Khalifa University Center for Autonomous Robotic Systems (KUCARS), Khalifa University of Science and Technology, Abu Dhabi 127788, UAE.
School of Engineering Technology, Purdue University, West Lafayette, IN 47907, USA.
Sensors (Basel). 2020 Aug 21;20(17):4724. doi: 10.3390/s20174724.
In recent years, robotic sorting is widely used in the industry, which is driven by necessity and opportunity. In this paper, a novel neuromorphic vision-based tactile sensing approach for robotic sorting application is proposed. This approach has low latency and low power consumption when compared to conventional vision-based tactile sensing techniques. Two Machine Learning (ML) methods, namely, Support Vector Machine (SVM) and Dynamic Time Warping-K Nearest Neighbor (DTW-KNN), are developed to classify material hardness, object size, and grasping force. An Event-Based Object Grasping (EBOG) experimental setup is developed to acquire datasets, where 243 experiments are produced to train the proposed classifiers. Based on predictions of the classifiers, objects can be automatically sorted. If the prediction accuracy is below a certain threshold, the gripper re-adjusts and re-grasps until reaching a proper grasp. The proposed ML method achieves good prediction accuracy, which shows the effectiveness and the applicability of the proposed approach. The experimental results show that the developed SVM model outperforms the DTW-KNN model in term of accuracy and efficiency for real time contact-level classification.
近年来，机器人分拣在工业中得到了广泛的应用，这是由必要性和机会驱动的。本文提出了一种新颖的基于神经形态视觉的触觉传感方法，用于机器人分拣应用。与传统的基于视觉的触觉传感技术相比，该方法具有低延迟和低功耗的特点。开发了两种机器学习 (ML) 方法，即支持向量机 (SVM) 和动态时间规整-K 最近邻 (DTW-KNN)，用于分类材料硬度、物体大小和夹持力。开发了基于事件的物体抓取 (EBOG) 实验装置来获取数据集，其中进行了 243 次实验来训练所提出的分类器。基于分类器的预测，可以自动对物体进行分拣。如果预测精度低于某个阈值，则夹爪会重新调整并重新抓取，直到达到适当的抓取。所提出的 ML 方法实现了良好的预测精度，表明了所提出方法的有效性和适用性。实验结果表明，所开发的 SVM 模型在实时接触级分类的准确性和效率方面优于 DTW-KNN 模型。
