An efficient Spatial-Temporal model based on gated linear units for trajectory prediction
An efficient Spatial-Temporal model based on gated linear units for trajectory prediction
复制标题
基于门控线性单元的高效时空模型用于轨迹预测
DOI：
10.1016/j.neucom.2021.12.051
复制
发表时间：
2022-04-28
期刊：
影响因子：
6
通讯作者：
Mao, Tianlu
中科院分区：
文献类型：
--
作者：
Liu, Shaohua;Wang, Yisu;Mao, Tianlu
轨迹预测是许多领域（例如自动驾驶和机器人导航）的一项至关重要且具有挑战性的任务。首先，高质量的轨迹预测方法需要有效地捕获人类的相互作用和人类的相互作用，以避免与移动的药物和静态障碍发生冲突。此外，这些方法要高效且轻量级以降低计算成本并节省公共资源是必不可少的。为了应对这些挑战，我们提出了一个基于封闭线性单元的空间 - 周期模块和热图模块的模型。在时空模块中，提出了一个自适应图卷积网络来捕获人类相互作用，该卷积相互作用将物理特征与图形卷积网络相结合，以推测代理的隐式关系。至于人类场景相互作用，我们编码热图模块中每个试剂周围的顺序局部热图。该模型包括两个封闭式线性单元，以捕获代理运动的相关性和周围场景的动态变化趋势的相关性。与以前的方法相比，我们的方法更加轻巧，效率较小，参数尺寸较小，推理时间较短。同时，我们的模型在两个公开可用的数据集（ETH和UCY）上取得了更好的实验结果，并预测了更多社会合理的轨迹。 （c）2021 Elsevier B.V.保留所有权利。
Trajectory prediction is a crucial and challenging task in many domains (e.g., autonomous driving and robot navigation). First, high-quality trajectory prediction methods need to capture the human-human interactions and human-scene interactions effectively to avoid collisions with moving agents and static obstacles. Moreover, it is indispensable for the approaches to be efficient and lightweight to reduce computing costs and economize public resources. To address these challenges, we propose a model with a Spatial-Temporal module and a heatmap module based on gated linear units. In the Spatial-Temporal module, an adaptive Graph Convolutional Network was proposed to capture the human-human interactions, which combines physical features with graph convolutional networks to speculate the agents' implicit relationships. As for the human-scene interaction, we encode the sequential local heatmap around each agent in the heatmap module. The model includes two gated linear units to capture the correlations of the agent's motion and dynamic changing trend of the surrounding scene, respectively. Compared with previous methods, our method is more lightweight and efficient with a smaller parameter size and shorter inference time. Meanwhile, our model achieves better experimental results on two publicly available datasets (ETH and UCY) and predicts more socially reasonable trajectories. (C) 2021 Elsevier B.V. All rights reserved.