Jul 2026
MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving
End-to-end autonomous driving systems commonly follow a cascaded two-stage pipeline where a perception stage compresses multi-modal sensor inputs into a compact context and a downstream planner predicts trajectories conditioned on this context. We argue that this one-way perception-to-planning interface forces sensor i...
Zhijing Cheng, Xuan Zhang, Donglin Di et al.
· arXiv.org · 0 citations