Problem
Research questions and friction points this paper is trying to address.
Future-aware
Autonomous Driving
Planning Gains
Proposal Ordering
Driving Performance
From Proxy Learning to Driving Decisions: A Transfer-Based Framework for Evaluating Future-Aware Autonomous Driving Planners
🤖 AI Summary
研究提出Proxy-to-Decision Transfer框架，通过分析未来信息学习对驾驶性能的影响，验证自主驾驶规划器的改进是否可靠。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Proxy-to-Decision Transfer
future-aware autonomous driving
reliability-constrained validation
decision-transfer decomposition
driving-performance improvement
🔎 Similar Papers
No similar papers found.
