论文标题
基于图形的多代理体育游戏中基于图形的轨迹预测方法
A Graph Attention Based Approach for Trajectory Prediction in Multi-agent Sports Games
论文作者
论文摘要
这项工作研究了多代理轨迹预测的问题。先前的方法缺乏在协调剂之间捕获细粒依赖性的能力。在本文中，我们提出了一种时空轨迹预测方法，该方法能够学习具有多个协调代理的团队的策略。特别是，我们使用基于图的注意模型来学习代理的依赖性。此外，我们的方法不利用复发网络（例如VRNN，LSTM），而是使用时间卷积网络（TCN）作为顺序模型来支持较长的有效历史记录并提供并提供并行性和稳定梯度等重要特征。我们在两个不同的体育游戏数据集上演示了方法的验证和有效性：篮球和足球数据集。结果表明，与相关方法相比，我们的模型侵入玩家的依赖性可以大大提高性能。代码可从https://github.com/iheartgraph/predict获得
This work investigates the problem of multi-agents trajectory prediction. Prior approaches lack of capability of capturing fine-grained dependencies among coordinated agents. In this paper, we propose a spatial-temporal trajectory prediction approach that is able to learn the strategy of a team with multiple coordinated agents. In particular, we use graph-based attention model to learn the dependency of the agents. In addition, instead of utilizing the recurrent networks (e.g., VRNN, LSTM), our method uses a Temporal Convolutional Network (TCN) as the sequential model to support long effective history and provide important features such as parallelism and stable gradients. We demonstrate the validation and effectiveness of our approach on two different sports game datasets: basketball and soccer datasets. The result shows that compared to related approaches, our model that infers the dependency of players yields substantially improved performance. Code is available at https://github.com/iHeartGraph/predict
