MP-3D

The MP3D dataset is a benchmark used to evaluate Open-Vocabulary Object Navigation (OVON) by providing environments for embodied agents to locate language-specified targets.

Papers using MP-3D (10)

Drive-nav: Directional Reasoning, Inspection, And Verification For Efficient Open-vocabulary Navigation2026FSUNav: A Cerebrum-Cerebellum Architecture for Fast, Safe, and Universal Zero-Shot Goal-Oriented Navigation2026AERR-Nav: Adaptive Exploration-Recovery-Reminiscing Strategy for Zero-Shot Object Navigation2026FOM-Nav: Frontier-Object Maps for Object Goal Navigation2025Think, Remember, Navigate: Zero-Shot Object-Goal Navigation with VLM-Powered Reasoning2025Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities2025Object Navigation With Structure-semantic Reasoning-based Multi-level Map And Multimodal Decision-making LLM2025LOG-Nav: Efficient Layout-Aware Object-Goal Navigation with Hierarchical Planning2025Stairway to Success: An Online Floor-Aware Zero-Shot Object-Goal Navigation Framework via LLM-Driven Coarse-to-Fine Exploration2025WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation2025