International Journal of Robotics
Volume:9 Issue: 1, Spring 2022

The first and most important part of mechanical design of a prosthetic hand is the finger. Over the years, many diverse and innovative designs for the prosthetic finger mechanism have been proposed. For this aim, capability of grasping objects in a stable manner with suitable contact force and an anthropomorphic structure are critical factors for design. In this article, after examining the anatomy of a natural finger the most prominent mechanisms offered by researchers are investigated. Then the ATLAS artificial finger mechanism and the 3D-printed prototype of which is introduced. Finally, the amount of contact force produced by the ATLAS upper finger phalange is calculated and verified with some motion study simulations. For validation of proposed mechanism, the amount of contact forces produced by the designed finger and the natural finger are compared. The results prove the effectiveness of the design.

In this paper, the design and performance evaluation of a new safety stop mechanism for a soft-hand exoskeleton are presented. The considered wearable orthosis comprises an under-actuated tendon-driven mechanism to perform flexion and extension on each finger using a separate electrical motor. The flexor and extensor tendons move through different paths connected to the motors with custom-made double-groove rollers to flex and extend the thumb, index, and middle fingers. A series flexible actuator unit is designed, including a mechanical module and a flexible one, fulfilling the hand-wearable robot’s functional and safety requirements. The actuator system’s flexible module uses a novel safety stop mechanism to prevent hyper-flexion, hyper-extension, or large forces applied to the user’s hand. Experiments are conducted on a healthy subject to evaluate the effectiveness of the design exoskeleton for patients with hand movement disorders. The experimental results show that the robot can follow the desired path by preserving its back-drivability and compliant properties. The efficacy of the novel safety stop mechanism is also evaluated on the prototype version of the robot, which shows that it can mechanically restrict the range of motion to a safe range. Finally, an adaptive variable impedance controller is designed to achieve assist-as-needed characteristics for the robot. The proposed controller overcomes the need to direct measurement of the participation of the patient via force sensors, which could ease the rehabilitation process.

The method is presented for object assembling via a manipulator robot. This method was designed to track the pieces based on image feedback for pick and placement tasks. The depth of the pieces is calculated by stereo triangulation. Vision-guided robotics is most often based on the training steps, therefore it is a time-consuming process. For this reason, we have proposed a modified stereo vision method to predict the movement of the part in the image space. The linear and angular velocities of moving objects predict by a state estimator. The object velocity components predicted by estimation algorithms such as Kalman filter, Recursive least square and Extended Kalman Filter. Results show that in the case of, Extended Kalman filter estimator shows better tracking and convergence behavior. This method does not need to know the three-dimensional model of the parts, and it can be used on pick and place robots if the physical limitations of the joints are considered. The proposed method was experimentally tested in a laboratory environment. The cameras were installed parallel and non-parallel to determine the effect of the field of view on the precision and speed detection. A comparison of the simulation and experimental results showed that the use of the parallel stereo Image-based visual servoing with the Extended Kalman Filter method could be smoother and more accurate than the other methods.

For decades, plastic components have been the main parts of products in industries such as food, pharmaceutical, automotive, etc. Generally, these components are created by injection molding machines. Using these machines, raw materials are converted to plastic parts, e.g., bottle caps, dosing spoons, and bumpers. The part of the machine that provisionally holds plastic products is called “Mold” which has a unique form for each product. Since molds are sensitive components with high prices, appropriate care is required. When mold is used as the dynamic part of the machine, it’s a high potential for damages due to incomplete product ejection. Utilizing an automated inspection system is a modern solution to prevent possible problems. In this paper, we propose an intelligent system based on machine vision that consists of image capturing, processing, and classification sections. In the processing section, we have used a novel modified Local Binary Pattern algorithm which leads to the suitable features for classifying images into two categories. To achieve the best classifier, four potent machine learning-based methods are evaluated: KNN, SVM, Random Forest, and Gradient Boosting. This evaluation is based on criteria like F1-score, training and processing time, and the experimental results claim that the SVM method is the best classifier with 11.87ms training time, 9.04us processing time, and F1-Score of 0.96.

This paper presents a real-time approach for detecting compensatory movements in upper limb rehabilitation for stroke patients using deep learning algorithms. The study applied Recurrent Neural Networks (RNN), Gated Recurrent Unit (GRU), Long-Short-Term-Memory (LSTM), and Transformer to analyze Microsoft Kinect data from the Toronto Rehab Stroke Pose dataset. The models were trained with focal loss to address imbalanced data distribution. The simulation results showed that the proposed deep learning algorithms are effective in detecting compensatory movements. The GRU-based models provide the fastest results and the transformer models exhibit the best accuracy and fastest inference time on the employed CPU .

Here, we are going to design a stabilized controller for the Stewart platform. A new model of the Stewart platform will be presented which has many applications in the industry. The dynamics of the Stewart platform are presented in two separate systems. One system for the linear motion of the Stewart platform and another system for its angular moment. In addition, we use a quaternion-based method to analyze the dynamics of the Stewart platform. The 6-DOF Stewart-Platform dynamics is nonlinear, then at first by using the feedback linearization method we convert the nonlinear dynamics in new space as a linear state-space. Then we design an -stabilized controller for this platform in linear space. A linear controller for linear motion systems will be designed but for the second system, it must first be linearization and then design controller for it. After design of stabilized-LQR controller for linearized space system, we convert our design to original nonlinear space and exert on system for simulations. The simulations results show that we will succeed to design a controller for the Stewart platform.