Motion planning for autonomous driving must account for multi-modal uncertainty in both the intentions and trajectories of surrounding vehicles. Handling uncertainty in a worst-case manner guarantees robustness but often leads to excessive conservatism. Stochastic Model Predictive Control (SMPC) reduces trajectory-level conservatism through chance constraints, yet remains conservative with respect to intention uncertainty since constraints must hold across all intentions. We present a novel combination of SMPC and the branching structure, enabling the planner to generate distinct trajectories for different possible intentions while maintaining safety under trajectory uncertainty. A novel scenario clustering is proposed to merge prediction scenarios based on high-level decision similarity, thereby ensuring real-time tractability. Furthermore, an adaptive branching-time computation postpones commitment to separate plans until intention uncertainty is sufficiently reduced. Simulation studies in challenging highway scenarios demonstrate that the proposed method improves safety, reduces conservatism, and achieves real-time computational performance.

翻译：自动驾驶运动规划必须考虑周围车辆意图和轨迹中的多模态不确定性。以最坏情况方式处理不确定性虽能保证鲁棒性，但往往导致过度保守。随机模型预测控制通过机会约束降低了轨迹层面的保守性，但针对意图不确定性仍保持保守性，因为约束必须涵盖所有意图。我们提出一种结合随机模型预测控制与分支结构的新方法，使规划器能够针对不同可能意图生成差异化轨迹，同时保证轨迹不确定性下的安全性。进一步，提出一种基于高层决策相似性合并预测场景的新型场景聚类方法，从而保障实时可解性。此外，自适应分支时间计算机制可推迟执行独立规划方案直至意图不确定性充分降低。在具有挑战性的高速公路场景仿真验证表明，所提方法提升了安全性、降低了保守性，并实现了实时计算性能。