AI RESEARCH
Trajectory-Diversity-Driven Robust Vision-and-Language Navigation
arXiv CS.CV
•
ArXi:2603.15370v1 Announce Type: new Vision-and-Language Navigation (VLN) requires agents to navigate photo-realistic environments following natural language instructions. Current methods predominantly rely on imitation learning, which suffers from limited generalization and poor robustness to execution perturbations. We present NavGRPO, a reinforcement learning framework that learns goal-directed navigation policies through Group Relative Policy Optimization.