论文标题
使用多个任务进行自主驾驶的有效潜在表示
Efficient Latent Representations using Multiple Tasks for Autonomous Driving
论文作者
论文摘要
在动态，多机构和复杂的城市环境中开车是需要复杂决策政策的艰巨任务。学习这样的政策需要一个可以编码整个环境的状态表示。将车辆环境编码为图像的中级表示已成为一个流行的选择，但它们是相当高的尺寸，这限制了它们在诸如增强式学习之类的数据筛选案例中的使用。在本文中，我们建议通过训练编码器描述器深神经网络来学习环境的低维和丰富特征表示，以预测多个应用相关因素，例如其他代理的轨迹。我们证明，与单头编码器模型相比，多头编码器折线神经网络的使用会导致更有信息的表示。特别是，与使用单头网络的现有方法相比，提出的代表学习方法可以帮助策略网络更快地学习性能和更少的数据。
Driving in the dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level representations that encode a vehicle's environment as images have become a popular choice, but they are quite high-dimensional, which limits their use in data-scarce cases such as reinforcement learning. In this article, we propose to learn a low dimensional and rich feature representation of the environment by training an encoder-decoder deep neural network to predict multiple application relevant factors such as trajectories of other agents. We demonstrate that the use of the multi-head encoder-decoder neural network results in a more informative representation compared to a single-head encoder-decoder model. In particular, the proposed representation learning approach helps the policy network to learn faster, with increased performance and with less data, compared to existing approaches using a single-head network.
