Preprint
Aug 2026
DaViNCi: A Dataset Towards Outdoor Vision-and-Language Navigation with Continuous Actions and Dynamic Elements
The proposed DaViNCi is the first outdoor VLN dataset that simultaneously introduces both continuous and dynamic factors, and the practical value of DaViNCi in advancing outdoor VLN toward more realistic environments is demonstrated.
Zihao Xie, Pingrui Lai, Yitong Wu et al.
· 0 citations