OpenFrontier: General Navigation with Visual-Language Grounded Frontiers
This work provides a training-free, generalizable navigation framework for mobile robots, which could benefit researchers and practitioners by reducing the need for extensive data collection and task-specific training.
This paper addresses open-world robot navigation by formulating it as a sparse subgoal identification and reaching problem, using visual-language grounded frontiers as semantic anchors. The proposed OpenFrontier framework achieves efficient, training-free navigation without dense 3D mapping or policy fine-tuning, demonstrating strong zero-shot performance on benchmarks and real-world deployment.
Open-world navigation requires robots to make decisions in complex everyday environments while adapting to flexible task requirements. Conventional navigation approaches often rely on dense 3D reconstruction and hand-crafted goal metrics, which limits their generalization across tasks and environments. Recent advances in vision--language navigation (VLN) and vision--language--action (VLA) models enable end-to-end policies conditioned on natural language, but typically require interactive training, large-scale data collection, or task-specific fine-tuning with a mobile agent. We formulate navigation as a sparse subgoal identification and reaching problem and observe that providing visual anchoring targets for high-level semantic priors enables highly efficient goal-conditioned navigation. Based on this insight, we select navigation frontiers as semantic anchors and propose OpenFrontier, a training-free navigation framework that seamlessly integrates diverse vision--language prior models. OpenFrontier enables efficient navigation with a lightweight system design, without dense 3D mapping, policy training, or model fine-tuning. We evaluate OpenFrontier across multiple navigation benchmarks and demonstrate strong zero-shot performance, as well as effective real-world deployment on a mobile robot.