CADENCE：面向导航和计算效率的上下文自适应深度估计
CADENCE: Context-Adaptive Depth Estimation for Navigation and Computational Efficiency
AI总结：
CADENCE通过动态调整轻量级单目深度估计网络的计算复杂度，实现导航需求与环境上下文的闭环控制，降低能耗并提升导航精度。
摘要：
自动驾驶车辆在远程环境中通常依赖嵌入式处理器、紧凑电池和轻量传感器。这些硬件限制与需要获取环境鲁棒表示的需求相冲突，后者通常需要执行计算密集型深度神经网络进行感知。为此，我们提出了CADENCE，一种自适应系统，能够根据导航需求和环境上下文动态调整可压缩单目深度估计网络的计算复杂度。通过感知精度与执行要求之间的闭环，CADENCE确保仅在任务关键时使用高精度计算。我们在发布的开源测试平台中进行了评估，该平台集成了Microsoft AirSim与NVIDIA Jetson Orin Nano。与最先进的静态方法相比，CADENCE分别减少了9.67%的传感器采集、16.1%的能耗和74.8%的推理延迟。结果表明总体能耗降低了75.0%，导航精度提高了7.43%。
英文摘要：
Autonomous vehicles deployed in remote environments typically rely on embedded processors, compact batteries, and lightweight sensors. These hardware limitations conflict with the need to derive robust representations of the environment, which often requires executing computationally intensive deep neural networks for perception. To address this challenge, we present CADENCE, an adaptive system that dynamically scales the computational complexity of a slimmable monocular depth estimation network in response to navigation needs and environmental context. By closing the loop between perception fidelity and actuation requirements, CADENCE ensures high-precision computing is only used when mission-critical. We conduct evaluations on our released open-source testbed that integrates Microsoft AirSim with an NVIDIA Jetson Orin Nano. As compared to a state-of-the-art static approach, CADENCE decreases sensor acquisitions, power consumption, and inference latency by 9.67%, 16.1%, and 74.8%, respectively. The results demonstrate an overall reduction in energy expenditure by 75.0%, along with an increase in navigation accuracy by 7.43%.
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。
