Search

COVID-19 has caused disruptions to many aspects of everyday life. To reduce the impact of this pandemic, its spreading must be controlled via face mask wearing. Manually mask-checking for everybody is embarrassing and uncontrollable. Hence, the proposed technique is used to help for automatic mask-checking based on deep learning platforms with real-time surveillance live infra-red (IR) camera. In this paper, two recent object detection platforms, named, you only look once version 3 (YOLOv3) and TensorFlow lite are adopted to accomplish this task. The two models are trained with a dataset consisting of images of persons with/without masks. This work is simulated with Google Colab then tested in real-time on an embedded device mated with fast GPU called Raspberry Pi 4 model B, 8 GB RAM. A comparison is made between the two models to verify their performance in relation to their precision rate and processing time. The work of this paper is also succeeded to realize multiple face masks real-time detection up to 10 facemasks in a single scene with high inference speed. Temperature is also measured using IR touchless sensor for each person with sound alarming to alert fever. The presented detector is cheap, light, small, and fast, with 99% accuracy rate during training and testing.

According to the growing interest in the soft robotics research field, where various industrial and medical applications have been developed by employing soft robots. Our focus in this paper will be the Pneumatic Muscle Actuator (PMA), which is the heart of the soft robot. Achieving an accurate control method to adjust the actuator length to a predefined set point is a very difficult problem because of the hysteresis and nonlinearity behaviors of the PMA. So the construction and control of a 30 cm soft contractor pneumatic muscle actuator (SCPMA) were done here, and by using different strategies such as the PID controller, Bang-Bang controller, Neural network controller, and Fuzzy controller, to adjust the length of the (SCPMA) between 30 cm and 24 cm by utilizing the amount of air coming from the air compressor. All of these strategies will be theoretically implemented using the MATLAB/Simulink package. Also, the performance of these control systems will be compared with respect to the time-domain characteristics and the root mean square error (RMSE). As a result, the controller performance accuracy and robustness ranged from one controller to another, and we found that the fuzzy logic controller was one of the best strategies used here according to the simplicity of the implementation and the very accurate response obtained from this method.

This paper presents a simple and fast design and implementation for a soft robot arm. The proposed continuum arm has been built by a single self-bending contraction actuator (SBCA) with two-fingers soft gripper. Because of the valuable advantages of the pneumatic artificial muscle (PAM), this continuum arm provides a high degree of safety to individuals. The proposed soft robot arm has a bending behaviour of more 180° at 3.5 kg, while, its weight is 0.7 kg. Moreover, it is designed to assist the people by reducing the number of backbends and that leads to a decrease in the possibility of lower back pain.

This article proposed a novel controller structure to track the non-linear behavior of the pneumatic muscle actuator (PMA), such as the elongation for the extensor actuator and bending for the bending PMA. The proposed controller consists of a neural network (NN) controller laid in parallel with the proportional controller (P). The parallel neural network proportional (PNNP) controllers provide a high level of precision and fast-tracking control system. The PNNP has been applied to control the length of the single extensor PMA and the bending angle of the single self-bending contraction actuator (SBCA) at different load values. For further validation, the PNNP has been applied to control a human–robot shared control system. The results show the efficiency of the proposed controller structure.

In this paper, the material constant of the dielectric elastomer (DE) has been observed under three parameters; the electrical frequency, the prestretch ratio, and the environmental temperature. While the dielectric elastomer actuator (DEA) can be used under different environmental conditions, the temperature factor is considered in this paper at the prestretch condition and various frequencies. Which shows a significant effect on the constant of the DEA.

This paper proposes an innovative design of a continuum arm inspired by the human upper limb, which could rotate clockwise and counterclockwise similar to the pronation and supination movements of the human arm. In addition to this unique feature, the proposed arm can contract and bend in different directions. The proposed continuum arm is designed to provide these features and is constructed by using two contraction pneumatic muscle actuators (PMA) and one self-bending contraction actuator (SBCA). The kinematics of the proposed rotating arm has been explained. The design provides flexibility in selecting the rotating radius according to the distance between the rotating centre and the contraction actuators. This article shows the advantages of using soft actuators to form different structures, which provide multiple operations.

