Search papers, labs, and topics across Lattice.
This paper introduces FSD-VLN, a dual-system architecture designed to enhance aerial Vision-Language Navigation (VLN) by separating high-level semantic reasoning from low-latency flight command generation. By employing a slow stream for stable semantic extraction and a fast stream using a Diffusion Transformer for action distribution modeling, the framework significantly improves navigation success rates and reduces decision latency. Experimental results demonstrate that FSD-VLN achieves up to 2X higher success rates in unseen environments while halving the inference delay and total task runtime compared to state-of-the-art methods.
A dual-system approach in aerial navigation can double success rates and cut decision delays by over 50%, revolutionizing how UAVs interpret language instructions in real-time.
Vision-Language Navigation (VLN) enables UAV autonomous navigation in unknown environments by mapping language instructions to real-time visual inputs. Compared with GPS-dependent or pre-programmed navigation, VLN supports intuitive human-machine interaction and stronger environmental adaptability, requiring tight integration of high-level semantic reasoning and low-latency flight control.Existing methods suffer from structural misalignment between global multimodal understanding and sequential action generation, causing jittery trajectories and severe decision latency for long-horizon aerial navigation. To solve this issue, we propose FSD-VLN, a fast-slow dual-system architecture disentangling semantic reasoning and low-latency flight command generation.The framework has two asynchronous branches: a slow stream extracting stable semantic priors from pre-trained vision-language models, and a Diffusion Transformer (DiT) fast stream modeling cross-temporal action distributions to produce consistent flight outputs. We further introduce a time-aware adaptive optimizer to stabilize long-sequence training and reduce gradient oscillation.Large-scale low-altitude simulation experiments show FSD-VLN achieves up to 2X higher navigation success rates on unseen scenes than SOTA methods, while cutting single-action inference delay and total task runtime by over 50%. Our work validates the benefit of decoupled semantic-control modeling and provides a practical paradigm for long-horizon aerial VLN.
