Asymmetric Identification Model for Human-Robot Contacts via Supervised Learning

Abstract

Human-robot interaction (HRI) occupies an essential role in the flourishing market for intelligent robots for a wide range of asymmetric personal and entertainment applications, ranging from assisting older people and the severely disabled to the entertainment robots at amusement parks. Improving the way humans and machines interact can help democratize robotics. With machine and deep learning techniques, robots will more easily adapt to new tasks, conditions, and environments. In this paper, we develop, implement, and evaluate the performance of the machine-learning-based HRI model in a collaborative environment. Specifically, we examine five supervised machine learning models viz. the ensemble of bagging trees (EBT) model, the k-nearest neighbor (kNN) model, the logistic regression kernel (LRK), the fine decision trees (FDT), and the subspace discriminator (SDC). The proposed models have been evaluated on an ample and modern contact detection dataset (CDD 2021). CDD 2021 is gathered from a real-world robot arm, Franka Emika Panda, when it was executing repetitive asymmetric movements. Typical performance assessment factors are applied to assess the model effectiveness in terms of detection accuracy, sensitivity, specificity, speed, and error ratios. Our experiential evaluation shows that the ensemble technique provides higher performance with a lower error ratio compared with other developed supervised models. Therefore, this paper proposes an ensemble-based bagged trees (EBT) detection model for classifying physical human–robot contact into three asymmetric types of contacts, including noncontact, incidental, and intentional. Our experimental results exhibit outstanding contact detection performance metrics scoring 97.1%, 96.9%, and 97.1% for detection accuracy, precision, and sensitivity, respectively. Besides, a low prediction overhead has been observed for the contact detection model, requiring a 102 µS to provide the correct detection state. Hence, the developed scheme can be efficiently adopted through the application requiring physical human–robot contact to give fast accurate detection to the contacts between the human arm and the robot arm.

Neural Network-Based Classifier for Collision Classification and Identification for a 3-DOF Industrial Robot

“…Their method only used IR sensor measurements as inputs to the neuro-fuzzy inference model. Abu Al-Haija and Al-Saraireh [20] applied five methods of machine learning to detect collisions. These methods were the k-nearest neighbor (KNN) model, the fine decision trees (FDT) model, the logistic regression kernel (LRK), the subspace discriminator (SDC), and the ensemble of bagging trees (EBT) model.…”

An intelligent identification and classification system for malicious uniform resource locators (URLs)

“… Dataset Shuffling: This process is responsible for mixing data and preserving logical relationships between columns. It randomly shuffles data from a dataset within a set of features (columns) [ 35 ]. The process of Dataset Shuffling is illustrated in Fig 4 C .…”

Symmetrical Simulation Scheme for Anomaly Detection in Autonomous Vehicles Based on LSTM Model

“…We can observe that majority of observations were correctly classified with only three observations are incorrectly classified. In addition, we evaluated our test method using detection accuracy, detection precision, detection recall, and the F1-score metrics, as represented in Table 2 [42]. The accuracy of our model reached 99.95%.…”

“…The detection accuracy, precision, recall and the F1-Score are calculated using the standard Equations (Equations ( 3)-( 6)) [41]. In addition, we evaluated our test method using detection accuracy, detection precision, detection recall, and the F1-score metrics, as represented in Table 2 [42]. The accuracy of our model reached 99.95%.…”