{"ID":5438910,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-02T02:11:27.934456424Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30696","arxiv_id":"2606.30696","title":"ViTL: Temporal Logic-Guided Zero-Shot Natural Language Navigation via Vision-Language Models","abstract":"Enabling robots to follow natural language commands to complete zero-shot long-horizon tasks remains challenging. It requires extracting implicit temporal and logical constraints from natural language commands and executing multiple sub-tasks accordingly. Recent zero-shot object navigation methods use vision-language models (VLMs) to guide frontier-based exploration in unknown environments, but they are limited to single-target tasks. Real-world commands such as \"Clean either the chair or the couch, then turn on the tv.\" require navigating to multiple targets in a temporally constrained order, which no existing zero-shot system can handle. We present ViTL, a framework that addresses this gap at two levels. At the task level, we use a large language model (LLM) to compile natural language commands into Linear Temporal Logic (LTL) formulas, which are then converted into Deterministic Finite Automata~(DFA) that coordinate multi-channel value maps and trigger dynamic replanning when new objects are detected. At the navigation level, we introduce directional score: rather than producing a direction-agnostic value across the entire field of view, we label frontier directions on the observation image and extract per-direction scores from the VLM. Experiments on Habitat-Matterport 3D (HM3D) show that the full framework enables zero-shot long-horizon completion of natural language navigation tasks with temporal constraints, and that directional score improves single-target navigation accuracy and efficiency over the baseline.","short_abstract":"Enabling robots to follow natural language commands to complete zero-shot long-horizon tasks remains challenging. It requires extracting implicit temporal and logical constraints from natural language commands and executing multiple sub-tasks accordingly. Recent zero-shot object navigation methods use vision-language m...","url_abs":"https://arxiv.org/abs/2606.30696","url_pdf":"https://arxiv.org/pdf/2606.30696v1","authors":"[\"Kaier Liang\",\"Hengde Dai\",\"Cristian-Ioan Vasile\"]","published":"2026-06-29T02:22:31Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.CL\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}