Learning Modular Policy for Multi-Floor Object Navigation:A Factorized Framework for Diagnostic Study
cs.RO
Submitted: 2026-10-03
Updated: 2026-10-03
Comments: 9 pages, 5 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Stairway to Success: An Online Floor-Aware Zero-Shot Object-Goal Navigation Framework via LLM-Driven Coarse-to-Fine Exploration
- Multi-Floor Zero-Shot Object Navigation Policy
- ApexNav: An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusion
- VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation
- TriHelper: Zero-Shot Object Navigation with Dynamic Assistance
- VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model
- SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
- OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models
- ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings
- Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill
- FiLM-Nav: Efficient and Generalizable Navigation via VLM Fine-tuning
- Offline Visual Representation Learning for Embodied Navigation
- OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav
- PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav
- Exploitation-Guided Exploration for Semantic Embodied Navigation
- ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects
- D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement
- Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
- Faster Segment Anything: Towards Lightweight SAM for Mobile Applications
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies