Reproduce “Caging Vision-Language Navigation for Legged Robots via Barrier-Certified Safety Architecture” 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
Abhijeet M. Kulkarni, Saimouli Katragadda, Yuze Du, Zijun Sha, Guoquan Huang
The authors introduce a physical-grounding cage for language-guided legged navigation, mapping proposed goals to sensed geometry and checking motion with a discrete exponential barrier function (dEBF). On a Unitree G1, 20 trials per condition with JPS enabled showed collisions fell from 100% to 0% when dEBF was added to MPPI. This guarantee assumes a sensed map and planar model.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.