Lune

CVPR Findings2026

Trajectory-Diversity-Driven Robust Vision-and-Language Navigation

Jiangyang Li, Cong Wan, SongLin Dong, Chenhao Ding, Qiang Wang, Zhiheng Ma, Yihong Gong

Abstract

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. By exploring diverse trajectories and optimizing via within-group performance comparisons, our method enables agents to distinguish effective strategies beyond expert paths without requiring additional value networks. Built on ScaleVLN, NavGRPO achieves superior robustness on R2R and REVERIE benchmarks with +3.0% and +1.71% SPL improvements in unseen environments. Under extreme early-stage perturbations, we demonstrate +14.89% SPL gain over the baseline, confirming that goal-directed RL training builds substantially more robust navigation policies. The code is available at https://github.com/cocoastar/NavGRPO.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation cites Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding
  • Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation cites History Aware Multimodal Transformer for Vision-and-Language Navigation
  • NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models cites Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation
  • NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models cites Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding
  • NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models cites History Aware Multimodal Transformer for Vision-and-Language Navigation
  • History Aware Multimodal Transformer for Vision-and-Language Navigation cites Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on45

  1. Habitat: A Platform for Embodied AI ResearchManolis Savva, Jitendra Malik, Devi Parikh, Dhruv Batra et al.ICCV 2019 · 1,863 citations
  2. History Aware Multimodal Transformer for Vision-and-Language NavigationShizhe Chen, Pierre-Louis Guhur, Cordelia Schmid, Ivan LaptevNeurIPS 2021 · 427 citations
  3. NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language ModelsGengze Zhou, Yicong Hong, Qi WuAAAI 2024 · 361 citations
  4. Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal GroundingAlexander Ku, Peter Anderson, Roma Patel, Eugene Ie et al.EMNLP 2020 · 208 citations
  5. Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language NavigationShizhe Chen, Pierre-Louis Guhur, Makarand Tapaswi, Cordelia Schmid et al.CVPR 2022 · 150 citations

Related papers

  1. Contrastive Instruction-Trajectory Learning for Vision-Language NavigationXiwen Liang, Fengda Zhu, Yi Zhu, Bingqian Lin et al.AAAI 2022 · 29 citations
  2. Vision-Language Navigation with Energy-Based PolicyRui Liu, Wenguan Wang, Yi YangNeurIPS 2024 · 39 citations
  3. Mind the Gap: Improving Success Rate of Vision-and-Language Navigation by Revisiting Oracle Success RoutesChongyang Zhao, Yuankai Qi, Qi WuACM MM 2023 · 17 citations
  4. Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' RuleShuhei Kurita, Kyunghyun ChoICLR 2021 · 29 citations
  5. A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation LearningAishwarya Kamath, Peter Anderson, Su Wang, Jing Yu Koh et al.CVPR 2023
Dusk over the sea between two cliffs drawn in fine vertical lines