Sensor-based Facial expression recognition (FER) is an attractive research topic. Nowadays, FER is used for different application such as smart environments and healthcare solutions. The machine can learn human emotion by using FER technology. It is the primary and essential for quantitative analysis of human sentiments. FER is an image recognition problem within the broader field of computer vision. Face detection and tracking, reliable face recognition still present a considerable challenge for researchers in computer vision and pattern recognition. First, data processing and analytics are intensive and require a large number of computation resources and memory. Second, the fundamental technical limitation is its robustness in changes in the environment. Finally, illumination variation further complicates the design of robust algorithms because of changes in shadow casts. However, sensor-based FER overcomes all these limitations. Sensor technologies, especially low-power, wireless communication, high-capacity, and data processing have made substantial progress, making it possible for sensors to evolve from low-level data collection and transmission to high-level inference. This study aims to develop a stretchable sensor-based FER system. We use random forest machine learning algorithms used for training the FER model. Commercial stretchable facial expression dataset is simulated into the anaconda software. In this research, our stretch sensor FER dataset obtained around 95% accuracy for four different emotions (Neutral, Happy, Sad, and Disgust).
This article attempts to review papers on power assist rehabilitation robots, human motion intention, control laws, and estimation of power assist rehabilitation robots based on human motion intention in recent years. This paper presents the various ways in which human motion intention in rehabilitation can be estimated. This paper also elaborates on the control laws for the estimation of motion intention of the power assist rehabilitation robot. From the review, it has been found that the motion intention estimation method includes: Artificial Intelligence-based motion intention and Model-based motion intention estimation. The controllers include hybrid force/position control, EMG control, and adaptive control. Furthermore, Artificial Intelligence based motion intention estimation can be subdivided into Electromyography (EMG), Surface Electromyography (SEMG), Extreme Learning Machine (ELM), and Electromyography-based Admittance Control (EAC). Also, Model-based motion intention estimation can be subdivided into Impedance and Admittance control interaction. Having reviewed several papers, EAC and ELM are proposed for efficient motion intention estimation under artificial-based motion intention. In future works, Impedance and Admittance control methods are suggested under model-based motion intention for efficient estimation of motion intention of power assist rehabilitation robot. In addition, hybrid force/position control and adaptive control are suggested for the selection of control laws. The findings of this review paper can be used for developing an efficient power assist rehabilitation robot with motion intention to aid people with lower or upper limb impairment.
Upper limb movement disorders significantly hamper the ability of impaired to perform basic activities of daily living (ADL). Eating, without doubt, is one of the essential ADLs necessary for human survival. To develop a rehabilitation system meant specifically to assist the hand during eating, an in-depth knowledge of hand motion and the forces/torques produced, during eating is vital. Since, Human Upper Limb (HUL) motion is highly dexterous, its dynamic model can be beneficial for predicting the torques during different eating activities. Four degrees of freedom (DOF), dynamic model of HUL including wrist and elbow joints, focusing on elbow and wrist flexion/extension, forearm pronation/supination, wrist flexion/extension and wrist adduction/abduction is formulated, using Nonlinear AutoRegressive network with eXogenous input Neural Network (NARX-NN), during different eating activities. We conducted an experimental validation involving five different food types and using two types of cutleries. Torque prediction accuracy of the model is determined by comparing predicted values to that of measured load cell torques, for all eating activities and using Root mean square error (RMSE) as a statistical measure, to test the model performance. Torques predicted by the model track the measured torque efficiently.
Kane's method is becoming increasingly popular among the dynamists because of its advantages over the Newton-Euler and Lagrange. Many of the literatures have used Kane's method successfully to model the dynamic systems but none has provided a detailed and quick explanation on how to implement the method on a system. This paper provides a fast and easy guide to learn the Kane's method, especially for the beginners. A dynamic model of 3 DOF kinematic chain has been developed as an example to demonstrate the detailed steps involved in modeling using Kane's method. The formulated model is then verified successfully using Lagrange method.
To gain the maximum benefit from robot assisted rehabilitation therapy, participants should be actively engaged in the training session and this can be done though assist-as-needed (AAN) strategy. The assist-as-needed (AAN) control strategy gains wide popularity in the field of rehabilitation robotics in the recent years with numerous positive outcomes. The strategy encourages subjects’ active participation during physical exercise systematically by modulating robotic assistance in accordance to subjects’ movement ability while at the same time discourage the slacking behavior in motor control. For effective implementation, an accurate and consistent estimation of subjects’ functional movement or motor ability is crucial and has been a major limitation for current implementation. The existing gap between the current robotic approach and clinical practices is also another important concern that can lead to conflict in the near future. This paper provides a systematic overview of the assist-as-needed control strategies and estimation techniques found in the research literatures till date. An overview of specific clinical practices in functional motor assessment and estimation procedure that runs parallel to the robotic system counterpart is also designed to provide the significance and challenges in bridging the gap between robotic and clinical practices. This review concludes with major findings in the state of the art in AAN robotic therapy and outlines of procedures for clinical adoption. The further research is required to determine the effectiveness of clinical assessment procedure alongside with the robotic therapy that can address this need by providing a consistent and accurate estimation of subjects’ functional ability.
