Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	He, Honglin, Ma, Yukai, Wu, Wayne, Zhou, Bolei
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Robotics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Learning Sidewalk Autopilot from Multi-Scale Imitation with Corrective Behavior Expansion
di: He, Honglin, et al.
Pubblicazione: (2026)

UrbanVerse: Scaling Urban Simulation by Watching City-Tour Videos
di: Liu, Mingxuan, et al.
Pubblicazione: (2025)

Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation
di: Xie, Ziyang, et al.
Pubblicazione: (2025)

MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility
di: Wu, Wayne, et al.
Pubblicazione: (2024)

Towards Autonomous Micromobility through Scalable Urban Simulation
di: Wu, Wayne, et al.
Pubblicazione: (2025)

Recursive Visual Imagination and Adaptive Linguistic Grounding for Vision Language Navigation
di: Chen, Bolei, et al.
Pubblicazione: (2025)

AURA: Multimodal Shared Autonomy for Real-World Urban Navigation
di: Ma, Yukai, et al.
Pubblicazione: (2026)

SceneStreamer: Continuous Scenario Generation as Next Token Group Prediction
di: Peng, Zhenghao, et al.
Pubblicazione: (2025)

VANP: Learning Where to See for Navigation with Self-Supervised Vision-Action Pre-Training
di: Nazeri, Mohammad, et al.
Pubblicazione: (2024)

Embodied Scene Understanding for Vision Language Models via MetaVQA
di: Wang, Weizhen, et al.
Pubblicazione: (2025)

UrbanNav: Learning Language-Guided Urban Navigation from Web-Scale Human Trajectories
di: Mei, Yanghong, et al.
Pubblicazione: (2025)

SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation
di: Chen, Ziyi, et al.
Pubblicazione: (2025)

VLD: Visual Language Goal Distance for Reinforcement Learning Navigation
di: Milikic, Lazar, et al.
Pubblicazione: (2025)

Zero-shot Object-Centric Instruction Following: Integrating Foundation Models with Traditional Navigation
di: Raychaudhuri, Sonia, et al.
Pubblicazione: (2024)

CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos
di: Liu, Xinhao, et al.
Pubblicazione: (2024)

A Pragmatic VLA Foundation Model
di: Wu, Wei, et al.
Pubblicazione: (2026)

VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model
di: Wu, Pengying, et al.
Pubblicazione: (2024)

ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation
di: Chu, Zedong, et al.
Pubblicazione: (2026)

Collision-Aware Object-Goal Visual Navigation via Two-Stage Deep Reinforcement Learning
di: Wang, Hongwu, et al.
Pubblicazione: (2025)

SignNav: Leveraging Signage for Semantic Visual Navigation in Large-Scale Indoor Environments
di: Sun, Jian, et al.
Pubblicazione: (2026)

See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model
di: Feng, Yixu, et al.
Pubblicazione: (2026)

VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation agents
di: Zhao, Xunyi, et al.
Pubblicazione: (2025)

Efficient Camera Exposure Control for Visual Odometry via Deep Reinforcement Learning
di: Zhang, Shuyang, et al.
Pubblicazione: (2024)

MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning
di: Xu, Tianyu, et al.
Pubblicazione: (2025)

Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels
di: Liu, Zhizheng, et al.
Pubblicazione: (2024)

Perspective from a Higher Dimension: Can 3D Geometric Priors Help Visual Floorplan Localization?
di: Chen, Bolei, et al.
Pubblicazione: (2025)

Adaptive Articulated Object Manipulation On The Fly with Foundation Model Reasoning and Part Grounding
di: Zhang, Xiaojie, et al.
Pubblicazione: (2025)

Vision-Based Deep Reinforcement Learning of UAV Autonomous Navigation Using Privileged Information
di: Wang, Junqiao, et al.
Pubblicazione: (2024)

MetricNet: Recovering Metric Scale in Generative Navigation Policies
di: Nayak, Abhijeet, et al.
Pubblicazione: (2025)

Quadrotor Navigation using Reinforcement Learning with Privileged Information
di: Lee, Jonathan, et al.
Pubblicazione: (2025)

Structured Observation Language for Efficient and Generalizable Vision-Language Navigation
di: Peng, Daojie, et al.
Pubblicazione: (2026)

NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
di: Zhang, Jiazhao, et al.
Pubblicazione: (2024)

GPA-VGGT:Adapting VGGT to Large Scale Localization by Self-Supervised Learning with Geometry and Physics Aware Loss
di: Xu, Yangfan, et al.
Pubblicazione: (2026)

NVSim: Novel View Synthesis Simulator for Large Scale Indoor Navigation
di: Jeong, Mingyu, et al.
Pubblicazione: (2025)

SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding
di: Li, Rong, et al.
Pubblicazione: (2024)

PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators
di: Zeng, Kuo-Hao, et al.
Pubblicazione: (2024)

Learning to See and Act: Task-Aware Virtual View Exploration for Robotic Manipulation
di: Bai, Yongjie, et al.
Pubblicazione: (2025)

ManiVID-3D: Generalizable View-Invariant Reinforcement Learning for Robotic Manipulation via Disentangled 3D Representations
di: Li, Zheng, et al.
Pubblicazione: (2025)

What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models
di: Deng, Tianchen, et al.
Pubblicazione: (2025)

SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation
di: Hirose, Noriaki, et al.
Pubblicazione: (2024)