arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.07569cs.ROcs.AIcs.LG
收藏

车辆运动规划能否泛化到现实的長尾场景?

Can Vehicle Motion Planning Generalize to Realistic Long-tail Scenarios?

University of Tübingen(蒂宾根大学);Robert Bosch GmbH(罗伯特·博世有限公司);University of Duisburg-Essen(杜伊斯堡-埃森大学);Tübingen AI Center(蒂宾根人工智能中心)

Marcel Hallgarten, Julian Zapata, Martin Stoll, Katrin Renz, Andreas Zell

AI总结:

针对现有自动驾驶规划器难以泛化到罕见场景的问题,本文提出闭环基准 interPlan,并设计结合 LLM 行为规划与规则运动规划的混合规划器,在该基准上取得最优性能。

摘要:

现实世界的自动驾驶系统必须在罕见且多样的交通场景中做出安全决策。当前最先进的规划器大多在真实世界数据集上进行评估,例如 nuScenes(开环)或 nuPlan(闭环)。特别是 nuPlan 似乎是一种具有表现力的评估方法,因为它基于真实世界数据且采用闭环方式,但它主要覆盖基本驾驶场景。这使得很难判断规划器泛化到罕见场景的能力。因此,我们提出了一个新颖的闭环基准 interPlan,其中包含多个边缘案例和具有挑战性的驾驶场景。我们在该基准上评估了现有的最先进规划器,并表明无论是基于规则的规划器还是基于学习的规划器都无法安全地通过 interPlan 场景。最近一个正在发展的方向是使用基础模型(如大型语言模型 LLM)来处理泛化问题。我们评估了一个仅使用 LLM 的规划器,并提出了一种新颖的混合规划器,它将基于 LLM 的行为规划器与基于规则的运动规划器相结合,在我们的基准上取得了最先进的性能。

英文摘要:

Real-world autonomous driving systems must make safe decisions in the face of rare and diverse traffic scenarios. Current state-of-the-art planners are mostly evaluated on real-world datasets like nuScenes (open-loop) or nuPlan (closed-loop). In particular, nuPlan seems to be an expressive evaluation method since it is based on real-world data and closed-loop, yet it mostly covers basic driving scenarios. This makes it difficult to judge a planner's capabilities to generalize to rarely-seen situations. Therefore, we propose a novel closed-loop benchmark interPlan containing several edge cases and challenging driving scenarios. We assess existing state-of-the-art planners on our benchmark and show that neither rule-based nor learning-based planners can safely navigate the interPlan scenarios. A recently evolving direction is the usage of foundation models like large language models (LLM) to handle generalization. We evaluate an LLM-only planner and introduce a novel hybrid planner that combines an LLM-based behavior planner with a rule-based motion planner that achieves state-of-the-art performance on our benchmark.

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。

↑