Reproduce “AsymEEF: Bimanual Manipulation with Asymmetric End Effectors” 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
Xiaokang Sun, Ningyue Wang, Kunqi Xu, Guangqi Jiang, Jianglong Ye, Yong Wu, Xueyan Zou
AsymEEF transfers bimanual demonstrations between heterogeneous robot hand pairs by translating source wrist and hand states into target-specific commands and replaying full tasks, retaining only successful trajectories. A shared encoder and morphology-conditioned decoder support this mapping. Across six real tabletop tasks, its mean Replay SR is 88.7%, versus 20.8% for LAD and 45.2% for CEI; physical calibration remains required.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.