Reproduce “Towards Path-Creative Navigation: Robot Navigation through Embodied Interaction” 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
Haoyu Xi, Siwei Cheng, Xiangyuan Liu, Brenda Li, Wei Zhang
Path-Creative Navigation (PCN) lets a mapless robot decide when to alter its surroundings while navigating. It combines visual semantics, depth, LiDAR geometry, and odometry to interact only with actionable objects that block its route and cannot be safely bypassed. It achieved 93.57% simulated task success and 80% success in a 10-trial real-world manipulation task, within the tested settings.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.