Nav-R1：具身場景中的推理與導航

摘要

具身導航要求智能體在複雜的三維環境中整合感知、推理和行動，以實現穩健的交互。現有方法常因推理軌跡的不連貫與不穩定而阻礙了跨多樣環境的泛化能力，且在平衡長時程語義推理與低延遲控制以實現實時導航方面存在困難。為應對這些挑戰，我們提出了Nav-R1，一個統一具身環境中推理的基礎模型。首先，我們構建了Nav-CoT-110K，一個大規模的逐步思維鏈（CoT）數據集，專為具身任務設計，支持基於結構化推理的冷啟動初始化。在此基礎上，我們設計了一個基於GRPO的強化學習框架，包含格式、理解和導航三種互補獎勵，以提升結構遵循性、語義接地性和路徑保真度。此外，我們引入了“快慢分離”推理範式，將深思熟慮的語義推理與低延遲的反應控制解耦，實現高效且連貫的導航。在具身AI基準上的廣泛評估表明，Nav-R1在推理和導航性能上平均提升超過8%，持續超越強基準。在移動機器人上的實際部署進一步驗證了其在有限機載資源下的魯棒性。代碼：https://github.com/AIGeeksGroup/Nav-R1。網站：https://aigeeksgroup.github.io/Nav-R1。

English

Embodied navigation requires agents to integrate perception, reasoning, and action for robust interaction in complex 3D environments. Existing approaches often suffer from incoherent and unstable reasoning traces that hinder generalization across diverse environments, and difficulty balancing long-horizon semantic reasoning with low-latency control for real-time navigation. To address these challenges, we propose Nav-R1, an embodied foundation model that unifies reasoning in embodied environments. We first construct Nav-CoT-110K, a large-scale dataset of step-by-step Chains-of-Thought (CoT) for embodied tasks, which enables cold-start initialization with structured reasoning. Building on this foundation, we design a GRPO-based reinforcement learning framework with three complementary rewards: format, understanding, and navigation, to improve structural adherence, semantic grounding, and path fidelity. Furthermore, we introduce a Fast-in-Slow reasoning paradigm, decoupling deliberate semantic reasoning from low-latency reactive control for efficient yet coherent navigation. Extensive evaluations on embodied AI benchmarks demonstrate that Nav-R1 consistently outperforms strong baselines, with over 8% average improvement in reasoning and navigation performance. Real-world deployment on a mobile robot further validates its robustness under limited onboard resources. Code: https://github.com/AIGeeksGroup/Nav-R1. Website: https://aigeeksgroup.github.io/Nav-R1.

Nav-R1：具身場景中的推理與導航

Nav-R1: Reasoning and Navigation in Embodied Scenes

摘要

Support