Survey and Real-World Evaluation Reveals Large Simulation-to-Reality Gap in Vision-and-Language Navigation

Jul 14, 2026

A comprehensive survey of Vision-and-Language Navigation (VLN) research organizes methods along action and model paradigms. Systematic real-world evaluation on a physical robot across ten scenes shows a monolithic RGB-only method drops from 61% success in simulation to 22% in reality, while a hierarchical framework achieves 51% real-world success. The study highlights key challenges in perception, decision-making, and control for future research.

Why it matters: This work quantifies the significant performance gap between simulation and real-world deployment in embodied navigation, emphasizing the need for more robust approaches.

Full story at: arXiv Robotics ↗