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

TL;DR

ABot-N0 is a unified foundation model for embodied navigation that integrates vision, language, and action to perform multiple tasks with state-of-the-art performance, supported by extensive data and hierarchical reasoning architecture.

Contribution

Introduces ABot-N0, a novel VLA foundation model with a hierarchical architecture and large-scale data engine, unifying multiple navigation tasks and achieving SOTA results.

Findings

Achieves new SOTA across 7 benchmarks.

Outperforms specialized models significantly.

Enables robust long-horizon navigation in real-world environments.

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.