Reproduce “Follow-Bench: A Unified Motion Planning Benchmark for Socially-Aware Robot Person Following” 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
Hanjing Ye, Weixi Situ, Jianwei Peng, Yu Zhan, Bingyi Xia, Kuanqi Cai, Hong Zhang
Follow-Bench evaluates person-following planners across varied paths, crowds, and layouts in controlled two-dimensional simulation. It compares eight re-implemented planners. In cluttered back-following with 20 obstacles and 30 pedestrians, MPC with trajectory prediction reaches 52% success versus 44% for MPC, but has higher jerk and planning time. The benchmark assumes perfect positions when visible and does not establish real-world comfort.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.