论文标题
在现实世界驾驶场景中的随机未来预测
Stochastic Future Prediction in Real World Driving Scenarios
论文作者
论文摘要
不确定性在未来的预测中起着关键作用。未来是不确定的。这意味着可能有很多可能的未来。未来的预测方法应涵盖鲁棒的全部可能性。在自动驾驶中，涵盖预测部分中多种模式对于做出安全至关重要的决策至关重要。尽管近年来计算机视觉系统已经大大提高，但如今的未来预测仍然很困难。几个例子是未来的不确定性，对完整场景理解的要求以及嘈杂的输出空间。在本文中，我们通过以随机方式对运动进行建模并学习潜在空间中的时间动态来提出解决这些挑战的解决方案。
Uncertainty plays a key role in future prediction. The future is uncertain. That means there might be many possible futures. A future prediction method should cover the whole possibilities to be robust. In autonomous driving, covering multiple modes in the prediction part is crucially important to make safety-critical decisions. Although computer vision systems have advanced tremendously in recent years, future prediction remains difficult today. Several examples are uncertainty of the future, the requirement of full scene understanding, and the noisy outputs space. In this thesis, we propose solutions to these challenges by modeling the motion explicitly in a stochastic way and learning the temporal dynamics in a latent space.
