The Year in AI Papers
The year/Independent research

Paper 2607.10383

ABot-N1: Toward a General Visual Language Navigation Foundation Model

Ruiyan Gong, Yingnan Guo, Junjun Hu, Jintao Kong, Xiaoxu Leng, Tianlun Li, Weize Li, Fei Liu, Zhicheng Liu, Jia Lu, Minghua Luo, Chenlin Ming, et al.

Published
Jul 2026
Research lab
Independent
Citations
0
GitHub
Not linked

01 In brief

Summary

ABot-N1 is a general visual language navigation foundation model from AMAP CV Lab (Alibaba Group) that decouples cognition from control using a slow-fast architecture.

The slow system (4B-parameter VLM) performs Chain-of-Thought reasoning and outputs pixel goals (affordance and target pixels) in image space, serving as a universal interface for five tasks: point-goal, object-goal, POI-goal, instruction-following, and person-following.

The fast system (2B-parameter VLM) uses these pixel anchors and textual cues to generate continuous waypoints at high frequency.

The model is trained on 30M samples with pretraining and GRPO-based post-training, and introduces two new benchmarks: ABotN-PointBench and ABotN-POIBench.

ABot-N1 achieves state-of-the-art results, including 70.89% SR on R2R-CE, 92.9% SR on outdoor point-goal, 77.3% SR on POI-goal (a 35.0-point improvement over POINav), 84.9% SR on object-goal, and 90.1% SR on person-following.

Real-world deployment on the AMap TuTu quadruped robot validates its robustness and interpretability across diverse environments.

02 From the paper

Abstract

Visual Language Navigation foundation models aim to unify deep reasoning for grounded spatial decisions with broad versatility for diverse embodied tasks. Current approaches typically achieve this integration via monolithic policies that map observations directly to actions, yet they often suffer from coordinate drift and poor handling of long-tail semantics. Furthermore, these black-box mappings lack interpretability, hindering the simultaneous achievement of generality, robustness, and transparency. We present ABot-N1, a step toward a general Visual Language Navigation foundation model, that addresses these challenges by decoupling cognition from control via a slow-fast architecture guided by dual visual-language signals. More specifically, a slow vision-language reasoner performs explicit Chain-of-Thought reasoning while producing a pixel goal. This compact set of image-space anchor points serves as a universal interface for diverse tasks, including point-goal, object-goal, poi-goal, instruction-following, and person-following. Subsequently, a fast action expert leverages both the textual cues and the pixel guidance to generate continuous waypoints at the native control frequency. By bridging high-level intents and low-level control through pixel-grounded anchors paired with explicit linguistic traces, our approach ensures robust, generalizable, and interpretable navigation across simulation and real-world benchmarks. ABot-N1 establishes new state-of-the-art records, delivering massive gains specifically in urban-scale navigation: boosting POI arrival by 35.0% (to 77.3%) and achieving 95.4%/92.9% SR in complex indoor and outdoor scenes. It also maintains superior robustness across object-reaching, person-following, and instruction-following tasks. New Point-Goal/POI-Goal benchmarks are released as open source to advance the field of urban-scale navigation.