Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021)(2021)
摘要
In this paper, we propose an end-to-end self-driving network featuring a sparse attention module that learns to automatically attend to important regions of the input. The attention module specifically targets motion planning, whereas prior literature only applied attention in perception tasks. Learning an attention mask directly targeted for motion planning significantly improves the planner safety by performing more focused computation. Furthermore, visualizing the attention improves interpretability of end-to-end self-driving.
更多查看译文
关键词
sparse attention module,important regions,motion planning,prior literature,perception tasks,attention mask,perceive,spatial attention,safe self-driving,end-to-end self-driving network
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要