Hanjun Choi, Hyunsung Kim, Minho Lee, Chang-Jo Kim, Jinsung Yoon, Sang-Ki Ko
{"title":"DBHP:利用基于派生的混合预测在多代理运动中进行轨迹推断","authors":"Hanjun Choi, Hyunsung Kim, Minho Lee, Chang-Jo Kim, Jinsung Yoon, Sang-Ki Ko","doi":"arxiv-2408.10878","DOIUrl":null,"url":null,"abstract":"Many spatiotemporal domains handle multi-agent trajectory data, but in\nreal-world scenarios, collected trajectory data are often partially missing due\nto various reasons. While existing approaches demonstrate good performance in\ntrajectory imputation, they face challenges in capturing the complex dynamics\nand interactions between agents due to a lack of physical constraints that\ngovern realistic trajectories, leading to suboptimal results. To address this\nissue, the paper proposes a Derivative-Based Hybrid Prediction (DBHP) framework\nthat can effectively impute multiple agents' missing trajectories. First, a\nneural network equipped with Set Transformers produces a naive prediction of\nmissing trajectories while satisfying the permutation-equivariance in terms of\nthe order of input agents. Then, the framework makes alternative predictions\nleveraging velocity and acceleration information and combines all the\npredictions with properly determined weights to provide final imputed\ntrajectories. In this way, our proposed framework not only accurately predicts\nposition, velocity, and acceleration values but also enforces the physical\nrelationship between them, eventually improving both the accuracy and\nnaturalness of the predicted trajectories. Accordingly, the experiment results\nabout imputing player trajectories in team sports show that our framework\nsignificantly outperforms existing imputation baselines.","PeriodicalId":501315,"journal":{"name":"arXiv - CS - Multiagent Systems","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"DBHP: Trajectory Imputation in Multi-Agent Sports Using Derivative-Based Hybrid Prediction\",\"authors\":\"Hanjun Choi, Hyunsung Kim, Minho Lee, Chang-Jo Kim, Jinsung Yoon, Sang-Ki Ko\",\"doi\":\"arxiv-2408.10878\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Many spatiotemporal domains handle multi-agent trajectory data, but in\\nreal-world scenarios, collected trajectory data are often partially missing due\\nto various reasons. While existing approaches demonstrate good performance in\\ntrajectory imputation, they face challenges in capturing the complex dynamics\\nand interactions between agents due to a lack of physical constraints that\\ngovern realistic trajectories, leading to suboptimal results. To address this\\nissue, the paper proposes a Derivative-Based Hybrid Prediction (DBHP) framework\\nthat can effectively impute multiple agents' missing trajectories. First, a\\nneural network equipped with Set Transformers produces a naive prediction of\\nmissing trajectories while satisfying the permutation-equivariance in terms of\\nthe order of input agents. Then, the framework makes alternative predictions\\nleveraging velocity and acceleration information and combines all the\\npredictions with properly determined weights to provide final imputed\\ntrajectories. In this way, our proposed framework not only accurately predicts\\nposition, velocity, and acceleration values but also enforces the physical\\nrelationship between them, eventually improving both the accuracy and\\nnaturalness of the predicted trajectories. Accordingly, the experiment results\\nabout imputing player trajectories in team sports show that our framework\\nsignificantly outperforms existing imputation baselines.\",\"PeriodicalId\":501315,\"journal\":{\"name\":\"arXiv - CS - Multiagent Systems\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Multiagent Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.10878\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Multiagent Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.10878","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
DBHP: Trajectory Imputation in Multi-Agent Sports Using Derivative-Based Hybrid Prediction
Many spatiotemporal domains handle multi-agent trajectory data, but in
real-world scenarios, collected trajectory data are often partially missing due
to various reasons. While existing approaches demonstrate good performance in
trajectory imputation, they face challenges in capturing the complex dynamics
and interactions between agents due to a lack of physical constraints that
govern realistic trajectories, leading to suboptimal results. To address this
issue, the paper proposes a Derivative-Based Hybrid Prediction (DBHP) framework
that can effectively impute multiple agents' missing trajectories. First, a
neural network equipped with Set Transformers produces a naive prediction of
missing trajectories while satisfying the permutation-equivariance in terms of
the order of input agents. Then, the framework makes alternative predictions
leveraging velocity and acceleration information and combines all the
predictions with properly determined weights to provide final imputed
trajectories. In this way, our proposed framework not only accurately predicts
position, velocity, and acceleration values but also enforces the physical
relationship between them, eventually improving both the accuracy and
naturalness of the predicted trajectories. Accordingly, the experiment results
about imputing player trajectories in team sports show that our framework
significantly outperforms existing imputation baselines.