PnPNet: End-to-End Perception and Prediction with Tracking in the Loop

被引:114
作者
Liang, Ming [1 ]
Yang, Bin [1 ,2 ]
Zeng, Wenyuan [1 ,2 ]
Chen, Yun [1 ]
Hu, Rui [1 ]
Casas, Sergio [1 ,2 ]
Urtasun, Raquel [1 ,2 ]
机构
[1] Uber Adv Technol Grp, Pittsburgh, PA 15201 USA
[2] Univ Toronto, Toronto, ON, Canada
来源
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020) | 2020年
关键词
D O I
10.1109/CVPR42600.2020.01157
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We tackle the problem of joint perception and motion forecasting in the context of self-driving vehicles. Towards this goal we propose PnPNet, an end-to-end model that takes as input sequential sensor data, and outputs at each time step object tracks and their future trajectories. The key component is a novel tracking module that generates object tracks online from detections and exploits trajectory level features for motion forecasting. Specifically, the object tracks get updated at each time step by solving both the data association problem and the trajectory estimation problem. Importantly, the whole model is end-to-end trainable and benefits from joint optimization of all tasks. We validate PnPNet on two large-scale driving datasets, and show significant improvements over the state-of-the-art with better occlusion recovery and more accurate future prediction.
引用
收藏
页码:11550 / 11559
页数:10
相关论文
共 53 条
[1]   Social LSTM: Human Trajectory Prediction in Crowded Spaces [J].
Alahi, Alexandre ;
Goel, Kratarth ;
Ramanathan, Vignesh ;
Robicquet, Alexandre ;
Li Fei-Fei ;
Savarese, Silvio .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :961-971
[2]  
[Anonymous], 2019, CVPR, DOI DOI 10.1109/CVPR.2019.00587
[3]  
[Anonymous], 2019, IEEE INT CONF ROBOT, DOI [DOI 10.1109/ICRA.2019.8793868, 10.1109/ICRA.2019.8793868]
[4]  
[Anonymous], 2019, CVPR, DOI DOI 10.1109/CVPR.2019.01298
[5]  
[Anonymous], 2018, CVPR, DOI DOI 10.1109/CVPR.2018.00412
[6]  
[Anonymous], 2015, CVPR
[7]  
[Anonymous], 2012, ECCV
[8]  
[Anonymous], 2010, IEEE T PAMI
[9]  
Bansal M., 2018, ARXIV
[10]  
Bernardin K., 2006, 6 IEEE INT WORKSHOP, V90, P91