论文标题
用于自动驾驶操作的多任务网络的边缘设备部署
Edge Device Deployment of Multi-Tasking Network for Self-Driving Operations
论文作者
论文摘要
安全，强大的自主驾驶系统依赖于对面向应用的方案的环境的准确感知。本文提议在嵌入式系统上部署三个最关键的任务（即对象检测，可驱动区域分割和车道检测任务），以进行自动驾驶操作。为了实现这一研究目标，使用简单的编码器架构来利用多任务网络。对基于不同骨干网络的两个模型进行了全面和广泛的比较。所有培训实验均在服务器上执行，而Nvidia Jetson Xavier NX被选为部署设备。
A safe and robust autonomous driving system relies on accurate perception of the environment for application-oriented scenarios. This paper proposes deployment of the three most crucial tasks (i.e., object detection, drivable area segmentation and lane detection tasks) on embedded system for self-driving operations. To achieve this research objective, multi-tasking network is utilized with a simple encoder-decoder architecture. Comprehensive and extensive comparisons for two models based on different backbone networks are performed. All training experiments are performed on server while Nvidia Jetson Xavier NX is chosen as deployment device.
