Vision-and-Language Navigation (VLN) in continuous environments requires agents to interpret natural language instructions while navigating unconstrained 3D spaces. Existing VLN-CE frameworks rely on a two-stage approach: a waypoint predictor to generate waypoints and a navigator to execute movements. However, current waypoint predictors struggle with spatial awareness, while navigators lack historical reasoning and backtracking capabilities, limiting adaptability. We propose a zero-shot VLN-CE framework integrating an enhanced waypoint predictor with a Multi-modal Large Language Model (MLLM)-based navigator. Our predictor employs a stronger vision encoder, masked cross-attention fusion, and an occupancy-aware loss for better waypoint quality. The navigator incorporates history-aware reasoning and adaptive path planning with backtracking, improving robustness. Experiments on R2R-CE and MP3D benchmarks show our method achieves state-of-the-art (SOTA) performance in zero-shot settings, demonstrating competitive results compared to fully supervised methods. Real-world validation on Turtlebot 4 further highlights its adaptability.
View on arXiv@article{shi2025_2503.10069,
title={ SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation },
author={ Xiangyu Shi and Zerui Li and Wenqi Lyu and Jiatong Xia and Feras Dayoub and Yanyuan Qiao and Qi Wu },
journal={arXiv preprint arXiv:2503.10069},
year={ 2025 }
}