R-2R

The 'R-2R' dataset/benchmark contains navigation tasks that require agents to follow natural language instructions in photo-realistic environments and is used to evaluate the robustness and effectiveness of vision-and-language navigation methods.

Papers using R-2R (14)

Language and Planning in Robotic Navigation: A Multilingual Evaluation of State-of-the-Art Models2025 · 1 citesImplicit Geometry Representations for Vision-and-Language Navigation from Web Videos2026Trajectory-Diversity-Driven Robust Vision-and-Language Navigation2026Does Peer Observation Help? Vision-Sharing Collaboration for Vision-Language Navigation2026Structured Observation Language for Efficient and Generalizable Vision-Language Navigation2026Global Commander and Local Operative: A Dual-Agent Framework for Scene Navigation2026DV-VLN: Dual Verification for Reliable LLM-Based Vision-and-Language Navigation2026ETP-R1: Evolving Topological Planning with Reinforcement Fine-tuning for Vision-Language Navigation in Continuous Environments2025Vision-and-Language Navigation with Analogical Textual Descriptions in LLMs2025Landmark-Guided Knowledge for Vision-and-Language Navigation2025CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation2025Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation2025Fine-Grained Instruction-Guided Graph Reasoning for Vision-and-Language Navigation2025RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation2024