Making space first
The robot makes space by first moving a cup out of the way.
Robotics Institute, Carnegie Mellon University
*Equal contribution; listed alphabetically by surname.
Full paper on arXiv and code on GitHub coming soon.
Rebuilding perception and motion routines for each task consumes time and model tokens. FAR lets an agent reuse tested code from a similar task on the same arm.
Five Embodied First Exam tasks. The transfer agent receives code from a solved mug-placement task (CoffeeSetupMug); the baseline receives no donor library.
Agent time is the summed duration of coding-agent turns, excluding robot execution and operator waits. Three seeds per condition, Opus 5.5 at high effort.
Videos play at 2×. Click any video to enlarge it.
Ten transfers on two Kinova Gen3 arms. The baseline receives a demonstration, calibration, and the robot interface; the transfer agent also receives the donor skill library.
Agent time is the summed duration of coding-agent turns, excluding robot execution and operator waits. Values average two seeds, Opus 5.5 at medium effort.
Videos play at 4×. Click any video to enlarge it.
The robot makes space by first moving a cup out of the way.
The robot learns to place the cup upright on the fingertip instead of along the finger.