arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.16733cs.ROcs.CVcs.LG
收藏

基于预测性个体世界模型的驾驶梦想

Dream to Drive with Predictive Individual World Model

School of Automation and Electrical Engineering, University of Science and Technology Beijing(北京科技大学自动化与电气工程学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)

Yinfeng Gao, Qichao Zhang, Da-wei Ding, Dongbin Zhao

AI总结:

针对复杂城市环境中道路使用者意图未知导致难以实现反应性驾驶的问题,提出基于预测性个体世界模型(PIWM)的MBRL方法,通过个体级视角建模车辆交互与意图,并在想象中训练行为策略,实现安全高效的自动驾驶。

摘要:

在复杂的城市环境中,由于道路使用者的意图未知,实现反应性驾驶行为仍然是一个具有挑战性的课题。基于模型的强化学习(MBRL)通过构建能够提供信息性状态和想象训练的世界模型,为学习反应性策略提供了巨大潜力。然而,相关研究中的一个关键局限在于场景级重建表示学习,这可能忽略关键的交互车辆,并且难以建模车辆之间的交互特征及其长期意图。因此,本文提出了一种新颖的基于预测性个体世界模型(PIWM)的MBRL方法用于自动驾驶。PIWM从个体层面的视角描述驾驶环境,并通过轨迹预测任务捕捉车辆的交互关系及其意图。同时,行为策略与PIWM联合学习。它在PIWM的想象中进行训练,并利用意图感知的潜在状态在城市驾驶场景中有效导航。所提出的方法在基于真实世界挑战性交互场景构建的仿真环境中进行了训练和评估。与流行的无模型方法和最先进的基于模型的强化学习方法相比,实验结果表明,所提出的方法在安全性和效率方面实现了最佳性能。

英文摘要:

It is still a challenging topic to make reactive driving behaviors in complex urban environments as road users' intentions are unknown. Model-based reinforcement learning (MBRL) offers great potential to learn a reactive policy by constructing a world model that can provide informative states and imagination training. However, a critical limitation in relevant research lies in the scene-level reconstruction representation learning, which may overlook key interactive vehicles and hardly model the interactive features among vehicles and their long-term intentions. Therefore, this paper presents a novel MBRL method with a predictive individual world model (PIWM) for autonomous driving. PIWM describes the driving environment from an individual-level perspective and captures vehicles' interactive relations and their intentions via trajectory prediction task. Meanwhile, a behavior policy is learned jointly with PIWM. It is trained in PIWM's imagination and effectively navigates in the urban driving scenes leveraging intention-aware latent states. The proposed method is trained and evaluated on simulation environments built upon real-world challenging interactive scenarios. Compared with popular model-free and state-of-the-art model-based reinforcement learning methods, experimental results show that the proposed method achieves the best performance in terms of safety and efficiency.

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。

↑