End-to-end autonomous driving faces persistent challenges in both generating diverse, rule-compliant trajectories and robustly selecting the optimal path from these options via learned, multi-faceted evaluation. To address these challenges, we introduce HMAD, a framework integrating a distinctive Bird's-Eye-View (BEV) based trajectory proposal mechanism with learned multi-criteria scoring. HMAD leverages BEVFormer and employs learnable anchored queries, initialized from a trajectory dictionary and refined via iterative offset decoding (inspired by DiffusionDrive), to produce numerous diverse and stable candidate trajectories. A key innovation, our simulation-supervised scorer module, then evaluates these proposals against critical metrics including no at-fault collisions, drivable area compliance, comfortableness, and overall driving quality (i.e., extended PDM score). Demonstrating its efficacy, HMAD achieves a 44.5% driving score on the CVPR 2025 private test set. This work highlights the benefits of effectively decoupling robust trajectory generation from comprehensive, safety-aware learned scoring for advanced autonomous driving.
@article{arxiv.2505.23129,
title = {HMAD: Advancing E2E Driving with Anchored Offset Proposals and Simulation-Supervised Multi-target Scoring},
author = {Bin Wang and Pingjun Li and Jinkun Liu and Jun Cheng and Hailong Lei and Yinze Rong and Huan-ang Gao and Kangliang Chen and Xing Pan and Weihao Gu},
journal= {arXiv preprint arXiv:2505.23129},
year = {2025}
}