In recent years, surface electromyography (sEMG)-based human–computer interaction has been developed to improve the quality of life for people. Gesture recognition based on the instantaneous values of sEMG has the advantages of accurate prediction and low latency. However, the low generalization ability of the hand gesture recognition method limits its application to new subjects and new hand gestures, and brings a heavy training burden. For this reason, based on a convolutional neural network, a transfer learning (TL) strategy for instantaneous gesture recognition is proposed to improve the generalization performance of the target network. CapgMyo and NinaPro DB1 are used to evaluate the validity of our proposed strategy. Compared with the non-transfer learning (non-TL) strategy, our proposed strategy improves the average accuracy of new subject and new gesture recognition by 18.7% and 8.74%, respectively, when up to three repeated gestures are employed. The TL strategy reduces the training time by a factor of three. Experiments verify the transferability of spatial features and the validity of the proposed strategy in improving the recognition accuracy of new subjects and new gestures, and reducing the training burden. The proposed TL strategy provides an effective way of improving the generalization ability of the gesture recognition system.
Unmanned aerial vehicles (UAVs) are frequently adopted in disaster management. The vision they provide is extremely valuable for rescuers. However, they face severe problems in their stability in actual disaster scenarios, as the images captured by the on-board sensors cannot consistently give enough information for deep learning models to make accurate decisions. In many cases, UAVs have to capture multiple images from different views to output final recognition results. In this paper, we desire to formulate the fly path task for UAVs, considering the actual perception needs. A convolutional neural networks (CNNs) model is proposed to detect and localize the objects, such as the buildings, as well as an optimization method to find the optimal flying path to accurately recognize as many objects as possible with a minimum time cost. The simulation results demonstrate that the proposed method is effective and efficient, and can address the actual scene understanding and path planning problems for UAVs in the real world well.
16 September 2023 in Journal of Intelligent & Robotic Systems
Purpose: The purpose of this paper was to present a soft landing control strategy for a biped robot to avoid and absorb the impulsive reaction forces (which weakens walking stability) caused by the landing impact between the swing foot and the ground. Design/methodology/approach: First, a suitable trajectory of the swing foot is preplanned to avoid the impulsive reaction forces in the walking direction. Second, the impulsive reaction forces of the landing impact are suppressed by the on-line trajectory modification based on the extended time-domain passivity control with admittance causality that has the reaction forces as inputs and the decomposed swing foot’s positions to trim off the forces as the outputs. Findings: The experiment data and results are described and analyzed, showing that the proposed soft landing control strategy can suppress the impulsive forces and improve walking stability. Originality/value: The main contribution is that a soft landing control strategy for a biped robot was proposed to deal with the impulsive reaction forces generated by the landing impact, which enhances walking stability.
16 May 2016 in Industrial Robot: the international journal of robotics research and application
Purpose: Walking on inclined ground is an important ability for humanoid robots. In general, conventional strategies for walking on slopes lack technical analysis in, first, the waist posture with respect to actual robot and, second, the landing impact, which weakens the walking stability. The purpose of this paper is to propose a generic method for walking pattern generation considering these issues with the aim of enabling humanoid robot to walk dynamically on a slope. Design/methodology/approach: First, a virtual ground method (VGM) is proposed to give a continuous and intuitive zero-moment point (ZMP) on slopes. Then, the dynamic motion equations are derived based on 2D and 3D models, respectively, by using VGM. Furthermore, the waist posture with respect to the actual robot is analyzed. Finally, a reformative linear inverted pendulum (LIP) named the asymmetric linear inverted pendulum (ALIP) is proposed to achieve stable and dynamical walking in any direction on a slope with lower landing impact. Findings: Simulations and experiments are carried out using the DRC-XT humanoid robot platform with the aim of verifying the validity and feasibility of these new methods. ALIP with consideration of waist posture is practical in extending the ability of walking on slopes for humanoid robots. Originality/value: A generic method called ALIP for humanoid robots walking on slopes is proposed. ALIP is based on LIP and several changes, including model analysis, motion equations and ZMP functions, are discussed.