The Importance of Prior Knowledge in Precise Multimodal Prediction

被引:20
作者
Casas, Sergio [1 ,2 ]
Gulino, Cole [1 ]
Suo, Simon [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/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) | 2020年
关键词
D O I
10.1109/IROS45743.2020.9341199
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Roads have well defined geometries, topologies, and traffic rules. While this has been widely exploited in motion planning methods to produce maneuvers that obey the law, little work has been devoted to utilize these priors in perception and motion forecasting methods. In this paper we propose to incorporate these structured priors as a loss function. In contrast to imposing hard constraints, this approach allows the model to handle non-compliant maneuvers when those happen in the real world. Safe motion planning is the end goal, and thus a probabilistic characterization of the possible future developments of the scene is key to choose the plan with the lowest expected cost. Towards this goal, we design a framework that leverages REINFORCE to incorporate non-differentiable priors over sample trajectories from a probabilistic model, thus optimizing the whole distribution. We demonstrate the effectiveness of our approach on real-world self-driving datasets containing complex road topologies and multi-agent interactions. Our motion forecasts not only exhibit better precision and map understanding, but most importantly result in safer motion plans taken by our self-driving vehicle. We emphasize that despite the importance of this evaluation, it has been often overlooked by previous perception and motion forecasting works.
引用
收藏
页码:2295 / 2302
页数:8
相关论文
共 26 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]  
Bansal M, 2019, ROBOTICS: SCIENCE AND SYSTEMS XV
[3]  
Bishop CM., 2006, Pattern Recognition and Machine Learning
[4]  
Bishop CM, 1994, tech. rep.
[5]   nuScenes: A multimodal dataset for autonomous driving [J].
Caesar, Holger ;
Bankiti, Varun ;
Lang, Alex H. ;
Vora, Sourabh ;
Liong, Venice Erin ;
Xu, Qiang ;
Krishnan, Anush ;
Pan, Yu ;
Baldan, Giancarlo ;
Beijbom, Oscar .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, :11618-11628
[6]  
Casas S., 2019, ARXIV191008233
[7]  
Casas S, 2018, PR MACH LEARN RES, V87
[8]  
Chai Y., 2019, CORL
[9]   Argoverse: 3D Tracking and Forecasting with Rich Maps [J].
Chang, Ming-Fang ;
Lambert, John ;
Sangkloy, Patsorn ;
Singh, Jagjeet ;
Bak, Slawomir ;
Hartnett, Andrew ;
Wang, De ;
Carr, Peter ;
Lucey, Simon ;
Ramanan, Deva ;
Hays, James .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :8740-8749
[10]  
Cui HG, 2019, IEEE INT CONF ROBOT, P2090, DOI [10.1109/ICRA.2019.8793868, 10.1109/icra.2019.8793868]