预测
文章平均质量分 91
64318@461
这个作者很懒,什么都没留下…
展开
-
VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation
动机Can we learn a meaningful context representation directly from the structured HD maps?【CC】开宗明义提问,直接从结构化的HD MAP数据学习一个信息丰富的上下文(带动态ObjList)This paper focuses on behavior prediction in complex multi-agent systems, such as self-driving vehicles.The core i原创 2022-02-01 17:12:24 · 1119 阅读 · 0 评论 -
TNT: Target-driveN Trajectory Prediction
概要:Our key insight is that for prediction within a moderate time horizon, the future modes can be effectively captured by a set of target states【CC】个人理解核心思想是未来的可能性很多,但是可以通过一组预测状态来刻画。 实际就是后面的先预测一些目标点,然后基于这些点来预测轨迹 这么一个思路。这样做的好处是通过目标点来压缩搜索空间。直观来想这个事情,先规划几个目原创 2021-12-18 20:27:50 · 969 阅读 · 0 评论 -
MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction
背景假设:A fundamental aspect of future state prediction is that it is inherently stochastic, as agents cannot know each other’s motivations【CC】这里假设我们是无法正真知道其他agnent的行为,跟RL计算纳什均衡思路不一样,后者假设每个agent都是理智的,都想达到自己的最优解We seek a model of the future that can provide原创 2021-12-05 18:03:56 · 1104 阅读 · 2 评论 -
IntentNet: Learning to Predict Intention from Raw Sensor Data
动机In this paper we develop a one-stage detector and forecaster that exploits both 3D point clouds produced by a LiDAR sensor as well as dynamic maps of the environment.we exploit 3D LiDAR point clouds and dynamic HD maps containing semantic elements such原创 2021-10-24 18:36:52 · 657 阅读 · 0 评论