Speech emotion recognition (SER) plays an important role in real-time applications of human-machine interaction. The Attention Mechanism is widely used to improve the performance of SER. However, the applicable rules of attention mechanism are not deeply discussed. This paper discussed the difference between Global-Attention and Self-Attention and explored their applicable rules to SER classification construction. The experimental results show that the Global-Attention can improve the accuracy of the sequential model, while the Self-Attention can improve the accuracy of the parallel model when conducting the model with the CNN and the LSTM. With this knowledge, a classifier (CNN-LSTM×2+Global-Attention model) for SER is proposed. The experiments result show that it could achieve an accuracy of 85.427% on the EMO-DB dataset.

The increased demand for robotic manipulator has driven the development of industrial manufacturing. In particular, the trajectory tracking and contact constant force control of the robotic manipulator for the working environment under contact condition has become popular because of its high precision and quality operation. However, the two factors are opposite, that is to say, to maintain constant force control, it is necessary to make limited adjustment to the trajectory. It is difficult for the traditional PID controller because of the complexity parameters and nonlinear characteristics. In order to overcome this issue, a PID controller based on fuzzy neural network algorithm is developed in this paper for tracking the trajectory and contact constant force simultaneously. Firstly, the kinetic and potential energy is calculated, and the Lagrange function is constructed for a two-link robotic manipulator. Furthermore, a precise dynamic model is built for analyzing. Secondly, fuzzy neural network algorithm is proposed, and two kinds of turning parameters are derived for trajectory tracking and contact constant force control. Finally, numerical simulation results are reported to demonstrate the effectiveness of the proposed method.

With advancements in mobile robot technology, wheel-legged robots have emerged as promising next-generation mobile solutions, reducing design costs and enhancing adaptability in unstructured environments. As underactuated systems, their balance control has become a prominent research focus. Despite there being numerous control approaches, challenges remain. Balance control methods for wheel-legged robots are influenced by hardware characteristics, such as motor friction, which can induce oscillations and hinder dynamic convergence. This paper presents a friction feedforward Linear Quadratic Regulator (LQR) balance control method. Specifically, a basic LQR controller is developed based on the dynamics model of the wheel-legged robot, and a Stribeck friction model is established to characterize motor friction. A constant-speed excitation trajectory is designed to gather data for friction identification, and the Particle Swarm Optimization (PSO) algorithm is applied to determine the optimal friction parameters. The identified friction model is subsequently incorporated as feedforward compensation for the LQR controller’s torque output, resulting in the proposed friction feedforward LQR balance control algorithm. The minimum standard deviation for friction identification is approximately 0.30, and the computed friction model values closely match the actual values, indicating effective and accurate identification results. Balance experiments demonstrate that under diverse conditions—such as flat ground, single-sided bridges, and disturbance scenarios—the convergence performance of the friction feedforward LQR algorithm markedly surpasses that of the baseline LQR, effectively reducing oscillations, accelerating convergence, and improving the robot’s stability and robustness.

Purpose: The purpose of this paper is to reduce the strain and vibration during robotic machining. Design/methodology/approach: An intelligent approach based on particle swarm optimization (PSO) and adaptive iteration algorithms is proposed to optimize the PD control parameters in accordance with robotic machining state. Findings: The proposed intelligent approach can significantly reduce robotic machining strain and vibration. Originality value: The relationship between robotic machining parameters is studied and the dynamics model of robotic machining is established. In view of the complexity of robotic machining process, the PSO and adaptive iteration algorithms are used to optimize the PD control parameters in accordance with robotic machining state. The PSO is used to optimize the PD control parameters during stable-machining state, and the adaptive iteration algorithm is used to optimize the PD control parameters during cut-into state.