This article presents the development of a self-bending contraction actuator (SBCA) through the analysis of its structure, kinematics, and torque formulas, and then explores its applications. The proposed actuator has been fabricated by two methods to prove the efficiency of the human body inspiration, which represents the covering of human bones by soft tissues to protect the bone and give the soft texture. The SBCA provides bending behaviour along with a high force-to-weight ratio. As with the simple pneumatic muscle actuator (PMA), the SBCA is soft and easy to implement. Both the kinematics and the torque formula presented for the SBCA are scalable and can be used with different actuator sizes. The bending actuator has been tested under an air pressure of up to 500 kPa, and the behaviour of its bending angle, parameters, dimensions, and the bending torques have been illustrated. On the other hand, the experiments showed the efficient performances of the actuator and validate the proposed kinematics. Therefore, the actuator can be used in many different applications, such as soft grippers and continuum arms.

The position of multi-robot system in an indoor localization system is successfully estimated using a new algorithm. The localization problem is resolved by using an array of IR receiver sensors distributed uniformly in the environment. The necessary information about the localization development is collected by scanning the IR sensor array in the environment. The scheme of scanning process is done column by column to recognize and mention the position of IR receiver’s sensors, which received signals from the IR transmitter that is fixed on the robot. This principle of scanning helps to minimize the required time for robot localization. The k-means clustering algorithm is used to estimate the multi-robot locations by isolating the labeled IR receivers into clusters. Basically the multi-robot position is estimated to be the middle of each cluster. Simulation results demonstrate the advances algorithm in estimation the multi-robot positions for various dimensional IR receiver’s array.

This paper proposes a novel continuum robot arm based on the pneumatic muscle actuator (PMA). The simple design of the extensor and the contractor PMAs are used to implement the extension and the contraction sections respectively. Five actuators are used in each section to achieve an elongation and bending for the top section and a contraction and bending for the bottom section. Then, four self-bending contraction actuators (SBCA) are used instead of the five contractions PMA to enhance the bending performances. The performances of the proposed soft robot arm showed the advantages of using a biological inspiration robot arm for the unique features in comparison to its weight and cost.

This paper illustrates the design, implementation and kinematics of a novel circular pneumatic muscle actuator (CPMA), inspired by the skeletal muscles of a human. The variation of the inner diameter of this actuator is a unique feature. Furthermore, CPMA produces a radial force towards its centre by increasing the diameter of the actuator itself in addition to the reduction in the inner diameter. These performances make the presented actuator suitable to use in numerous applications. The grasping by a soft gripper is chosen as an application to design an efficient soft gripper by using single and multiple CPMAs.

The end effector is a major part of a robot system and it defines the task the robot can perform. However, typically, a gripper is suited to grasping only a single or relatively small number of different objects. Dexterous grippers offer greater grasping ability but they are often very expensive, difficult to control and are insufficiently robust for industrial operation. This paper explores the principles of soft robotics and the design of low-cost grippers able to grasp a broad range of objects without the need for complex control schemes. Two different soft end effectors have been designed and built and their physical structure, characteristics, and operational performances have been analyzed. The soft grippers deform and conform to the object being grasped, meaning they are simple to control and minimal grasp planning is required. The soft nature of the grippers also makes them better suited to handling fragile and delicate objects than a traditional rigid gripper.

Designing a multi-robot system provides numerous\ud advantages for many applications such as low cost, multi-tasking and more efficient group work. However, the rigidity of the robots used in industrial and medical applications increases the probability of injury. Therefore, lots of research is done to increase the safety factor for robot-human interaction. As a result, either separation between the human and robot is suggested, or the force shutdown to the robot system is applied.\ud These solutions might be useful for industrial applications, but it is not for medical applications as a direct interaction between the human and the machine is required. To overcome the rigidity problem, a soft robot arm is presented in this paper. Studying the structure and performance of a contraction pneumatic muscle\ud actuator (PMA) is illustrated, then useful strategies are used to implement a multi PMA continuum arm to increase the performance options for such types of the actuator. Moreover, twin arms are constructed to organise a collaborative project depending on the performance abilities of the proposed arms and end effectors.

Modelling a continuum arm is one of the major\ud challenges in soft robotic researches. An accurate position model allows wider use of continuum robot arms in industrial and medical applications. Furthermore, accurate control can be achieved. This paper illustrates the 3D position of a constructed soft arm from 4 pneumatic muscle actuators (PMAs) in parallel, and models the movement of its free end in space. The performance of the contraction and extension PMAs and the behaviour of the contraction and extension arms are analysed, and a comparison between the two arms is explained. Finally, the\ud mathematical models are presented and validated.