AAAI
CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model
↗
↖
Zhuoyuan Yu*
, Yuxing Long*
, Zihan Yang
, Chengyan Zeng
, Hongwei Fan
, Jiyao Zhang
, Hao Dong†
Arxiv
AAAI
CCF A
Existing vision-and-language navigation models often deviate from the correct trajectory when …