R-2R-CE

The 'R-2R-CE' dataset/benchmark is used to evaluate vision-and-language navigation systems by providing a set of tasks that require grounding natural-language instructions into navigation actions in complex environments.

Papers using R-2R-CE (9)

P2DNav: Panorama-to-Downview Reasoning for Zero-shot Vision-and-Language Navigation2026SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning2026What Limits Vision-and-Language Navigation ?2026SpatialAnt: Autonomous Zero-Shot Robot Navigation via Active Scene Reconstruction and Visual Anticipation2026MapDream: Task-Driven Map Learning for Vision-Language Navigation2026One Agent to Guide Them All: Empowering MLLMs for Vision-and-Language Navigation via Explicit World Representation2026NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Prediction2025D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation2025ETP-R1: Evolving Topological Planning with Reinforcement Fine-tuning for Vision-Language Navigation in Continuous Environments2025