RMP-YOLO: A Robust Motion Predictor for Partially Observable Scenarios even if You Only Look Once

Jiawei Sun, Jiahui Li, Tingchen Liu, Chengran Yuan, Shuo Sun, Zefan Huang, Anthony Wong, Keng Peng Tee, Marcelo H. Ang Jr
{"title":"RMP-YOLO: A Robust Motion Predictor for Partially Observable Scenarios even if You Only Look Once","authors":"Jiawei Sun, Jiahui Li, Tingchen Liu, Chengran Yuan, Shuo Sun, Zefan Huang, Anthony Wong, Keng Peng Tee, Marcelo H. Ang Jr","doi":"arxiv-2409.11696","DOIUrl":null,"url":null,"abstract":"We introduce RMP-YOLO, a unified framework designed to provide robust motion\npredictions even with incomplete input data. Our key insight stems from the\nobservation that complete and reliable historical trajectory data plays a\npivotal role in ensuring accurate motion prediction. Therefore, we propose a\nnew paradigm that prioritizes the reconstruction of intact historical\ntrajectories before feeding them into the prediction modules. Our approach\nintroduces a novel scene tokenization module to enhance the extraction and\nfusion of spatial and temporal features. Following this, our proposed recovery\nmodule reconstructs agents' incomplete historical trajectories by leveraging\nlocal map topology and interactions with nearby agents. The reconstructed,\nclean historical data is then integrated into the downstream prediction\nmodules. Our framework is able to effectively handle missing data of varying\nlengths and remains robust against observation noise, while maintaining high\nprediction accuracy. Furthermore, our recovery module is compatible with\nexisting prediction models, ensuring seamless integration. Extensive\nexperiments validate the effectiveness of our approach, and deployment in\nreal-world autonomous vehicles confirms its practical utility. In the 2024\nWaymo Motion Prediction Competition, our method, RMP-YOLO, achieves\nstate-of-the-art performance, securing third place.","PeriodicalId":501031,"journal":{"name":"arXiv - CS - Robotics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Robotics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11696","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

We introduce RMP-YOLO, a unified framework designed to provide robust motion predictions even with incomplete input data. Our key insight stems from the observation that complete and reliable historical trajectory data plays a pivotal role in ensuring accurate motion prediction. Therefore, we propose a new paradigm that prioritizes the reconstruction of intact historical trajectories before feeding them into the prediction modules. Our approach introduces a novel scene tokenization module to enhance the extraction and fusion of spatial and temporal features. Following this, our proposed recovery module reconstructs agents' incomplete historical trajectories by leveraging local map topology and interactions with nearby agents. The reconstructed, clean historical data is then integrated into the downstream prediction modules. Our framework is able to effectively handle missing data of varying lengths and remains robust against observation noise, while maintaining high prediction accuracy. Furthermore, our recovery module is compatible with existing prediction models, ensuring seamless integration. Extensive experiments validate the effectiveness of our approach, and deployment in real-world autonomous vehicles confirms its practical utility. In the 2024 Waymo Motion Prediction Competition, our method, RMP-YOLO, achieves state-of-the-art performance, securing third place.
RMP-YOLO:即使只看一眼,也能预测部分可观测场景的稳健运动预测器
我们介绍了 RMP-YOLO,这是一个统一的框架,旨在即使在输入数据不完整的情况下也能提供稳健的运动预测。我们的主要见解源于我们的观察:完整可靠的历史轨迹数据在确保运动预测准确性方面发挥着关键作用。因此,我们提出了一种新的模式,即在将完整的历史轨迹数据输入预测模块之前,优先重建这些数据。我们的方法引入了一个新颖的场景标记化模块,以加强空间和时间特征的提取和融合。随后,我们提出的恢复模块利用本地地图拓扑以及与附近代理的交互作用,重建代理的不完整历史轨迹。重建后的干净历史数据将被整合到下游预测模块中。我们的框架能够有效处理不同长度的缺失数据,并在保持高预测精度的同时,对观测噪声保持稳健。此外,我们的恢复模块与现有的预测模型兼容,确保了无缝集成。广泛的实验验证了我们方法的有效性,在现实世界自动驾驶车辆中的部署也证实了它的实用性。在 2024 年 Waymo 运动预测竞赛中,我们的方法 RMP-YOLO 取得了最先进的性能,获得了第三名。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信