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 2409.18031cs.RO
收藏

交互式自动驾驶的推理多智能体行为拓扑

Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving

Nanyang Technological University(南洋理工大学);Shanghai AI Lab(上海人工智能实验室);University of Hong Kong(香港大学)

Haochen Liu, Li Chen, Yu Qiao, Chen Lv, Hongyang Li

AI总结:

针对多智能体场景下行为表示低效导致预测与规划不稳定的问题,提出基于辫子理论的行为拓扑BeTop及协同学习框架BeTopNet,通过提炼交互拓扑先验提升行为一致性与不确定性管理,在nuPlan和WOMD等数据集上达到SOTA性能。

摘要:

自动驾驶系统旨在通过交互智能体间的行为整合实现安全且符合社会一致性的驾驶。然而,由于多智能体场景的不确定性和异构交互,挑战依然存在。当前的密集和稀疏行为表示在多智能体建模中存在低效和不一致的问题,导致在整合预测与规划(IPP)时集体行为模式不稳定。为解决此问题,我们提出一种拓扑构形,作为合规的行为前景来引导下游轨迹生成。具体而言,我们引入行为拓扑(BeTop),这是一种关键的拓扑公式,明确表示多智能体未来之间的共识行为模式。BeTop源自辫子理论,用于从多智能体未来轨迹中提炼合规的交互拓扑。由BeTop监督的协同学习框架(BeTopNet)促进了在预测拓扑先验内行为预测和规划的一致性。通过模仿性应急学习,BeTop还有效管理预测和规划的行为不确定性。在包括nuPlan和WOMD在内的大规模真实世界数据集上的广泛验证表明,BeTop在预测和规划任务中均达到最先进性能。在所提出的交互场景基准上的进一步验证展示了交互情况下的规划合规性。

英文摘要:

Autonomous driving system aims for safe and social-consistent driving through the behavioral integration among interactive agents. However, challenges remain due to multi-agent scene uncertainty and heterogeneous interaction. Current dense and sparse behavioral representations struggle with inefficiency and inconsistency in multi-agent modeling, leading to instability of collective behavioral patterns when integrating prediction and planning (IPP). To address this, we initiate a topological formation that serves as a compliant behavioral foreground to guide downstream trajectory generations. Specifically, we introduce Behavioral Topology (BeTop), a pivotal topological formulation that explicitly represents the consensual behavioral pattern among multi-agent future. BeTop is derived from braid theory to distill compliant interactive topology from multi-agent future trajectories. A synergistic learning framework (BeTopNet) supervised by BeTop facilitates the consistency of behavior prediction and planning within the predicted topology priors. Through imitative contingency learning, BeTop also effectively manages behavioral uncertainty for prediction and planning. Extensive verification on large-scale real-world datasets, including nuPlan and WOMD, demonstrates that BeTop achieves state-of-the-art performance in both prediction and planning tasks. Further validations on the proposed interactive scenario benchmark showcase planning compliance in interactive cases.

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。

↑