EMS-Nav: Embodied Multi-Scale Navigation
cs.RO, cs.AI, cs.CV
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- Qwen3-VL Technical Report
- One Map to Find Them All: Real-time Open-Vocabulary Mapping for Zero-shot Multi-Object Navigation
- ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning
- Visual Language Maps for Robot Navigation
- LERF: Language Embedded Radiance Fields
- GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation
- FindAnything: Open-Vocabulary and Object-Centric Mapping for Robot Exploration in Any Environment
- LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation
- OpenScene: 3D Scene Understanding with Open Vocabularies
- LangSplat: 3D Language Gaussian Splatting
- Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI
- DF Louvain: Fast Incrementally Expanding Approach for Community Detection on Dynamic Graphs
- KeySG: Hierarchical Keyframe-Based 3D Scene Graphs
- SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
- Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
- Faster Segment Anything: Towards Lightweight SAM for Mobile Applications
- Multi-Scale Gaussian-Language Map for Zero-shot Embodied Navigation and Reasoning
- Fast Segment Anything
- Memory Over Maps: 3D Object Localization Without Reconstruction
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation