NEURA launches Neuron AI, a multimodal PLA model giving robots touch, force feedback and memory
CyberRobooo · x · 2026-10-17
Germany's NEURA Robotics introduced Neuron AI, a Perception-Language-Action model that fuses 3D vision, touch, force feedback, audio, robot state and language, plus memory to track objects and task progress.
- Key idea: force feedback and touch cover what cameras miss — whether a screw's threads caught or a latch clicked — so robots can verify task completion like humans
- The model will run across five NEURA robot platforms; customers can fine-tune skills via Neuraverse and deploy across a fleet, with a "Time-to-Skill" learning-speed metric
- At NVIDIA GTC Berlin (Oct 20–22), NEURA plans to demo its 4NE1 humanoid autonomously completing an 11-minute laundry task end to end
More from Embodied
- Tesla robot demo's barrel roll called 'very Star Fox coded' — matt_slotnick · 2026-10-17
- RAX learns precision robot skills with zero teleoperation, cuts inference from 72 min to 18 s — du_yilun · 2026-10-17
- RAX open-sources everything: zero demos, all experiment sessions included — du_yilun · 2026-10-17
- RAX hits 78.3% on RoboDojo vs prior SOTA 24.9%, scores 100% on pouring where baselines get 0% — du_yilun · 2026-10-17
- Inside RAX's cognitive architecture: exploration turns into versioned robot skill repositories — du_yilun · 2026-10-17
- RAX: A Robot Cognitive Architecture That Turns Exploration into Persistent Skills — du_yilun · 2026-10-17