R-2R-CE

The 'R-2R-CE' dataset is a large-scale benchmark containing hybrid samples used to evaluate vision-and-language navigation tasks for embodied agents.

Papers using R-2R-CE (10)

PlatonicNav: Unveiling Semantic Correspondence in Navigation with Platonic Topological Maps2026SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning2026P2DNav: Panorama-to-Downview Reasoning for Zero-shot Vision-and-Language Navigation2026LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning2026MapDream: Task-Driven Map Learning for Vision-Language Navigation2026Enhancing Vision-Language Navigation with Multimodal Event Knowledge from Real-World Indoor Tour Videos2026Efficient-VLN: A Training-Efficient Vision-Language Navigation Model2025D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation2025SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation2025ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments2023