Beyond imitation: A generate-and-evaluate framework with spatiotemporal risk assessment for end-to-end motion planning
End-to-end motion planning for autonomous vehicles is a critical research frontier, yet prevailing imitation learning approaches are fundamentally constrained by their reliance on regressing to a single, often sub-optimal, ground-truth trajectory. This paradigm fails to address the inherent multi-modality of driving scenarios and the interactive nature of traffic, limiting the system’s ability to discover safer or more efficient behaviors. To address these limitations, we propose a novel “generate-and-evaluate” framework for end-to-end motion planning that moves beyond direct imitation. The framework uses the sparse perception and multi-modal candidate-generation foundation of SparseDrive. Its ego-centric prediction module incorporates observed ego-vehicle, surrounding-agent, map, and temporal context. Subsequently, a principled trajectory selection methodology evaluates these candidates by constructing a predictive spatiotemporal risk field and utilizing a holistic cost function that synthesizes safety, efficiency, and comfort. A core innovation is a time-weighted safety metric that enables a more nuanced and proactive risk assessment. Experimental results show lower collision rate and longitudinal acceleration RMS on mini_val than SparseDrive, with nearly unchanged aver-age speed. On val, higher average speed and lower acceleration RMS come with a higher collision rate, indicating a trade-off among the evaluated criteria.
Authors
- Jun Wang (ORCID: https://orcid.org/0000-0001-5841-0289)
- Xuewu Lin
- Fang Zhang
- Ying Liu
- Chaoyi Chen
- Yi Liu
Institutions
- Nanjing Agricultural University (CN)
Publication Details
- Journal
- Tsinghua Science & Technology
- Published
- 2026-11-18
- DOI
- https://doi.org/10.26599/tst.2026.9010104
- Primary Topic
- Autonomous Vehicle Technology and Safety
- Type
- article
- Field-Weighted Citation Impact
- 0.00