Reproduce “DyPSI: Dynamic Physics Sensing via Joint Field and Sensor-Trajectory Generation” 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
Yizhou Zhang, Panqi Chen, Lei Cheng, Ting Zhang, Jianlong Li, Jianfeng Shi, Shikai Fang
DyPSI predicts a physical field and mobile sensor paths jointly. It represents sensor locations as fields and uses sequence-aware diffusion with correlated noise. In turbulent channel flow with 50 sensors, relative L2 error is 0.1352 versus 0.1558 for static PhySense placement, a 13.19% reduction. An oracle uses future ground truth and violates velocity limits in 89% of transitions.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.