Hybrid Recurrent Neural Network Architecture-Based Intention Recognition for Human-Robot Collaboration.

Human-robot-collaboration requires robot to proactively and intelligently recognize the intention of human operator. Despite deep learning approaches have achieved certain results in performing feature learning and long-term temporal dependencies modeling, the motion prediction is still not desirable enough, which unavoidably compromises the accomplishment of tasks. Therefore, a hybrid recurrent neural network architecture is proposed for intention recognition to conduct the assembly tasks cooperatively. Specifically, the improved LSTM (ILSTM) and improved Bi-LSTM (IBi-LSTM) networks are first explored with state activation function and gate activation function to improve the network performance. The employment of the IBi-LSTM unit in the first layers of the hybrid architecture helps to learn the features effectively and fully from complex sequential data, and the LSTM-based cell in the last layer contributes to capturing the forward dependency. This hybrid network architecture can improve the prediction performance of intention recognition effectively. One experimental platform with the UR5 collaborative robot and human motion capture device is set up to test the performance of the proposed method. One filter, that is, the quartile-based amplitude limiting algorithm in sliding window, is designed to deal with the abnormal data of the spatiotemporal data, and thus, to improve the accuracy of network training and testing. The experimental results show that the hybrid network can predict the motion of human operator more precisely in collaborative workspace, compared with some representative deep learning methods.

Design of an aircraft generator with radial force control.

With the increasing electrical energy demands in aviation propulsion systems, the increase in the onboard generators' power density is inevitable. During the flight, forces coming from the gearbox or gyroscopic forces generated by flight manoeuvres like take-off and landing can act on the generators' bearings, which can lead to wear and fatigue in the bearings. Utilizing the radial force control concept in the electrical machine can relieve loads from the bearings that not only minimize the bearing losses but also increase bearing life. The objective of the MAGLEV project (Measurement and Analysis of Generator bearing Loads and Efficiency with Validation) is to study, demonstrate, and test a new class of high-speed generators with radial force control. In this paper, design steps of this type of generator and its test rig are presented and the measurement methodology used for radial force control is explained. The concept is developed in an electrical machine and is validated on a test rig by measuring required parameters like shaft displacement, vibrations and bearing temperature. Additionally, the friction moment of each generator's bearings is measured and validated in a separate test rig under comparable conditions to the bearing loads in the generator. Therefore, a novel approach to determine precisely the bearing friction in a radial load unit, rotatably supported by an additional needle bearing is used, which shows a good agreement with the calculated friction. Furthermore, new calculation methods for the operating behavior of cylindrical roller bearings with clearance are presented, which are utilized in the generator test rig.