Abstract
In complex traffic environments, autonomous vehicles face multi-modal uncertainty about other agents' future behavior. To address this, recent advancements in learningbased motion predictors output multi-modal predictions. We present our novel framework that leverages Branch Model Predictive Control(BMPC) to account for these predictions. The framework includes an online scenario-selection process guided by topology and collision risk criteria. This efficiently selects a minimal set of predictions, rendering the BMPC realtime capable. Additionally, we introduce an adaptive decision postponing strategy that delays the planner's commitment to a single scenario until the uncertainty is resolved. Our comprehensive evaluations in traffic intersection and random highway merging scenarios demonstrate enhanced comfort and safety through our method.
Abstract (translated)
在复杂的交通环境中,自动驾驶车辆面临着其他车辆未来行为的 multi-modal 不确定性。为了解决这个问题, recent 的学习基础运动预测器取得了多模态预测。 我们提出了一个利用分支模型预测控制(BMPC)来处理这些预测的新框架。框架包括一个由拓扑和碰撞风险标准引导的在线场景选择过程。 这有效地选择了一个最小预测集,使得 BMPC 实时有能力。此外,我们引入了一种自适应的决策推迟策略,即在确定性解决之前,将规划器的承诺推迟到单个场景。 我们在交通交叉口和随机高速公路合并场景的全面评估证明了通过我们的方法可以提高舒适度和安全性。
URL
https://arxiv.org/abs/2405.03470