GG-Nav: Goal-oriented Grounding Chain-of-Thought Elicits Reasoning in Navigation Foundation Models

arXiv:2610.14541 · cs.RO, cs.AI · Submitted 2026-10-10 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-10-10

Updated: 2026-10-10

Code: https://github.com/DuangZhu/GG_Nav

Project page: https://duangzhu.github.io/GG-Nav-Project-Page

Terminology

• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Grounding — 1× in this paper · explained in 3 episodes

Sources

• Qwen3-VL Technical Report
• ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects
• Learning to Map for Active Semantic Goal Navigation
• VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs
• Multimodal Perception for Goal-oriented Navigation: A Survey
• Nav-R1: Reasoning and Navigation in Embodied Scenes
• InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment
• Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning
• VGGT-$\Omega$
• Hydra-Nav: Object Navigation via Adaptive Dual-Process Reasoning
• Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation
• StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling
• VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model
• Nav-$R^2$ Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation
• Auxiliary Tasks and Exploration Enable ObjectNav
• FiLM-Nav: Efficient and Generalizable Navigation via VLM Fine-tuning
• L3MVN: Leveraging Large Language Models for Visual Target Navigation
• Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
• Embodied Navigation Foundation Model
• BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies