FSUNav: A Cerebrum-Cerebellum Architecture for Fast, Safe, and Universal Zero-Shot Goal-Oriented Navigation
This work solves navigation challenges for heterogeneous robots, offering improved generalization and safety, though it appears incremental as it builds on existing vision-language models and reinforcement learning methods.
The paper tackled the problem of vision-language navigation by addressing bottlenecks in robot compatibility, real-time performance, and safety, proposing FSUNav, which achieved state-of-the-art results on benchmarks like MP3D, HM3D, and OVON, with real-world deployments validating its robustness.
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.