Event
CMU proposes Wiggle and Go rope manipulation planning method
1 reports · 1 sources
A team at Carnegie Mellon University's Robotics Institute proposes the Wiggle and Go method: the robot first briefly wiggles a rope or cable, uses an overhead camera to record the propagation of the waves, and then a computer vision algorithm tracks the motion and estimates its physical properties, on that basis planning subsequent manipulation, without the need for repeated trial and error beforehand. The model is trained entirely in simulation, and then uses motion-based property estimates from real rope wiggling to improve prediction accuracy on the real robot. The research has been accepted to the 2026 Conference on Robot Learning (CoRL), will be presented next month in Austin, and is partly funded by the U.S. National Science Foundation.
Report timeline
- CMU proposes Wiggle and Go: estimating physical properties of ropes by wiggling to plan manipulation
A team at CMU's Robotics Institute has proposed the Wiggle and Go system, in which a robot first briefly wiggles a rope or cable while an overhead camera records how the waves propagate; a computer vision algorithm then tracks the motion and estimates the object's physical properties, which are used to plan subsequent actions without repeated trial and error. The model is trained entirely in simulation, and properties are then estimated from the motion of real ropes being wiggled to improve prediction accuracy on real hardware. The research has been accepted to the 2026 Conference on Robot Learning (CoRL) and will be presented next month in Austin; it is partly funded by the U.S. National Science Foundation.
CMU Robotics Institute ·