Reproduce “FootQuery: Future-Touchdown-Guided Retrieval from Depth History for Perceptive Humanoid Locomotion” 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
Tao Dong, Jia Yu, Yuxuan Fan, Linna Zhao, Jiaqi Gong, Andong Yang, Chao Gao, Guyue Zhou
FootQuery addresses humanoid locomotion over terrain that may leave the camera’s view before touchdown. It predicts each foot’s next contact and uses those predictions to query retained depth images, with training supervision from realized contacts. At a 50-cm gap, it achieves 94% success versus 34% for NoFootQuery, but that ablation removes multiple paths and does not isolate retrieval alone.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.