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

2026-07-11

AI Summary

Existing vision-language navigation models often suffer from coordinate drift, limited long-tail semantic understanding, and opaque decision-making, hindering their ability to simultaneously achieve generality, robustness, and interpretability. This work proposes a slow-fast dual-pathway architecture: the slow pathway performs vision-language joint reasoning with explicit chain-of-thought generation to produce pixel-level target anchors, while the fast pathway integrates textual and pixel-level guidance for high-frequency continuous control, using these pixel anchors as a unified interface to decouple high-level intent from low-level actions. The framework is the first to support diverse navigation tasks within a single system, significantly enhancing both explainability and generalization. Experiments show a 35.0% absolute improvement in city-scale POI arrival rate (reaching 77.3%), with success rates of 95.4% and 92.9% in complex indoor and outdoor scenarios, respectively, and consistently superior robustness across object reaching, person following, and instruction-following tasks.

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.

Problem

• Visual Language Navigation
• foundation model
• coordinate drift
• long-tail semantics
• interpretability

Innovation

• slow-fast architecture
• Chain-of-Thought reasoning
• pixel-goal navigation
• visual language navigation
• foundation model