Reproduce “LIBERO-PeRM: Benchmarking Personalized 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
Zhixu Li, Keqian Tang, Litian Gong, Jingyu Yao, Wenqian Zhang, Tianze Xu, Zehao Wang, Yuping Wang and 2 more
The authors introduce LIBERO-PeRM, a simulation benchmark that separately measures task completion and satisfaction of language-expressed preferences in household manipulation. It covers motion, skill, and user-profile preferences that can be automatically scored in LIBERO. In zero-shot tests, an off-the-shelf policy achieved 100% task success but 25% preference satisfaction on skill-preference tasks, showing the measures diverge; results do not validate real-world personalization.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.