Peking University Releases MobileVLA-R1 2.0 with RL-Enhanced Robot Control
PekingUniversity · hf · 2026-09-15
Peking University released MobileVLA-R1 2.0 on Hugging Face, coupling structured reasoning with robot control via chain-of-thought alignment and reinforcement learning to improve long-horizon mobile robot instruction following.
More from Embodied
- Tesla Cybercab Heads to Mainland China for First Public Display — XFreeze · 2026-09-15
- RewardAI's OM-1 Robot Foundation Model Zero-Shot Generalizes to Arms and Humanoids — zipengfu · 2026-09-15
- Pi robot runs fully autonomous for hours at a chocolate factory — stacking boxes was the hard part — chelseabfinn · 2026-09-15
- X Humanoid Debuts Pelican-Sim 1.0, a General World Model Simulator for Embodied AI — X-Humanoid · 2026-09-15
- General Robotics pitches AI to automate parts of robot development — VraserX · 2026-09-15
- Full fruit fly brain map, 166,700 neurons, flies a drone in real time — anselm · 2026-09-15