نسخة أولية وصول مفتوح
Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution
Visual disruptions can arise while a robot is executing a task, leaving a vision-language-action (VLA) policy to respond without knowing the disruption type or timing. We introduce Self-supervised Adaptation from Leftover Trajectories (SALT), which uses the leftover trajectory, the unexecuted part of the previous actio …