Gemeinsames Audio

we proposed third-U me: Wrist-Cam-Free Robot Manipulation via Third-Person Point Clouds and Kinematic Retargeting. Using third-U me, we efficiently collect real-world data and deploy it to physical robots, enabling scalable data collection with minimal hardware for visuomotor policy learning. Third-U me employs a third-view camera without wrist cameras or electronic grippers. At only 380 grams, it is lightweight and enables 4.6 times faster data collection than 3D-mouse teleoperation.