ROCVSep 13, 2025

Nav-R1: Reasoning and Navigation in Embodied Scenes

arXiv:2509.10884v129 citationsh-index: 7Has Code
Originality Incremental advance
AI Analysis

This addresses the challenge of robust real-time navigation for embodied agents in complex 3D environments, representing a strong domain-specific advancement.

The paper tackles the problem of incoherent reasoning and unstable navigation in embodied AI by proposing Nav-R1, a foundation model that unifies reasoning with a Fast-in-Slow paradigm and GRPO-based reinforcement learning, achieving over 8% average improvement in reasoning and navigation performance on benchmarks.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes