[
    {
        "id": "osp-15587",
        "type": "article-journal",
        "title": "Beyond Waypoint Regression: Query-Based Cost Learning over Reachable Ego Futures for End-to-End Driving",
        "author": [
            {
                "family": "Abouelazm",
                "given": "Ahmed"
            },
            {
                "family": "Polley",
                "given": "Rupert"
            },
            {
                "family": "Zhang",
                "given": "Qingyuan"
            },
            {
                "family": "Wu",
                "given": "Yin"
            },
            {
                "family": "Schörner",
                "given": "Philip"
            },
            {
                "family": "Esselborn",
                "given": "Carl"
            },
            {
                "family": "Zöllner",
                "given": "J. Marius"
            }
        ],
        "URL": "https://omanscience.com/en/articles/beyond-waypoint-regression-query-based-cost-learning-over-reachable-ego-futures-for-end-to-end-driving",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "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."
    }
]