采用面向转向与制动控制的深度双模型解决方案的自动驾驶
Autonomous Driving with a Deep Dual-Model Solution for Steering and Braking Control
AI总结：
提出结合 PilotNet 与 MobileNet SSD 的双模型方案控制转向和制动，并通过原创网络设计压缩 PilotNet，在保持性能的同时降低资源需求。
摘要：
自动驾驶技术目前在学术界和工业界都引起了极大关注。本文提出了一种深度学习双模型解决方案，使用两个深度神经网络实现自动驾驶车辆的制动与转向联合控制。转向控制通过应用 NVIDIA 的 PilotNet 模型预测方向盘角度来实现，而制动控制则依赖于 MobileNet SSD。两个模型均依靠单个前置摄像头进行图像输入。MobileNet SSD 模型适用于资源受限的设备，而 PilotNet 难以在资源有限的小型设备上高效运行。为使其适用于此类设备，我们采用原创网络设计对 PilotNet 模型进行了修改，将模型参数量和内存占用减少了约 60%。推理延迟也有所降低，使该模型更适合在资源受限设备上运行。修改后的 PilotNet 模型取得了与原始 PilotNet 模型相近的损失和准确率。在仿真环境中评估时，两套自动驾驶系统——一套使用修改后的 PilotNet 模型、另一套使用原始 PilotNet 模型进行转向——表现出相近的自动驾驶性能水平。
英文摘要：
The technology of autonomous driving is currently attracting a great deal of interest in both research and industry. In this paper, we present a deep learning dual-model solution that uses two deep neural networks for combined braking and steering in autonomous vehicles. Steering control is achieved by applying the NVIDIA's PilotNet model to predict the steering wheel angle, while braking control relies on the use of MobileNet SSD. Both models rely on a single front-facing camera for image input. The MobileNet SSD model is suitable for devices with constrained resources, whereas PilotNet struggles to operate efficiently on smaller devices with limited resources. To make it suitable for such devices, we modified the PilotNet model using our own original network design and reduced the number of model parameters and its memory footprint by approximately 60%. The inference latency has also been reduced, making the model more suitable to operate on resource-constrained devices. The modified PilotNet model achieves similar loss and accuracy compared to the original PilotNet model. When evaluated in a simulated environment, both autonomous driving systems, one using the modified PilotNet model and the other using the original PilotNet model for steering, show similar levels of autonomous driving performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
