A Novel, Oriented to Graphs Model of Robot Arm Dynamics

Robotics is an interdisciplinary field and there exist several well-known approaches to represent the dynamics model of a robot arm. The robot arm is an open kinematic chain of links connected through rotational and translational joints. In the general case, it is very difficult to obtain explicit expressions for the forces and the torques in the equations where the driving torques of the actuators produce desired motion of the gripper. The robot arm control depends significantly on the accuracy of the dynamic model. In the existing literature, the complexity of the dynamic model is reduced by linearization techniques or techniques like machine learning for the identification of unmodelled dynamics. This paper proposes a novel approach for deriving the equations of motion and the actuator torques of a robot arm with an arbitrary number of joints. The proposed approach for obtaining the dynamic model in closed form employs graph theory and the orthogonality principle, a powerful concept that serves as a generalization for the law of conservation of energy. The application of this approach is demonstrated using a 3D-printed planar robot arm with three degrees of freedom. Computer experiments for this robot are executed to validate the dynamic characteristics of the mathematical model of motion obtained by the application of the proposed approach. The results from the experiments are visualized and discussed in detail.

Facilitative Exercise for Surface Myoelectric Activity Using Robot Arm Control System – Training Scheme with Gradually Increasing Difficulty Level –

Various control systems for robot arms using surface myoelectric signals have been developed. Abundant pattern-recognition techniques have been proposed to predict human motion intent based on these signals. However, it is laborious for users to train the voluntary control of myoelectric signals using those systems. In this research, we aim to develop a rehabilitation support system for hemiplegic upper limbs with a robot arm controlled by surface myoelectric signals. In this study, we construct a simple one-link robot arm that is controlled by estimating the wrist motion from the surface myoelectric signals on the forearm. We propose a training scheme with gradually increasing difficulty level for robot arm manipulation to evoke surface myoelectric signals. Subsequently, we investigate the possibility of facilitative exercise for the voluntary surface myoelectric activity of the desired muscles through trial experiments.

Using Deep Learning Technology to Realize the Automatic Control Program of Robot Arm Based on Hand Gesture Recognition

In this study, the robot arm control, computer vision, and deep learning technologies are combined to realize an automatic control program. There are three functional modules in this program, i.e., the hand gesture recognition module, the robot arm control module, and the communication module. The hand gesture recognition module records the user’s hand gesture images to recognize the gestures’ features using the YOLOv4 algorithm. The recognition results are transmitted to the robot arm control module by the communication module. Finally, the received hand gesture commands are analyzed and executed by the robot arm control module. With the proposed program, engineers can interact with the robot arm through hand gestures, teach the robot arm to record the trajectory by simple hand movements, and call different scripts to satisfy robot motion requirements in the actual production environment.

Improving Gaussianity of EMG Envelope for Myoelectric Robot Arm Control

Several methods have been developed in biomedical signal processing to extract the envelope and features of electromyography (EMG) signals and predict human motion. Also, efforts were made to use this information to improve the interaction of a human body and artificial protheses. The main operations here are envelope acquiring, artifacts filtering, estimate smoothing, EMG value standardizing, feature classifying, and motion recognizing. In this paper, we employ EMG data to extract the envelope with a highest Gaussianity using the rectified signal, where we deal with the absolute EMG signals so that all values become positive. First, we remove artifacts from EMG data by using filters such as the Kalman filter (KF), H1 filter, unbiased finite impulse response (UFIR) filter, and the cKF, cH1 filter, and cUFIR filter modified for colored measurement noise. Next, we standardize the EMG envelope and improve the Gaussianity. Finally, we extract the EMG signal features to provide an accurate prediction.

Gesture and Vision Based Automatic Grasping and Flexible Placement in Teleoperation

Teleoperation system has attracted a lot of attention because of its advantages in dangerous or unknown environment. It is very difficult to develop an operating system that can complete complex tasks in an completely autonomous. This paper proposes a robot arm control strategy based on gesture and visual perception. The strategy combines the advantages of humans and robots to obtain a convenient and flexible interaction model. The hand data were obtained by Leap-Motion. Then a neural network algorithm was used to classify the nine gestures used for robot control by a finite state machine. The control mode switched between indicative control and mapping control. The robot acquired a autonomous grasp ability by incorporating YOLO 6D, depth data, and a probabilistic roadmap planner algorithm. The robot completed most of the trajectory independently, and a few flexible trajectories required a user to make mapping actions. This interactive mode reduces the burden of the user to a certain extent, that makes up for the shortcomings of traditional teleoperation.