Reproduce “VP-EVT: Active Visibility Preservation for Embodied Visual Tracking” 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

Yanci Wen, Tianle Zeng, Jianwei Peng, Weixi Situ, Hanjing Ye, Hong Zhang

VP-EVT adds visibility-preserving control to a frozen robot follower by predicting whether pedestrians will persistently block the target along planned waypoints, then selectively changing the robot’s viewpoint. On OccEVT-Bench Risk episodes, it achieves 77.5% success, versus 35.0% for OA-VAT, while reducing visibility deficit and longest target loss. Its collision-free rate is 90.5%, below OmTrackVLA’s 97.5%.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.