RxR

The 'RxR' dataset is a benchmark used to evaluate Vision-Language Navigation (VLN) methods by providing natural language instructions for navigating complex environments.

Papers using RxR (4)

Structured Observation Language for Efficient and Generalizable Vision-Language Navigation2026ETP-R1: Evolving Topological Planning with Reinforcement Fine-tuning for Vision-Language Navigation in Continuous Environments2025General-Purpose Robotic Navigation via LVLM-Orchestrated Perception, Reasoning, and Acting2025Fine-Grained Instruction-Guided Graph Reasoning for Vision-and-Language Navigation2025