The study analyzes research trends, collaboration patterns, and key focus areas in the field of upper limb rehabilitation devices using bibliometric methods. With advancements in robotics and assistive technologies, these devices have become crucial for individuals with upper limb impairments, particularly stroke survivors. However, the rapid increase in publications necessitates a comprehensive understanding of research directions and influential contributions. This study used the Scopus Analyzer and VOSviewer software to examine a dataset of 1,208 publications. The Scopus analyzer provided insights into publication trends and author productivity. At the same time, VOSviewer was employed to map keyword occurrences and co-authorship networks, revealing the main topics and collaborative linkages across countries. The analysis highlights a steady increase in research output from 2015 to 2024, with a slight decline in the last two years, likely due to shifting research priorities or market saturation. Keywords such as "rehabilitation," "stroke," "upper limb," and "exoskeleton" indicate strong interest in assistive technology for motor recovery, while terms like "adaptive control" and "impedance control" emphasize the importance of control mechanisms tailored to patient needs. Additionally, international collaboration networks are led by countries like China, the United States, and Italy, reflecting their high research impact and extensive partnerships. In conclusion, this bibliometric analysis offers valuable insights into the progress and collaborative efforts within upper limb rehabilitation devices research, highlighting the interdisciplinary nature of the field and identifying potential areas for future exploration. This study serves as a reference for researchers aiming to develop further rehabilitation control solutions that enhance the quality of life for patients with upper limb impairments.
This paper presents the design and development of a new low-cost pick and place anthropomorphic robotic arm for the disabled and humanoid applications. Anthropomorphic robotic arms are weapons similar in scale, appearance, and functionality to humans, and functionality. The developed robotic arm was simple, lightweight, and has four degrees of freedom (DOF) at the hand, shoulder, and elbow joints. The measurement of the link was made close to the length of the human arm. The anthropomorphic robotic arm was actuated by four DC servo motors and controlled using an Arduino UNO microcontroller board. The voice recognition unit drove the command input for the targeted object. The forward and inverse kinematics of the proposed new robotic arm has been analysed and used to program the low cost anthropomorphic robotic arm prototype to reach the desired position in the pick and place operation. This paper’s contribution is in developing the low cost, light, and straightforward weight anthropomorphic arm that can be easily attached to other applications such as a wheelchair and the kinematic study of the specific robot. The low-cost robotic arm’s capability has been tested, and the experimental results show that it can perform basic pick place tasks for the disabled and humanoid applications.
Feedback Error Learning (FEL) control is regarded as a hybrid controller, which consists of a feedforward and feedback controller. This paper presents a new FEL control scheme to control underactuated systems with the application of Radial Basis Function Network (RBFN) based Finite Impulse Response (FIR) filter. In this system, the feedback controller is derived from backstepping control procedure, while the least square method is employed in the feedforward controller to obtain the inverse dynamic model of the plant. Simulations on a two link acrobat robot with nonzero initial angular momentum in achieving a final desired posture angle are performed to validate the proposed algorithm.
Facial expression plays an important factor in human communication which helps us to
understand the intentions and emotions of others. Generally, people infer the emotional
states of other people such as fear, sadness, joy and anger just by looking at the facial
expression and vocal tone. Moreover, facial expression can also be used to deliver messages
especially for those who are paralyzed which their only means of communication is
through facial expression. Therefore, by exploiting the facial expression of a paralyzed
patient, a sensory system could be developed which would allow the patient to
communicate with others and to assist them to actuate robotic limbs in order to improve
their mobility. Conventional methods such as vision sensors that use cameras to detect
facial expression have suffered from low mobility, high complexity, high cost and difficulty
to adapt as wearable. Stretchable electronic devices have been developed for various
applications including heaters, energy converters, transistors and sensors. Wearability,
conformability to the skin, less complicated design and low cost promotes the use of strain
sensor as part of a system for facial expression detection. This review paper presents the
development of stretchable strain sensors for human facial expression detection focusing
mainly on the materials and fabrication strategies. In addition, this paper also provides
fundamental structural design as well as challenges and opportunities in realizing
stretchable strain sensor and their various potential applications.
This paper presents system identification to obtain the closed-loop models of a couple of cooperative manipulators in a system, which function to hold deformable objects. The system works using the master-slave principle. In other words, one of the manipulators is position-controlled through encoder feedback, while a force sensor gives feedback to the other force-controlled manipulator. Using the closed-loop input and output data, the closed-loop models, which are useful for model-based control design, are estimated. The criteria for model validation are a 95% fit between the measured and simulated output of the estimated models and residual analysis. The results show that for both position and force control respectively, the fits are 95.73% and 95.88%.
'/%3e%3cuse xlink:href='%23a' transform='translate(0 -400)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -600)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -800)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -1000)'/%3e%3cuse xlink:href='%23a' transform='translate(0 -1200)'/%3e%3cpath d='M0 0h1400v800H0z' style='fill:%23010066'/%3e%3cpath d='M576 100c-166.146 0-301 134.406-301 300s134.854 300 301 300c60.027 0 115.955-17.564 162.927-47.783-27.353 9.44-56.71 14.602-87.271 14.602-147.327 0-266.897-119.172-266.897-266.01 0-146.837 119.57-266.01 266.897-266.01 32.558 0 63.746 5.815 92.602 16.468C696.217 118.91 638.305 100 576 100z' style='fill:%23fc0'/%3e%3cpath d='m914.286 471.429-99.538-53.25 29.43 108.982-66.575-91.165-20.77 110.96-20.428-111.024-66.857 90.96L699.314 418l-99.701 52.943 74.065-85.192-112.8 4.441 103.694-44.62-103.555-44.94L673.8 305.42 600 220l99.538 53.25-29.43-108.982 66.575 91.165 20.77-110.96 20.428 111.023 66.857-90.959L814.97 273.43l99.702-52.944-74.065 85.193 112.8-4.441-103.694 44.62 103.555 44.94-112.785-4.79z' style='fill:%23fc0' transform='matrix(1.2738 0 0 1.2423 -89.443 -29.478)'/%3e%3c/svg%3e)
'/%3e%3cpath fill='%23fff' d='m8.751-17.959 10.11 11.373L3.997-9.844l13.94-6.1-7.692 13.129z'/%3e%3c/svg%3e)
