E2M: an energy-efficient middleware for computer vision applications on autonomous mobile robots
E2M: an energy-efficient middleware for computer vision applications on autonomous mobile robots
复制标题
E2M：一种用于自主移动机器人计算机视觉应用的节能中间件
DOI：
10.1145/3318216.3363302
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Shi, Weisong
中科院分区：
文献类型：
--
作者：
Liu, Liangkai;Chen, Jiamin;Brocanelli, Marco;Shi, Weisong
自主式移动的机器人（AMR）已经在工业中广泛地用于执行各种机载计算机视觉应用，包括自主引导、安全巡逻、对象检测和面部识别。AMR执行的大多数应用程序都涉及通过经过训练的机器学习模型分析相机图像。许多关于机器学习的研究要么关注性能，而不考虑能源效率，要么关注修剪和压缩等技术，以使模型更节能。然而，大多数以前的工作没有研究的根本原因，能源效率低下的AMR上执行这些应用程序。AMR上的计算堆栈占总能耗的33%，因此会极大地影响机器人的电池寿命。由于对AMR充电可能会中断应用程序的执行，因此有效利用可用能量以最大限度地延长电池寿命至关重要。本文首先分析了在AMR上执行计算机视觉应用程序的功耗分解，并发现了能源效率低下的三个主要根源：传感器数据的不协调访问，面向性能的模型推理执行，以及并发作业的不协调执行。为了解决这三个效率低下的问题，我们提出了E2M，一种用于自主移动的机器人的节能中间件软件栈。首先，E2M规范不同进程对传感器数据的访问，例如，照相机帧，从而可以最小化由同时执行的作业实际捕获的数据量。其次，基于预定义的每进程性能度量（例如，安全性、准确性）和预期目标，E2M操纵流程执行周期，以找到最佳的能源性能折衷。第三，E2M协调并发进程的执行，以最大化计算硬件的总连续睡眠时间，从而最大化节能。我们已经在HydraOne上实现了E2M的原型，这是一个真实的AMR。我们的实验结果表明，与几个基线相比，E2M为计算平台节省了24%的能源，这意味着额外的11.5%的电池时间和14分钟的机器人运行时间，安全性能下降低于7.9%，准确性低于1.84%。
Autonomous mobile robots (AMRs) have been widely utilized in industry to execute various on-board computer-vision applications including autonomous guidance, security patrol, object detection, and face recognition. Most of the applications executed by an AMR involve the analysis of camera images through trained machine learning models. Many research studies on machine learning focus either on performance without considering energy efficiency or on techniques such as pruning and compression to make the model more energy-efficient. However, most previous work do not study the root causes of energy inefficiency for the execution of those applications on AMRs. The computing stack on an AMR accounts for 33% of the total energy consumption and can thus highly impact the battery life of the robot. Because recharging an AMR may disrupt the application execution, it is important to efficiently utilize the available energy for maximized battery life.In this paper, we first analyze the breakdown of power dissipation for the execution of computer-vision applications on AMRs and discover three main root causes of energy inefficiency:uncoordinated access to sensor data, performance-oriented model inference execution, anduncoordinated execution of concurrent jobs.In order to fix these three inefficiencies, we propose E2M, an energy-efficient middleware software stack for autonomous mobile robots. First, E2M regulates the access of different processes to sensor data, e.g., camera frames, so that the amount of data actually captured by concurrently executing jobs can be minimized. Second, based on a predefined per-process performance metric (e.g., safety, accuracy) and desired target, E2M manipulates the process execution period to find the best energy-performance trade off. Third, E2M coordinates the execution of the concurrent processes to maximize the total contiguous sleep time of the computing hardware for maximized energy savings. We have implemented a prototype of E2M on HydraOne, a real-world AMR. Our experimental results show that, compared to several baselines, E2M leads to 24% energy savings for the computing platform, which translates into an extra 11.5% of battery time and 14 extra minutes of robot runtime, with a performance degradation lower than 7.9% for safety and 1.84% for accuracy.
登录
查看更多内容
无通信共享充电站的自主机器人：案例研究
DOI：
10.1007/978-4-431-65941-9_10
发表时间：
2002
期刊：
Proceedings of the Fifth International Workshop on Robot Motion and Control, 2005. RoMoCo '05.
影响因子：
--
作者：
François Sempé;Angélica Muñoz;A. Drogoul
通讯作者：
A. Drogoul
影响因子：
3.7
作者：
Josué Feliu;J. Sahuquillo;S. Petit;J. Duato
通讯作者：
J. Duato
影响因子：
3.7
作者：
Garcia-Garcia, Adrian;Carlos Saez, Juan;Prieto-Matias, Manuel
通讯作者：
Prieto-Matias, Manuel
为自主机器人的长期活动提供共享充电站
DOI：
10.1109/irds.2002.1041685
发表时间：
2002
期刊：
IEEE/RSJ International Conference on Intelligent Robots and Systems
影响因子：
--
作者：
F. Michaud;E. Robichaud
通讯作者：
E. Robichaud
影响因子：
2.2
作者：
Jason M. Hirst;Jonathan R. Miller;Brent A. Kaplan;Derek D. Reed
通讯作者：
Derek D. Reed