Interaction-Aware and Hierarchically-Explainable Heterogeneous Graph-based Imitation Learning for Autonomous Driving Simulation
Interaction-Aware and Hierarchically-Explainable Heterogeneous Graph-based Imitation Learning for Autonomous Driving Simulation
复制标题
DOI：
10.1109/iros55552.2023.10342051
复制
发表时间：
2023-10
期刊：
影响因子：
--
通讯作者：
Mahan Tabatabaie;Suining He;Kang G. Shin
中科院分区：
文献类型：
--
作者：
Mahan Tabatabaie;Suining He;Kang G. Shin
理解和学习参与者与x之间的交互（AXIs），例如焦点车辆（参与者）与其他交通参与者（例如，其他车辆、行人）以及交通环境（例如，城市/路线图）之间的交互，对于开发决策模型和自动驾驶（AD）的模拟至关重要。现有的模仿学习（IL）用于AD仿真的实践，尽管在模型可学习性方面取得了进展，但尚未考虑在复杂道路环境中融合和区分异质轴。此外，如何进一步解释复杂轴中的层次结构在很大程度上仍有待探索。为了克服这些挑战，我们提出了HGIL，一种用于AD仿真的基于异构图的交互感知和层次可解释的模仿学习方法。我们设计了一种新的异构交互图（HIG）来提供本地和全局表示以及对AXIs的感知。结合HIG作为状态嵌入，我们设计了一种具有局部子图和全局交叉图关注的分层可解释的生成对抗模仿学习方法，以捕获交互行为并驱动决策过程。我们的数据驱动模拟和解释研究证实了HGIL在学习和捕获复杂轴方面的准确性和可解释性。
Understanding and learning the actor-to-X inter-actions (AXIs), such as those between the focal vehicles (actor) and other traffic participants (e.g., other vehicles, pedestrians) as well as traffic environments (e.g., city/road map), is essential for the development of a decision-making model and simulation of autonomous driving (AD). Existing practices on imitation learning (IL) for AD simulation, despite the advances in the model learnability, have not accounted for fusing and differentiating the heterogeneous AXIs in complex road environments. Furthermore, how to further explain the hierarchical structures within the complex AXIs remains largely under-explored. To overcome these challenges, we propose HGIL, an interaction- aware and hierarchically-explainable Heterogeneous _Graph- based Imitation Learning approach for AD simulation. We have designed a novel heterogeneous interaction graph (HIG) to provide local and global representation as well as awareness of the AXIs. Integrating the HIG as the state embeddings, we have designed a hierarchically-explainable generative adversarial imitation learning approach, with local sub-graph and global cross-graph attention, to capture the interaction behaviors and driving decision-making processes. Our data-driven simulation and explanation studies have corroborated the accuracy and explainability of HGIL in learning and capturing the complex AXIs.