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 1903.00848cs.ROcs.LG
收藏

基于行为交互网络的车辆行为预测

Predicting Vehicle Behaviors Over An Extended Horizon Using Behavior Interaction Network

Hong Kong University of Science and Technology(香港科技大学);DJI Technology Co., Ltd.(大疆创新科技有限公司)

Wenchao Ding, Jing Chen, Shaojie Shen

摘要:

预测交通参与者的可能行为是自动驾驶车辆的基本能力。许多行为检测和机动识别方法只有非常有限的预测范围,这使得规划的时间和空间不足。为了避免不令人满意的反应性决策,在规划中计算长期的未来回报至关重要,这需要扩展预测范围。在本文中,我们发现,在一个扩展的地平线上的车辆行为的线索,可以在车辆的相互作用,这使得人们有可能预测某种行为的可能性,即使在没有任何明确的机动模式。我们采用递归神经网络(RNN)的观察编码,并在此基础上,我们提出了一种新的车辆行为交互网络(VBIN),捕捉车辆的相互作用,从隐藏的状态和连接特征的每个相互作用对。我们的方法的输出是多个行为类的概率似然,这与遥远未来的多模态和不确定性相匹配。我们的方法对两个国家的最先进的方法和另外两个基线方法的公开可用的真实公路数据集的系统比较,表明我们的方法具有优越的精度和先进的交互建模能力。

英文摘要:

Anticipating possible behaviors of traffic participants is an essential capability of autonomous vehicles. Many behavior detection and maneuver recognition methods only have a very limited prediction horizon that leaves inadequate time and space for planning. To avoid unsatisfactory reactive decisions, it is essential to count long-term future rewards in planning, which requires extending the prediction horizon. In this paper, we uncover that clues to vehicle behaviors over an extended horizon can be found in vehicle interaction, which makes it possible to anticipate the likelihood of a certain behavior, even in the absence of any clear maneuver pattern. We adopt a recurrent neural network (RNN) for observation encoding, and based on that, we propose a novel vehicle behavior interaction network (VBIN) to capture the vehicle interaction from the hidden states and connection feature of each interaction pair. The output of our method is a probabilistic likelihood of multiple behavior classes, which matches the multimodal and uncertain nature of the distant future. A systematic comparison of our method against two state-of-the-art methods and another two baseline methods on a publicly available real highway dataset is provided, showing that our method has superior accuracy and advanced capability for interaction modeling.

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。

↑