Autonomous IoT Research Center, Korea Electronics Technology Institute, Seongnam 13509, Republic of Korea.
Caterpillar Inc., Peoria, IL 61629, USA.
Sensors (Basel). 2023 Apr 15;23(8):4005. doi: 10.3390/s23084005.
This paper presents a benchmark analysis of NVIDIA Jetson platforms when operating deep learning-based 3D object detection frameworks. Three-dimensional (3D) object detection could be highly beneficial for the autonomous navigation of robotic platforms, such as autonomous vehicles, robots, and drones. Since the function provides one-shot inference that extracts 3D positions with depth information and the heading direction of neighboring objects, robots can generate a reliable path to navigate without collision. To enable the smooth functioning of 3D object detection, several approaches have been developed to build detectors using deep learning for fast and accurate inference. In this paper, we investigate 3D object detectors and analyze their performance on the NVIDIA Jetson series that contain an onboard graphical processing unit (GPU) for deep learning computation. Since robotic platforms often require real-time control to avoid dynamic obstacles, onboard processing with a built-in computer is an emerging trend. The Jetson series satisfies such requirements with a compact board size and suitable computational performance for autonomous navigation. However, a proper benchmark that analyzes the Jetson for a computationally expensive task, such as point cloud processing, has not yet been extensively studied. In order to examine the Jetson series for such expensive tasks, we tested the performance of all commercially available boards (i.e., Nano, TX2, NX, and AGX) with state-of-the-art 3D object detectors. We also evaluated the effect of the TensorRT library to optimize a deep learning model for faster inference and lower resource utilization on the Jetson platforms. We present benchmark results in terms of three metrics, including detection accuracy, frame per second (FPS), and resource usage with power consumption. From the experiments, we observe that all Jetson boards, on average, consume over 80% of GPU resources. Moreover, TensorRT could remarkably increase inference speed (i.e., four times faster) and reduce the central processing unit (CPU) and memory consumption in half. By analyzing such metrics in detail, we establish research foundations on edge device-based 3D object detection for the efficient operation of various robotic applications.
本文对 NVIDIA Jetson 平台在运行基于深度学习的 3D 目标检测框架时进行了基准分析。三维（3D）目标检测对于机器人平台的自主导航非常有益，例如自动驾驶汽车、机器人和无人机。由于该功能提供了单次推断，可以提取具有深度信息和相邻物体航向方向的 3D 位置，机器人可以生成可靠的路径以避免碰撞。为了实现 3D 目标检测的顺利运行，已经开发了几种使用深度学习构建探测器的方法，以便进行快速准确的推断。在本文中，我们研究了 3D 目标探测器，并分析了它们在包含用于深度学习计算的板载图形处理单元（GPU）的 NVIDIA Jetson 系列上的性能。由于机器人平台通常需要实时控制以避免动态障碍物，因此具有内置计算机的板载处理是一种新兴趋势。Jetson 系列具有紧凑的板尺寸和适合自主导航的计算性能，满足了这些要求。然而，对于像点云处理这样的计算密集型任务，还没有广泛研究适当的基准来分析 Jetson。为了检验 Jetson 系列在这些昂贵任务中的性能，我们使用最先进的 3D 目标探测器测试了所有市售板（即 Nano、TX2、NX 和 AGX）的性能。我们还评估了 TensorRT 库的效果，以优化深度学习模型，从而在 Jetson 平台上实现更快的推断和更低的资源利用率。我们根据三个指标（包括检测精度、每秒帧数（FPS）和资源利用率以及功耗）呈现基准测试结果。从实验中，我们观察到所有 Jetson 板的 GPU 资源平均消耗超过 80%。此外，TensorRT 可以显著提高推断速度（即快四倍），并将 CPU 和内存消耗降低一半。通过详细分析这些指标，我们为基于边缘设备的 3D 目标检测奠定了研究基础，以便在各种机器人应用中高效运行。
