Environmental perception is a key element of autonomous driving because the information received from the perception module influences core driving decisions. An outstanding challenge in real-time perception for autonomous driving lies in finding the best trade-off between detection quality and latency. Major constraints on both computation and power have to be taken into account for real-time perception in autonomous vehicles. Larger object detection models tend to produce the best results, but are also slower at runtime. Since the most accurate detectors cannot run in real-time locally, we investigate the possibility of offloading computation to edge and cloud platforms, which are less resource-constrained. We create a synthetic dataset to train object detection models and evaluate different offloading strategies. Using real hardware and network simulations, we compare different trade-offs between prediction quality and end-to-end delay. Since sending raw frames over the network implies additional transmission delays, we also explore the use of JPEG and H.265 compression at varying qualities and measure their impact on prediction metrics. We show that models with adequate compression can be run in real-time on the cloud while outperforming local detection performance.

翻译：环境感知是自动驾驶的关键要素，因为感知模块接收到的信息直接影响核心驾驶决策。自动驾驶实时感知面临的一个突出挑战在于如何找到检测质量与延迟之间的最佳平衡点。在自动驾驶车辆的实时感知过程中，必须考虑计算能力和功耗方面的主要约束。较大规模的目标检测模型通常能产生最佳结果，但其运行时速度也较慢。由于最精确的检测器无法在本地实时运行，我们研究了将计算任务卸载至资源受限程度较低的边缘与云平台的可能性。我们创建了一个合成数据集用于训练目标检测模型，并评估不同的卸载策略。使用真实硬件和网络仿真，我们比较了预测质量与端到端延迟之间的不同权衡。由于通过网络传输原始帧会带来额外的传输延迟，我们还探索了在不同质量级别下使用JPEG和H.265压缩技术，并测量了其对预测指标的影响。研究表明，采用适当压缩的模型可以在云平台上实时运行，同时其检测性能优于本地检测。