Reproduce “TAPESIM: Efficient Simulation of Adhesive Tape Dispensing for Robotic Manipulation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zhaofeng Luo, Xinyu Lu, Jaehoon Choi, Zhehuan Chen, Trinity Chung, Xiaowen Qiu, Hugh Nicholas Perkins, Gianna Calderon and 5 more
TAPESIM models tape dispensing by representing wound tape as a rigid cluster, while a deformable collar and released strip remain flexible and reattachable. At 32 turns, clustering reduced physics-step time 4.5× under tolerances selected to match roll motion within 5%. In 100 paired Peel cases, Bond-R reached 76.3% balanced accuracy versus 50% for Coh-F; prediction was task-dependent, with limited Stick discrimination.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.