Most people with motor disabilities use a joystick to control an electric wheelchair. However, those who suffer from multiple sclerosis or amyotrophic lateral sclerosis may require other methods to control an electric wheelchair. This study implements an electroencephalography (EEG)-based brain–computer interface (BCI) system and a steady-state visual evoked potential (SSVEP) to manipulate an electric wheelchair. While operating the human–machine interface, three types of SSVEP scenarios involving a real-time virtual stimulus are displayed on a monitor or mixed reality (MR) goggles to produce the EEG signals. Canonical correlation analysis (CCA) is used to classify the EEG signals into the corresponding class of command and the information transfer rate (ITR) is used to determine the effect. The experimental results show that the proposed SSVEP stimulus generates the EEG signals because of the high classification accuracy of CCA. This is used to control an electric wheelchair along a specific path. Simultaneous localization and mapping (SLAM) is the mapping method that is available in the robotic operating software (ROS) platform that is used for the wheelchair system for this study.

A novel algorithm is proposed to identify the parameters of a synchronous dual-drive ball screw gantry system in this paper. The modeling of the gantry system is described in this paper, and dynamic equations are used to derive the relationship from the motor to the coupling mechanism. The modeling results are used to design the algorithm used to identify the model parameters. The proposed algorithm uses two disturbance observers (DOB) to identify the parameters for the coupling mechanism and sliding stages. The sinusoidal position and velocity commands for the proposed identification algorithm are relatively smooth to avoid damaging the mechanism. The proposed method is easy to implement in the position control loop and velocity control loop. Finally, simulation and experimental results show that the proposed DOBs can accurately estimate the parameters for a gantry system, and the estimated results can be further used to design a corresponding controller for the gantry stage.

Learning from demonstration (LfD) is an intuitive teaching technology without extensive programming for an operator. In recent LfD research, machine vision is usually used to capture the human-robot interaction. However, it's not reliable during the machining process. In this letter, a novel intuitive high-level kinesthetic teaching technology is proposed by reconstructing the motion information recorded from human-guided demonstrations. A hierarchical BiLSTM-based machine learning algorithm is proposed in this letter to recognize and segment motion primitives according to the therblig definition. A hybrid sensing interface is used to record and extract the motion features, consisting of the velocity profile, force/torque, and gripper information. The motion features are then used to classify into the target motion primitive by the proposed classifier. The experimental results and comparisons with the state-of-the-art algorithm show that the proposed method can correctly and efficiently synthesize the recorded motion features into a motion primitive sequence. Finally, the recognition results of real-world tasks show that the proposed algorithm can be used to reconstruct the human-guided task and further used to command a KUKA robot. The experimental results of the reconstructed trajectory show that a real-world task can represent and maintain the accuracy in 2.37 mm using the proposed algorithm.

This paper proposes a solution of collision avoidance path planning for the 6-degree of freedom (6-DOF) robotic manipulator based on the virtualized platform. It can effectively avoid danger by consider the planned path whether collide with other modules through the digital simulation. This technology includes: (1) collision detection, (2) avoidance path planning. The models of existing obstacles and 6-DOF robotic manipulator in the work-space are firstly created. The collision detection is further realized through the created models. Then, an optimal avoidance path is obtained by the rapidly-exploring random tree (RRT) algorithm, but it involves many redundant vertexes. This paper proposes the Reduce Vertex RRT algorithm (RVRRT) to decrease the redundant vertex. Therefore, the collision avoidance path can increase the productivity when the 6-DOF robotic manipulator is applied in the production line.

This paper proposes a real-time coplanar Non-Uniform Rational B-Spline (NURBS) curves fitting and interpolation for 6-DOF robot arm to improve the fitting and interpolation quality, and reduce the calculation effort. The process consists of (1) reading discrete points, (2) discrete points extraction, (3) curve fitting, (4) interpolation, and (5) inverse kinematics transformation. According to the simulation and experimental results, the proposed approach certainly raises the fitting and interpolation quality, and the efficiency of calculation.