arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.02550eess.SYcs.SY
收藏

基于可达性的针对多模态预测的应急规划与分支MPC

Reachability-Based Contingency Planning against Multi-Modal Predictions with Branch MPC

Mohamed-Khalil Bouzidi, Bojan Derajic, Daniel Goehring, Joerg Reichardt

AI总结:

本文提出将多模态交通预测与分支MPC结合的应急规划框架,利用可达性分析对预测走廊进行剪枝聚类以降低计算复杂度,并确定最大决策推迟时间,在保证安全的同时提升舒适性。

摘要:

本文提出了一种新颖的应急规划框架,将基于学习的交通参与者多模态预测集成到分支模型预测控制(MPC)中。利用可达性分析,我们通过将大量预测组织成行驶走廊,解决了与分支MPC相关的计算挑战。通过分析这些走廊之间的重叠,可以通过剪枝和聚类减少其数量,同时由于保留了所有预测模式而确保安全。这些处理后的走廊直接对应于场景树的不同分支,并为分支MPC提供了高效的约束表示。我们进一步利用可达性来确定最大可行的决策推迟时间,确保分支决策保持可执行性。定性和定量评估表明,计算复杂度显著降低,安全性和舒适性得到增强。

英文摘要:

This paper presents a novel contingency planning framework that integrates learning-based multi-modal predictions of traffic participants into Branch Model Predictive Control (MPC). Leveraging reachability analysis, we address the computational challenges associated with Branch MPC by organizing the multitude of predictions into driving corridors. Analyzing the overlap between these corridors, their number can be reduced through pruning and clustering while ensuring safety since all prediction modes are preserved. These processed corridors directly correspond to the distinct branches of the scenario tree and provide an efficient constraint representation for the Branch MPC. We further utilize the reachability for determining maximum feasible decision postponing times, ensuring that branching decisions remain executable. Qualitative and quantitative evaluations demonstrate significantly reduced computational complexity and enhanced safety and comfort.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