VLAExpertSample brief
π0.5: a Vision-Language-Action Model with Open-World Generalization
Co-training a VLA on heterogeneous data (multi-robot, web, high-level subtask labels) lets a mobile manipulator clean unseen homes end-to-end.
Research
Papers
New robotics and physical-AI papers, with what each one means for the industry.
Humanoid controlIntermediateSample brief
A Dual-System Vision-Language-Action Architecture for Whole-Upper-Body Humanoid Control
A slow VLM planner (7–9 Hz) and a fast visuomotor policy (200 Hz) control a full humanoid upper body from language.
LocomotionExpertSample brief
Massively Parallel Sim-to-Real for Humanoid Locomotion
RL policies trained in GPU simulation transfer zero-shot to a commodity humanoid on rough terrain.
TactileBeginnerSample brief
Tactile Sensing for Dexterous Robot Hands: A Survey
Survey of sensor modalities, coverage and learning methods for in-hand manipulation.
World modelsIntermediateSample brief
Learning World Models from Egocentric Video for Home Robots
A video world model trained on robot egocentric footage predicts outcomes of actions for evaluation and planning.
PolicyBeginnerSample brief
Safety Standards and Deployment Patterns of Collaborative Robots in Korean SMEs
Cobot adoption in Korean SMEs is limited by integration cost more than by unit price.
Topic pages
Papers come from arXiv robotics feeds. Where our summary is not written yet, you see the opening lines of the abstract.