KnotDLO: Toward Interpretable Knot Tying
This addresses the challenge of robotic manipulation of deformable objects like ropes, but it is incremental as it focuses on a specific knot-tying task with limited success rates.
The paper tackles the problem of one-handed knot tying with deformable linear objects by introducing KnotDLO, a method that plans grasp and target waypoints from the current shape without human demonstrations, achieving a 50% success rate in 16 trials for overhand knots from unseen configurations.
This work presents KnotDLO, a method for one-handed Deformable Linear Object (DLO) knot tying that is robust to occlusion, repeatable for varying rope initial configurations, interpretable for generating motion policies, and requires no human demonstrations or training. Grasp and target waypoints for future DLO states are planned from the current DLO shape. Grasp poses are computed from indexing the tracked piecewise linear curve representing the DLO state based on the current curve shape and are piecewise continuous. KnotDLO computes intermediate waypoints from the geometry of the current DLO state and the desired next state. The system decouples visual reasoning from control. In 16 trials of knot tying, KnotDLO achieves a 50% success rate in tying an overhand knot from previously unseen configurations.