Accurate prediction of pedestrian crossing behaviors by autonomous vehicles can significantly improve traffic safety. Existing approaches often model pedestrian behaviors using trajectories or poses but do not offer a deeper semantic interpretation of a person's actions or how actions influence a pedestrian's intention to cross in the future. In this work, we follow the neuroscience and psychological literature to define pedestrian crossing behavior as a combination of an unobserved inner will (a probabilistic representation of binary intent of crossing vs. not crossing) and a set of multi-class actions (e.g., walking, standing, etc.). Intent generates actions, and the future actions in turn reflect the intent. We present a novel multi-task network that predicts future pedestrian actions and uses predicted future action as a prior to detect the present intent and action of the pedestrian. We also designed an attention relation network to incorporate external environmental contexts thus further improve intent and action detection performance. We evaluated our approach on two naturalistic driving datasets, PIE and JAAD, and extensive experiments show significantly improved and more explainable results for both intent detection and action prediction over state-of-the-art approaches. Our code is available at: https://github.com/umautobots/pedestrian_intent_action_detection.
翻译:对自主车辆行人过境行为的准确预测可以大大改善交通安全。现有做法通常以轨迹或姿势为行人行为模型,但并不提供更深的语义解释,说明一个人的行为或行动如何影响行人今后跨行的意向。在这项工作中,我们遵循神经科学和心理文献,将行人跨行的行为定义为一种不受观察的内部意愿(即跨行与非越越的二进意的概率表示)和一套多级行动(如步行、站立等)的组合。 意图产生行动,而未来行动又反映这一意图。我们提出了一个新的多任务网络,预测行人今后的行动,并使用预测的未来行动,作为检测行人当前意向和行动的前提。我们还设计了一个关注关系网络,以纳入外部环境环境背景,从而进一步改善意向和行动检测绩效。我们评估了我们关于两种自然驱动数据集(PIE和JAAAD)和广泛实验的方法,显示在意图检测和行动预测方面有显著改进和更可解释的结果。我们在州-abest-action-action action appres:http-abroto-oto-oto-ob-oal action_ob-ob-oal_oto-oal_oction_oction_oal_oction_oction_oction_oction_oction_oction_oction_oction_oction_oction_tototototo-to-to-toto-to-to-to-to-to-toment_oction_to-action-to-to-toto-to-to-to-to-toction-action-action-action-action-action-action-action-action-action-to-to-to-to-to-to-to-to-to-action-action-to-action-to-to-action-action-action-action-action-action-action-action-action-action-action-action-action-action-action-to-action-to-action-action-action-action-action-action-action-action-action-action-action-action-action-