2602.11598v1 Feb 12, 2026 cs.RO

ABot-N0: 다목적 체화된 내비게이션을 위한 VLA 파운데이션 모델 기술 보고서

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

Zedong Chu
Zedong Chu
Citations: 91
h-index: 7
Shichao Xie
Shichao Xie
Citations: 153
h-index: 7
Xiaolong Wu
Xiaolong Wu
Citations: 134
h-index: 6
Yanfen Shen
Yanfen Shen
Citations: 22
h-index: 2
Minghua Luo
Minghua Luo
Citations: 64
h-index: 5
Zhengbo Wang
Zhengbo Wang
Citations: 14
h-index: 2
X. Leng
X. Leng
Citations: 29
h-index: 2
Junjun Hu
Junjun Hu
Citations: 89
h-index: 6
Mingyang Yin
Mingyang Yin
Citations: 206
h-index: 8
Jian Lu
Jian Lu
Citations: 29
h-index: 3
Yingnan Guo
Yingnan Guo
Citations: 19
h-index: 2
Kai Yang
Kai Yang
Citations: 40
h-index: 4
Jiawei Han
Jiawei Han
Citations: 200
h-index: 8
Xu Chen
Xu Chen
Citations: 60
h-index: 2
Yanqing Zhu
Yanqing Zhu
Citations: 10
h-index: 2
Yuxiang Zhao
Yuxiang Zhao
Citations: 19
h-index: 2
Xin Liu
Xin Liu
Citations: 21
h-index: 2
Yirong Yang
Yirong Yang
Citations: 50
h-index: 3
Ye He
Ye He
Citations: 15
h-index: 3
Jiahan Wang
Jiahan Wang
Citations: 36
h-index: 4
Yang Cai
Yang Cai
Citations: 60
h-index: 5
Tianlin Zhang
Tianlin Zhang
Citations: 16
h-index: 2
Li Gao
Li Gao
Citations: 8
h-index: 1
Liu Liu
Liu Liu
Citations: 10
h-index: 2
Min-peng Sun
Min-peng Sun
Citations: 8
h-index: 1
Fan Jiang
Fan Jiang
Citations: 30
h-index: 4
Chiyu Wang
Chiyu Wang
Citations: 50
h-index: 4
Zhichen Liu
Zhichen Liu
Citations: 8
h-index: 1
Hong-Ming Pan
Hong-Ming Pan
Citations: 28
h-index: 2
Honglin Han
Honglin Han
Citations: 29
h-index: 3
Zhining Gu
Zhining Gu
Citations: 30
h-index: 3
Kuan Yang
Kuan Yang
Citations: 19
h-index: 2
Jianfang Zhang
Jianfang Zhang
Citations: 32
h-index: 3
D. Jing
D. Jing
Citations: 14
h-index: 2
Zi-An Guan
Zi-An Guan
Citations: 11
h-index: 2
Wei Guo
Wei Guo
Citations: 34
h-index: 2
Guo-qing Liu
Guo-qing Liu
Citations: 11
h-index: 2
Dianzhe Yang
Dianzhe Yang
Citations: 9
h-index: 1
Xiangpo Yang
Xiangpo Yang
Citations: 14
h-index: 2
Meng-Yao Yang
Meng-Yao Yang
Citations: 13
h-index: 2
Hongguang Xing
Hongguang Xing
Citations: 31
h-index: 2
Weiguo Li
Weiguo Li
Citations: 13
h-index: 2
Mu Xu
Mu Xu
Citations: 82
h-index: 6
Fei Liu
Fei Liu
Citations: 39
h-index: 5

체화된 내비게이션은 오랫동안 작업 특화 아키텍처들에 의해 파편화되어 왔다. 우리는 포인트-목표(Point-Goal), 객체-목표(Object-Goal), 지시-따르기(Instruction-Following), POI-목표(POI-Goal), 그리고 사람-따르기(Person-Following) 등 5가지 핵심 작업 전반에 걸쳐 "대통합"을 달성한 통합 시각-언어-행동(VLA) 파운데이션 모델인 ABot-N0를 소개한다. ABot-N0는 의미론적 추론을 위한 LLM 기반 인지 두뇌(Cognitive Brain)와 정밀하고 연속적인 궤적 생성을 위한 플로우 매칭(Flow Matching) 기반 행동 전문가(Action Expert)를 결합한 계층적 "두뇌-행동(Brain-Action)" 아키텍처를 활용한다. 대규모 학습을 지원하기 위해, 우리는 ABot-N0 데이터 엔진을 개발하여 7,802개의 고충실도 3D 장면(10.7 $\text{km}^2$)에 걸쳐 1,690만 개의 전문가 궤적과 500만 개의 추론 샘플을 구축했다. ABot-N0는 특화 모델들을 크게 압도하며 7개의 벤치마크 전반에서 새로운 최고 성능(SOTA)을 달성했다. 더 나아가, 우리의 에이전트형 내비게이션 시스템은 계층적 위상 메모리를 갖춘 플래너를 통합하여 역동적인 실제 환경에서도 견고하고 장기적인(long-horizon) 임무 수행을 가능하게 한다.

Original Abstract

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.

9 Citations
0 Influential
4 Altmetric
29.0 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!