Self-Supervised Online Robot-Agnostic Traversability Estimation for Open-World Environments 事件

Self-Supervised Online Robot-Agnostic Traversability Estimation for Open-World Environments arXiv:2605.28442v1 Announce Type: cross Abstract: Self-supervised online traversability estimation enables robots to continuously learn from unlabeled open-world experiences and adapt their navigation behavior toward safe and efficient trajectories. Existing approaches either rely on handcrafted proprioceptive traversability scores, limiting robot-agnosticism, or cluster prior data, preventing online lea