提出PDT框架，评估自动驾驶规划中未来信息是否真能提升决策可靠性。
From Proxy Learning to Driving Decisions: A Transfer-Based Framework for Evaluating Future-Aware Autonomous Driving Planners
- 通过得分差、切换效用等分解方法定位决策损失来源
- 组件交叉熵降为0.530，选择轨迹保持率稳定在0.961
- 适合验证自动驾驶规划改进是否可信，尤其关注安全与稳健性
未来感知表征和世界模型在基于提案的自动驾驶规划器中日益普及，以提升轨迹选择效果。然而，代理目标或受限子集的改进常被误认为规划性能提升，而未验证提案排序、选定轨迹、全规模效用及关键驾驶组件。本文提出代理到决策迁移（PDT）框架，用于评估学习到的未来信息是否支持可靠的驾驶性能提升。其决策迁移分解模块通过得分差距、条件切换效用和选中与支持之间的遗憾来定位价值损失；可靠性约束验证模块要求精确配对、最小显著效应、规模扩展确认、安全不补偿、顺序可比性以及家族级鲁棒性。在使用NAVSIM-v1评估的代表性未来感知规划器上，组件二分类交叉熵从0.705降至0.530，所选PDM保持率从0.963降至0.961。一个独立候选在512条记录前缀上提升0.00909，95%置信区间为[0.000744, 0.0177]，但2048条记录及完整支持区间的置信区间包含零。提案级重放进一步验证了切换效用分解，但432个筛选配置中无一通过双半、双种子鲁棒性检验。PDT因此识别出在代理、子集、聚合与选择证据中，决策迁移失败或仍不确定的环节。
原文摘要 · Abstract (English)
Future-aware representations and world models are increasingly used in proposal-based autonomous-driving planners to improve trajectory selection. However, improvements in proxy objectives or restricted subsets are often interpreted as planning gains without verifying proposal ordering, selected trajectories, full-scale utility, and critical driving components. We propose the Proxy-to-Decision Transfer (PDT) Framework, an analysis framework that evaluates when learned future information supports a reliable driving-performance improvement claim. Its Decision-Transfer Decomposition Module localizes value loss through score margins, switch-conditioned utility, and support-versus-selection regret. Its Reliability-Constrained Validation Module requires exact pairing, a minimum meaningful effect, scale-expanded confirmation, safety non-compensation, sequential comparability, and family-level robustness. On a representative future-aware planner evaluated with NAVSIM-v1, component BCE decreases from 0.705 to 0.530 while held selected PDM decreases from 0.963 to 0.961. A separate candidate improves a 512-record prefix by 0.00909, with a scene-bootstrap 95% interval of [0.000744, 0.0177], but its 2048-record and complete-support intervals include zero. A proposal-level replay further confirms the switch-utility decomposition, yet none of 432 screened configurations passes the two-half, two-seed robustness gate. PDT therefore identifies where decision transfer fails or remains indeterminate across proxy, subset, aggregate, and selection evidence.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。