VR-Loop: Dual-Arm Rope Untangling
Manuscript under review · Second-author paper
Rope untangling requires reasoning about complex geometry: an unsuitable grasp or pull may tighten a tangle. VR-Loop treats the proposed interaction points and pulling directions as actions to be checked and refined before execution.
The framework combines visual-language reasoning, image-overlay verification, mask-based constraints, and depth-informed geometric execution for dual-arm rope manipulation.
Manuscript
Iterative Verify-and-Refine Vision-Language Agent for Reliable Dual-Arm Manipulation
Yuqi Cheng, Zhilun Hu, Cheng Jiang, Qingyu Peng, Weiming Shen.