Image de couverture de livre

From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	He, Honglin, Ma, Yukai, Wu, Wayne, Zhou, Bolei
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Learning Sidewalk Autopilot from Multi-Scale Imitation with Corrective Behavior Expansion
par: He, Honglin, et autres
Publié: (2026)

UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos
par: Liu, Mingxuan, et autres
Publié: (2025)

Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation
par: Xie, Ziyang, et autres
Publié: (2025)

MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility
par: Wu, Wayne, et autres
Publié: (2024)

Towards Autonomous Micromobility through Scalable Urban Simulation
par: Wu, Wayne, et autres
Publié: (2025)

Recursive Visual Imagination and Adaptive Linguistic Grounding for Vision Language Navigation
par: Chen, Bolei, et autres
Publié: (2025)

AURA: Multimodal Shared Autonomy for Real-World Urban Navigation
par: Ma, Yukai, et autres
Publié: (2026)

SceneStreamer: Continuous Scenario Generation as Next Token Group Prediction
par: Peng, Zhenghao, et autres
Publié: (2025)

VANP: Learning Where to See for Navigation with Self-Supervised Vision-Action Pre-Training
par: Nazeri, Mohammad, et autres
Publié: (2024)

Embodied Scene Understanding for Vision Language Models via MetaVQA
par: Wang, Weizhen, et autres
Publié: (2025)

UrbanNav: Learning Language-Guided Urban Navigation from Web-Scale Human Trajectories
par: Mei, Yanghong, et autres
Publié: (2025)

SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation
par: Chen, Ziyi, et autres
Publié: (2025)

VLD: Visual Language Goal Distance for Reinforcement Learning Navigation
par: Milikic, Lazar, et autres
Publié: (2025)

Zero-shot Object-Centric Instruction Following: Integrating Foundation Models with Traditional Navigation
par: Raychaudhuri, Sonia, et autres
Publié: (2024)

CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos
par: Liu, Xinhao, et autres
Publié: (2024)

A Pragmatic VLA Foundation Model
par: Wu, Wei, et autres
Publié: (2026)

VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model
par: Wu, Pengying, et autres
Publié: (2024)

ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation
par: Chu, Zedong, et autres
Publié: (2026)

Collision-Aware Object-Goal Visual Navigation via Two-Stage Deep Reinforcement Learning
par: Wang, Hongwu, et autres
Publié: (2025)

SignNav: Leveraging Signage for Semantic Visual Navigation in Large-Scale Indoor Environments
par: Sun, Jian, et autres
Publié: (2026)

See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model
par: Feng, Yixu, et autres
Publié: (2026)

VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation agents
par: Zhao, Xunyi, et autres
Publié: (2025)

Efficient Camera Exposure Control for Visual Odometry via Deep Reinforcement Learning
par: Zhang, Shuyang, et autres
Publié: (2024)

MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning
par: Xu, Tianyu, et autres
Publié: (2025)

Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels
par: Liu, Zhizheng, et autres
Publié: (2024)

Perspective from a Higher Dimension: Can 3D Geometric Priors Help Visual Floorplan Localization?
par: Chen, Bolei, et autres
Publié: (2025)

Adaptive Articulated Object Manipulation On The Fly with Foundation Model Reasoning and Part Grounding
par: Zhang, Xiaojie, et autres
Publié: (2025)

Vision-Based Deep Reinforcement Learning of UAV Autonomous Navigation Using Privileged Information
par: Wang, Junqiao, et autres
Publié: (2024)

MetricNet: Recovering Metric Scale in Generative Navigation Policies
par: Nayak, Abhijeet, et autres
Publié: (2025)

Quadrotor Navigation using Reinforcement Learning with Privileged Information
par: Lee, Jonathan, et autres
Publié: (2025)

Structured Observation Language for Efficient and Generalizable Vision-Language Navigation
par: Peng, Daojie, et autres
Publié: (2026)

NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
par: Zhang, Jiazhao, et autres
Publié: (2024)

GPA-VGGT:Adapting VGGT to Large Scale Localization by Self-Supervised Learning with Geometry and Physics Aware Loss
par: Xu, Yangfan, et autres
Publié: (2026)

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding
par: Li, Rong, et autres
Publié: (2024)

NVSim: Novel View Synthesis Simulator for Large Scale Indoor Navigation
par: Jeong, Mingyu, et autres
Publié: (2025)

PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators
par: Zeng, Kuo-Hao, et autres
Publié: (2024)

Learning to See and Act: Task-Aware Virtual View Exploration for Robotic Manipulation
par: Bai, Yongjie, et autres
Publié: (2025)

ManiVID-3D: Generalizable View-Invariant Reinforcement Learning for Robotic Manipulation via Disentangled 3D Representations
par: Li, Zheng, et autres
Publié: (2025)

What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models
par: Deng, Tianchen, et autres
Publié: (2025)

SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation
par: Hirose, Noriaki, et autres
Publié: (2024)