Reproduce “World SLAM Model: Joint World Modeling for SLAM and Navigation” 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
Minghui Qin, Yijun Yuan, Weicheng Zheng, Kenan Li, Weibang Wang, Chang Sun, Junhao Huang, Anmin Liu and 2 more
WSM integrates SLAM into a navigation model that predicts future RGB views, estimates their motion and geometry, and updates persistent spatial state from new camera observations. It replans while a controller executes short pose-path prefixes. On InternVLA-N1, WSM reaches 70.3% Home Success Rate versus 59.6% for LoGoPlanner, but evaluation is simulated and its cache grows with history.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.