Cover Image

ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chu, Zedong, Xie, Shichao, Wu, Xiaolong, Shen, Yanfen, Luo, Minghua, Wang, Zhengbo, Liu, Fei, Leng, Xiaoxu, Hu, Junjun, Yin, Mingyang, Lu, Jia, Guo, Yingnan, Yang, Kai, Han, Jiawei, Chen, Xu, Zhu, Yanqing, Zhao, Yuxiang, Liu, Xin, Yang, Yirong, He, Ye, Wang, Jiahang, Cai, Yang, Zhang, Tianlin, Gao, Li, Liu, Liu, Sun, Mingchao, Jiang, Fan, Wang, Chiyu, Liu, Zhicheng, Pan, Hongyu, Han, Honglin, Gu, Zhining, Yang, Kuan, Zhang, Jianfang, Jing, Di, Guan, Zihao, Guo, Wei, Liu, Guoqing, Yang, Di, Yang, Xiangpo, Yang, Menglin, Xing, Hongguang, Li, Weiguo, Xu, Mu
Format:	Preprint
Published:	2026
Subjects:	Robotics Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866914324491010048
author	Chu, Zedong Xie, Shichao Wu, Xiaolong Shen, Yanfen Luo, Minghua Wang, Zhengbo Liu, Fei Leng, Xiaoxu Hu, Junjun Yin, Mingyang Lu, Jia Guo, Yingnan Yang, Kai Han, Jiawei Chen, Xu Zhu, Yanqing Zhao, Yuxiang Liu, Xin Yang, Yirong He, Ye Wang, Jiahang Cai, Yang Zhang, Tianlin Gao, Li Liu, Liu Sun, Mingchao Jiang, Fan Wang, Chiyu Liu, Zhicheng Pan, Hongyu Han, Honglin Gu, Zhining Yang, Kuan Zhang, Jianfang Jing, Di Guan, Zihao Guo, Wei Liu, Guoqing Yang, Di Yang, Xiangpo Yang, Menglin Xing, Hongguang Li, Weiguo Xu, Mu
author_facet	Chu, Zedong Xie, Shichao Wu, Xiaolong Shen, Yanfen Luo, Minghua Wang, Zhengbo Liu, Fei Leng, Xiaoxu Hu, Junjun Yin, Mingyang Lu, Jia Guo, Yingnan Yang, Kai Han, Jiawei Chen, Xu Zhu, Yanqing Zhao, Yuxiang Liu, Xin Yang, Yirong He, Ye Wang, Jiahang Cai, Yang Zhang, Tianlin Gao, Li Liu, Liu Sun, Mingchao Jiang, Fan Wang, Chiyu Liu, Zhicheng Pan, Hongyu Han, Honglin Gu, Zhining Yang, Kuan Zhang, Jianfang Jing, Di Guan, Zihao Guo, Wei Liu, Guoqing Yang, Di Yang, Xiangpo Yang, Menglin Xing, Hongguang Li, Weiguo Xu, Mu
contents	Embodied navigation has long been fragmented by task-specific architectures. We introduce ABot-N0, a unified Vision-Language-Action (VLA) foundation model that achieves a ``Grand Unification'' across 5 core tasks: Point-Goal, Object-Goal, Instruction-Following, POI-Goal, and Person-Following. ABot-N0 utilizes a hierarchical ``Brain-Action'' architecture, pairing an LLM-based Cognitive Brain for semantic reasoning with a Flow Matching-based Action Expert for precise, continuous trajectory generation. To support large-scale learning, we developed the ABot-N0 Data Engine, curating 16.9M expert trajectories and 5.0M reasoning samples across 7,802 high-fidelity 3D scenes (10.7 $\text{km}^2$). ABot-N0 achieves new SOTA performance across 7 benchmarks, significantly outperforming specialized models. Furthermore, our Agentic Navigation System integrates a planner with hierarchical topological memory, enabling robust, long-horizon missions in dynamic real-world environments.
format	Preprint
id	arxiv_https___arxiv_org_abs_2602_11598
institution	arXiv
publishDate	2026
record_format	arxiv
spellingShingle	ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation Chu, Zedong Xie, Shichao Wu, Xiaolong Shen, Yanfen Luo, Minghua Wang, Zhengbo Liu, Fei Leng, Xiaoxu Hu, Junjun Yin, Mingyang Lu, Jia Guo, Yingnan Yang, Kai Han, Jiawei Chen, Xu Zhu, Yanqing Zhao, Yuxiang Liu, Xin Yang, Yirong He, Ye Wang, Jiahang Cai, Yang Zhang, Tianlin Gao, Li Liu, Liu Sun, Mingchao Jiang, Fan Wang, Chiyu Liu, Zhicheng Pan, Hongyu Han, Honglin Gu, Zhining Yang, Kuan Zhang, Jianfang Jing, Di Guan, Zihao Guo, Wei Liu, Guoqing Yang, Di Yang, Xiangpo Yang, Menglin Xing, Hongguang Li, Weiguo Xu, Mu Robotics Artificial Intelligence Computer Vision and Pattern Recognition Embodied navigation has long been fragmented by task-specific architectures. We introduce ABot-N0, a unified Vision-Language-Action (VLA) foundation model that achieves a ``Grand Unification'' across 5 core tasks: Point-Goal, Object-Goal, Instruction-Following, POI-Goal, and Person-Following. ABot-N0 utilizes a hierarchical ``Brain-Action'' architecture, pairing an LLM-based Cognitive Brain for semantic reasoning with a Flow Matching-based Action Expert for precise, continuous trajectory generation. To support large-scale learning, we developed the ABot-N0 Data Engine, curating 16.9M expert trajectories and 5.0M reasoning samples across 7,802 high-fidelity 3D scenes (10.7 $\text{km}^2$). ABot-N0 achieves new SOTA performance across 7 benchmarks, significantly outperforming specialized models. Furthermore, our Agentic Navigation System integrates a planner with hierarchical topological memory, enabling robust, long-horizon missions in dynamic real-world environments.
title	ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation
topic	Robotics Artificial Intelligence Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2602.11598