Self-Driving Car Steering Angle Prediction Based On Deep Neural Network An Example Of CarND Udacity Simulator
Self-Driving Car Steering Angle Prediction Based On Deep Neural Network An Example Of CarND Udacity Simulator
复制标题
基于深度神经网络的自动驾驶汽车转向角预测——CarND Udacity Simulator 示例
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
I. V. Stelmashchuk
中科院分区：
文献类型：
--
作者：
M. V. Smolyakov;Alexey I. Frolov;V. N. Volkov;I. V. Stelmashchuk
自动驾驶汽车的实现将改变人类的生活。这样的系统需要巨大的计算能力和大数据集。存在容易地生成期望数量的车辆运动图像的仿真器。我们探索了使用从仿真器获得的图像来训练深度神经网络以预测转向角的可能性。这种方法允许汽车在自动模式下移动。我们探索了卷积神经网络的各种架构，以便用最少的参数获得良好的结果。
The implementation of self-driving cars will change human lives. Such systems require huge computing power and big datasets. There exists an emulator generating the desired number of images of the vehicle movement easily. We explore the possibility of using obtained images from the emulator for training deep neural networks for prediction of steering angle. This approach allows car to move in automatic mode. We explore various architectures of convolutional neural networks in order to obtain good results with a minimum number of parameters.