الملخص
End-to-end planners based on waypoint regression achieve strong open-loop accuracy, but they primarily learn to mimic expert geometry and remain difficult to adapt to deployment-time safety constraints. We propose a query-based cost-learning framework that estimates bounded costs for dynamically reachable ego trajectory queries, rather than dense BEV cells or a small regressed trajectory set. Compact joint scene tokens capture coherent multimodal agent futures, while contingency-aware cost aggregation and cost-guided intra-cluster MPPI mixing convert the learned cost topology into feasible ego plans. On nuScenes, our method improves over prior cost-estimation planners such as ST-P3 and NMP, outperforms most regression baselines in collision rate, while remaining competitive in L2, and retaining an interpretable cost interface. On real-world driving logs, the proposed planner reduces collision rates compared with SparseDrive and Alpamayo without fine-tuning, while maintaining a diverse set of candidate trajectories.
الكلمات المفتاحية
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Abouelazm, A., Polley, R., Zhang, Q., Wu, Y., Schörner, P., Esselborn, C., & Zöllner, J. M. (2026). Beyond Waypoint Regression: Query-Based Cost Learning over Reachable Ego Futures for End-to-End Driving. https://omanscience.com/ar/articles/beyond-waypoint-regression-query-based-cost-learning-over-reachable-ego-futures-for-end-to-end-driving
MLA 9
Abouelazm, Ahmed, et al. "Beyond Waypoint Regression: Query-Based Cost Learning over Reachable Ego Futures for End-to-End Driving." https://omanscience.com/ar/articles/beyond-waypoint-regression-query-based-cost-learning-over-reachable-ego-futures-for-end-to-end-driving.
شيكاغو (المؤلف–التاريخ)
Abouelazm, Ahmed, Rupert Polley, Qingyuan Zhang, Yin Wu, Philip Schörner, Carl Esselborn, and J. Marius Zöllner. 2026. "Beyond Waypoint Regression: Query-Based Cost Learning over Reachable Ego Futures for End-to-End Driving." https://omanscience.com/ar/articles/beyond-waypoint-regression-query-based-cost-learning-over-reachable-ego-futures-for-end-to-end-driving.
هارفارد
Abouelazm, A., Polley, R., Zhang, Q., Wu, Y., Schörner, P., Esselborn, C. and Zöllner, J. M. (2026) 'Beyond Waypoint Regression: Query-Based Cost Learning over Reachable Ego Futures for End-to-End Driving', Available at: https://omanscience.com/ar/articles/beyond-waypoint-regression-query-based-cost-learning-over-reachable-ego-futures-for-end-to-end-driving.
فانكوفر
Abouelazm A, Polley R, Zhang Q, Wu Y, Schörner P, Esselborn C, et al. Beyond Waypoint Regression: Query-Based Cost Learning over Reachable Ego Futures for End-to-End Driving. https://omanscience.com/ar/articles/beyond-waypoint-regression-query-based-cost-learning-over-reachable-ego-futures-for-end-to-end-driving
IEEE
A. Abouelazm, R. Polley, Q. Zhang, Y. Wu, P. Schörner, C. Esselborn, and J. M. Zöllner, "Beyond Waypoint Regression: Query-Based Cost Learning over Reachable Ego Futures for End-to-End Driving," https://omanscience.com/ar/articles/beyond-waypoint-regression-query-based-cost-learning-over-reachable-ego-futures-for-end-to-end-driving.