A robotic eyeball gives embodied AI the power to zoom and focus
Researchers from Shanghai Jiao Tong University, CAS, and DUT just introduced EyeVLA, a biomimetic robotic eyeball for embodied AI. Unlike fixed cameras, it physically rotates and zooms in based on user instructions, turning movements into action tokens inside a vision-language model. This gives robots clear, fine-grained visual details across wide spaces without relying on expensive sensors.