Aulia Udink, Hasanuddin Iskandar, Dirhamsyah Muhammad, Nasaruddin Nasaruddin
Doctoral Program, School of Engineering, Post Graduate Program, Universitas Syiah Kuala, Banda Aceh, 23111, Indonesia.
Dept. of Mechanical and Industrial Engineering, Universitas Syiah Kuala, Banda Aceh, 23111, Indonesia.
Heliyon. 2024 Jul 26;10(15):e35247. doi: 10.1016/j.heliyon.2024.e35247. eCollection 2024 Aug 15.
Recently, autonomous mobile robots (AMRs) have begun to be used in the delivery of goods, but one of the biggest challenges faced in this field is the navigation system that guides a robot to its destination. The navigation system must be able to identify objects in the robot's path and take evasive actions to avoid them. Developing an object detection system for an AMR requires a deep learning model that is able to achieve a high level of accuracy, with fast inference times, and a model with a compact size that can be run on embedded control systems. Consequently, object recognition requires a convolutional neural network (CNN)-based model that can yield high object classification accuracy and process data quickly. This paper introduces a new CNN-based object detection system for an AMR that employs real-world vehicle datasets. First, we create original real-world datasets of images from Banda Aceh city. We then develop a new CNN-based object identification system that is capable of identifying cars, motorcycles, people, and rickshaws under morning, afternoon, and evening lighting conditions. An SSD Mobilenetv2 FPN Lite 320 × 320 architecture is employed for retraining using these real-world datasets. Quantitative and qualitative performance indicators are then applied to evaluate the CNN model. Training the pre-trained SSD Mobilenetv2 FPN Lite 320 × 320 model improves its classification and detection accuracy, as indicated by its performance results. We conclude that the proposed CNN-based object detection system has the potential for use in an AMR.
最近，自主移动机器人（AMR）已开始用于货物配送，但该领域面临的最大挑战之一是引导机器人到达目的地的导航系统。导航系统必须能够识别机器人路径中的物体并采取规避行动以避开它们。为AMR开发物体检测系统需要一个深度学习模型，该模型能够实现高精度、快速推理时间，并且模型尺寸紧凑，可以在嵌入式控制系统上运行。因此，物体识别需要一个基于卷积神经网络（CNN）的模型，该模型能够产生高物体分类准确率并快速处理数据。本文介绍了一种新的基于CNN的AMR物体检测系统，该系统采用真实世界的车辆数据集。首先，我们创建了来自亚齐市的原始真实世界图像数据集。然后，我们开发了一种新的基于CNN的物体识别系统，该系统能够在早晨、下午和晚上的光照条件下识别汽车、摩托车、行人及人力车。使用这些真实世界数据集对SSD Mobilenetv2 FPN Lite 320×320架构进行重新训练。然后应用定量和定性性能指标来评估CNN模型。对预训练的SSD Mobilenetv2 FPN Lite 320×320模型进行训练可提高其分类和检测准确率，其性能结果表明了这一点。我们得出结论，所提出的基于CNN的物体检测系统有潜力用于AMR。
