Research papers · Posted 2025.07.08 · Publication / acceptance: author-reported
DRO-EDL-MPC: Evidential Deep Learning-Based Distributionally Robust Model Predictive Control for Safe Autonomous Driving
DRO-EDL-MPC: Evidential Deep Learning-Based Distributionally Robust Model Predictive Control for Safe Autonomous Driving
Overview
DRO-EDL-MPC incorporates evidential estimates of perception uncertainty into distributionally robust predictive-control constraints. CARLA experiments examine how confidence-dependent conservatism balances efficient motion with caution under uncertain perception.
Publication and version information
Publication, acceptance or venue information is author-reported on arXiv. The exact source wording is preserved below.
Author-supplied source information
Author-supplied information on arXiv.
Accepted to IEEE Robotics and Automation Letters (RA-L)
Version: arXiv v3 — manuscript revision