SafeDriveVLA（世界模型组件） · 项目原始材料
核对原文摘录 · 4 段，支持 6 项资料
原阅读方向 / 输入什么 / 输出什么
predicts future driving representations from the current observation and a sequence of ego actions, following V-JEPA 2 AC [[3](#bib.bib36)].一句话认识
our predictor rolls out under a hypothetical action sequence executing the current navigation signal.动作是否影响预测
action-conditioned predictor trained from scratch over a 2.5 s horizon at 2 Hz under teacher-forced and autoregressive losses.材料说明的限制
the action anchors are defined per meta-command and do not encode speed