# Cartender: Verifiable Language-Conditioned Driving by Learning the Drives Not Taken

- Source: arXiv cs.RO
- Published: 2026-10-22T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/uf2989hkyvw5ios76vo7xyy2s
- Original: https://arxiv.org/abs/2610.26390

## Summary

Cartender proposes Counterfactual Branching, which constructs matched and mismatched instruction-action pairs from real driving recordings without a simulator, using a vision-language model to propose alternative futures and their selecting instructions, with instructions unsupported by the scene serving as negative samples.