Autonomous vehicle (AV) control systems increasingly rely on ML models for tasks such as perception and planning. Current practice is to run these models on the car's local hardware due to real-time latency constraints and reliability concerns, which limits model size and thus accuracy. Prior work has observed that we could augment current systems by running larger models in the cloud, relying on faster cloud runtimes to offset the cellular network latency. However, prior work does not account for an important practical constraint: limited cellular bandwidth. We show that, for typical bandwidth levels, proposed techniques for cloud-augmented AV models take too long to transfer data, thus mostly falling back to the on-car models and resulting in no accuracy improvement. In this work, we show that realizing cloud-augmented AV models requires intelligent use of this scarce bandwidth, i.e. carefully allocating bandwidth across tasks and providing multiple data compression and model options. We formulate this as a resource allocation problem to maximize car utility, and present our system \sysname which achieves an increase in average model accuracy by up to 15 percentage points on driving scenarios from the Waymo Open Dataset.

翻译：自动驾驶车辆（AV）控制系统日益依赖机器学习模型执行感知与规划等任务。由于实时延迟约束和可靠性考量，当前实践通常将这些模型部署在车辆本地硬件上运行，这限制了模型规模，进而影响了精度。先前研究指出，可通过在云端运行更大模型来增强现有系统，依赖更快的云端运行时以抵消蜂窝网络延迟。然而，先前工作未考虑一个重要的实际约束：有限的蜂窝网络带宽。我们证明，在典型带宽水平下，现有云增强AV模型方案的数据传输耗时过长，导致系统大多仍回退至车载模型，无法实现精度提升。本研究表明，实现云增强AV模型需要智能利用稀缺带宽资源，即跨任务精细分配带宽，并提供多种数据压缩与模型选项。我们将此问题形式化为资源分配问题以最大化车辆效用，并提出系统 \sysname，在Waymo开放数据集的驾驶场景中实现了平均模型精度最高15个百分点的提升。