[RSS 2026] OpenFrontier: General Navigation with Visual-Language Grounded Frontiers

RSS 2026 Paper We present OpenFrontier, a simple yet effective framework for general language-conditioned robot navigation. It detects and semantically evaluates visual frontiers directly in image space and grounds them into 3D, enabling efficient zero-shot navigation across diverse goals — without dense semantic 3D mapping, policy training, or model fine-tuning. Paper: https://arxiv.org/pdf/2603.05377 Project Page: https://boysun045.github.io/OpenFrontier-Project/ Code: https://github.com/cvg/OpenFrontier Related work: FrontierNet: https://boysun045.github.io/FrontierNet-Project/