FSUNav: A Cerebrum-Cerebellum Architecture for Fast, Safe, and Universal Zero-Shot Goal-Oriented Navigation

TL;DR

FSUNav introduces a novel cerebrum-cerebellum architecture that integrates vision-language models for fast, safe, and universal zero-shot goal-oriented navigation across diverse robotic platforms, enhancing generalization and real-time performance.

Contribution

The paper proposes a new cerebrum-cerebellum architecture that combines deep reinforcement learning and vision-language models for improved zero-shot navigation.

Findings

Achieves state-of-the-art results on MP3D, HM3D, and OVON benchmarks.

Demonstrates robust real-world deployment on various robotic platforms.

Significantly outperforms existing navigation methods in safety and efficiency.

Abstract

Current vision-language navigation methods face substantial bottlenecks regarding heterogeneous robot compatibility, real-time performance, and navigation safety. Furthermore, they struggle to support open-vocabulary semantic generalization and multimodal task inputs. To address these challenges, this paper proposes FSUNav: a Cerebrum-Cerebellum architecture for fast, safe, and universal zero-shot goal-oriented navigation, which innovatively integrates vision-language models (VLMs) with the proposed architecture. The cerebellum module, a high-frequency end-to-end module, develops a universal local planner based on deep reinforcement learning, enabling unified navigation across heterogeneous platforms (e.g., humanoid, quadruped, wheeled robots) to improve navigation efficiency while significantly reducing collision risk. The cerebrum module constructs a three-layer reasoning model and leverages VLMs to build an end-to-end detection and verification mechanism, enabling zero-shot open-vocabulary goal navigation without predefined IDs and improving task success rates in both simulation and real-world environments. Additionally, the framework supports multimodal inputs (e.g., text, target descriptions, and images), further enhancing generalization, real-time performance, safety, and robustness. Experimental results on MP3D, HM3D, and OVON benchmarks demonstrate that FSUNav achieves state-of-the-art performance on object, instance image, and task navigation, significantly outperforming existing methods. Real-world deployments on diverse robotic platforms further validate its robustness and practical applicability.