Cover Image

$NavA^3$: Understanding Any Instruction, Navigating Anywhere, Finding Anything

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Lingfeng, Hao, Xiaoshuai, Tang, Yingbo, Fu, Haoxiang, Zheng, Xinyu, Wang, Pengwei, Wang, Zhongyuan, Ding, Wenbo, Zhang, Shanghang
Format:	Preprint
Published:	2025
Subjects:	Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Video-CoT: A Comprehensive Dataset for Spatiotemporal Understanding of Videos Based on Chain-of-Thought
by: Zhang, Shuyi, et al.
Published: (2025)

MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigation
by: Zhang, Lingfeng, et al.
Published: (2025)

AffordGrasp: In-Context Affordance Reasoning for Open-Vocabulary Task-Oriented Grasping in Clutter
by: Tang, Yingbo, et al.
Published: (2025)

SocialNav-Map: Dynamic Mapping with Human Trajectory Prediction for Zero-Shot Social Navigation
by: Zhang, Lingfeng, et al.
Published: (2025)

Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation
by: Zhang, Lingfeng, et al.
Published: (2025)

Describe Anything Anywhere At Any Moment
by: Gorlo, Nicolas, et al.
Published: (2025)

The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms
by: Kong, Lingdong, et al.
Published: (2026)

Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models
by: Tan, Huajie, et al.
Published: (2025)

Learning to Navigate Socially Through Proactive Risk Perception
by: Xiao, Erjia, et al.
Published: (2025)

RoboAfford++: A Generative AI-Enhanced Dataset for Multimodal Affordance Learning in Robotic Manipulation and Navigation
by: Hao, Xiaoshuai, et al.
Published: (2025)

Team Xiaomi EV-AD VLA: Caption-Guided Retrieval System for Cross-Modal Drone Navigation -- Technical Report for IROS 2025 RoboSense Challenge Track 4
by: Zhang, Lingfeng, et al.
Published: (2025)

Hearing Anything Anywhere
by: Wang, Mason, et al.
Published: (2024)

PIGEON: VLM-Driven Object Navigation via Points of Interest Selection
by: Peng, Cheng, et al.
Published: (2025)

Walk With Me: Long-Horizon Social Navigation for Human-Centric Outdoor Assistance
by: Zhang, Lingfeng, et al.
Published: (2026)

The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
by: Kong, Lingdong, et al.
Published: (2024)

Tracking and Segmenting Anything in Any Modality
by: Zhang, Tianlu, et al.
Published: (2025)

Hearing Anywhere in Any Environment
by: Liu, Xiulong, et al.
Published: (2025)

AnyNav: Visual Neuro-Symbolic Friction Learning for Off-road Navigation
by: Fu, Taimeng, et al.
Published: (2025)

Depth Anything with Any Prior
by: Wang, Zehan, et al.
Published: (2025)

METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model
by: Fu, Yankai, et al.
Published: (2025)

Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding
by: Tang, Yiwen, et al.
Published: (2024)

Nav-R1: Reasoning and Navigation in Embodied Scenes
by: Liu, Qingxiang, et al.
Published: (2025)

InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment
by: Long, Yuxing, et al.
Published: (2024)

NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions
by: Yang, Haolin, et al.
Published: (2025)

Say Anything with Any Style
by: Tan, Shuai, et al.
Published: (2024)

Weather-Conditioned Branch Routing for Robust LiDAR-Radar 3D Object Detection
by: Li, Hongsheng, et al.
Published: (2026)

AnyImageNav: Any-View Geometry for Precise Last-Meter Image-Goal Navigation
by: Deng, Yijie, et al.
Published: (2026)

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

Place Anything into Any Video
by: Liu, Ziling, et al.
Published: (2024)

Anything in Any Scene: Photorealistic Video Object Insertion
by: Bai, Chen, et al.
Published: (2024)

Structurally Prune Anything: Any Architecture, Any Framework, Any Time
by: Wang, Xun, et al.
Published: (2024)

X-SAM: From Segment Anything to Any Segmentation
by: Wang, Hao, et al.
Published: (2025)

Create Anything Anywhere: Layout-Controllable Personalized Diffusion Model for Multiple Subjects
by: Li, Wei, et al.
Published: (2025)

Deep Instruction Tuning for Segment Anything Model
by: Huang, Xiaorui, et al.
Published: (2024)

Segment Any Motion in Videos
by: Huang, Nan, et al.
Published: (2025)

SAM 2++: Tracking Anything at Any Granularity
by: Zhang, Jiaming, et al.
Published: (2025)

TopoNav: Topological Graphs as a Key Enabler for Advanced Object Navigation
by: Liu, Peiran, et al.
Published: (2025)

Motion Anything: Any to Motion Generation
by: Zhang, Zeyu, et al.
Published: (2025)

NavBench: Probing Multimodal Large Language Models for Embodied Navigation
by: Qiao, Yanyuan, et al.
Published: (2025)

Compress Any Segment Anything Model (SAM)
by: Fan, Juntong, et al.
Published: (2025)