data-efficient.
✅ Strong performance on complex tasks with fewer demos and even no pretraining!
More details below.