MarvisNav: Making Memory Visible on Route Choices for Zero-Shot Object Navigation
cs.RO
Submitted: 2026-10-05
Updated: 2026-10-05
Project page: https://wangjincheng1998.github.io/MarvisNav
Sources
- How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers
- Think, Remember, Navigate: Zero-Shot Object-Goal Navigation with VLM-Powered Reasoning
- DyNaVLM: Zero-Shot Vision-Language Navigation System with Dynamic Viewpoints and Self-Refining Graph Memory
- Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models
- RF-DETR: Neural Architecture Search for Real-Time Detection Transformers
- ReMemNav: A Rethinking and Memory-Augmented Framework for Zero-Shot Object Navigation
- Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
- Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation
- Enhancing Glass Surface Reconstruction via Depth Prior for Robot Navigation
- TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-shot Object Navigation
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