Current-Sensor-Based Contact Stiffness Detection for Prosthetic Hands

Deng, Hua; Xu, Xiaolei; Zhuo, Wendi; Zhang, Yi

doi:10.1109/access.2020.2972588

Cited by 14 publications

(7 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, we proposed a methodology that uses intrinsic sensors (sensors and parameters already available on the prosthesis) for the normal functionality of the prosthesis that does not increase the cost and complexity of the device. In particular, we exploited the following intrinsic sensors: the motor-side current, whose relationship with the contact stiffness has been analytically demonstrated by Deng et al ( 2020 ); the reference position, given as input to control the device closure; and the position effectively measured by the encoder (encoder position). We implemented a closed-loop vibratory feedback, using a single vibromotor embedded in the Hannes system, closely related to the predictions made by the classifier.…”

Section: Introductionmentioning

confidence: 99%

Object stiffness recognition and vibratory feedback without ad-hoc sensing on the Hannes prosthesis: A machine learning approach

et al. 2023

View full text Add to dashboard Cite

IntroductionIn recent years, hand prostheses achieved relevant improvements in term of both motor and functional recovery. However, the rate of devices abandonment, also due to their poor embodiment, is still high. The embodiment defines the integration of an external object – in this case a prosthetic device – into the body scheme of an individual. One of the limiting factors causing lack of embodiment is the absence of a direct interaction between user and environment. Many studies focused on the extraction of tactile information via custom electronic skin technologies coupled with dedicated haptic feedback, though increasing the complexity of the prosthetic system. Contrary wise, this paper stems from the authors' preliminary works on multi-body prosthetic hand modeling and the identification of possible intrinsic information to assess object stiffness during interaction.MethodsBased on these initial findings, this work presents the design, implementation and clinical validation of a novel real-time stiffness detection strategy, without ad-hoc sensing, based on a Non-linear Logistic Regression (NLR) classifier. This exploits the minimum grasp information available from an under-sensorized and under-actuated myoelectric prosthetic hand, Hannes. The NLR algorithm takes as input motor-side current, encoder position, and reference position of the hand and provides as output a classification of the grasped object (no-object, rigid object, and soft object). This information is then transmitted to the user via vibratory feedback to close the loop between user control and prosthesis interaction. This implementation was validated through a user study conducted both on able bodied subjects and amputees.ResultsThe classifier achieved excellent performance in terms of F1Score (94.93%). Further, the able-bodied subjects and amputees were able to successfully detect the objects' stiffness with a F1Score of 94.08% and 86.41%, respectively, by using our proposed feedback strategy. This strategy allowed amputees to quickly recognize the objects' stiffness (response time of 2.82 s), indicating high intuitiveness, and it was overall appreciated as demonstrated by the questionnaire. Furthermore, an embodiment improvement was also obtained as highlighted by the proprioceptive drift toward the prosthesis (0.7 cm).

show abstract

Section: Introductionmentioning

confidence: 99%

Object stiffness recognition and vibratory feedback without ad-hoc sensing on the Hannes prosthesis: A machine learning approach

et al. 2023

View full text Add to dashboard Cite

show abstract

“…All these examples have a common theme: the sensing element is embedded in the finger. In fact, the only grasp force sensing approach found in the literature at the time of conducting this research were current sensing approaches [ 33 , 34 ]. This is problematic for several reasons.…”

Section: Introductionmentioning

confidence: 99%

An Improved Approach for Grasp Force Sensing and Control of Upper Limb Soft Robotic Prosthetics

2023

View full text Add to dashboard Cite

The following research proposes a closed loop force control system, which is implemented on a soft robotic prosthetic hand. The proposed system uses a force sensing approach that does not require any sensing elements to be embedded in the prosthetic’s fingers, therefore maintaining their monolithic structural integrity, and subsequently decreasing the cost and manufacturing complexity. This is achieved by embedding an aluminum test specimen with a full bridge strain gauge circuit directly inside the actuator’s housing rather than in the finger. The location of the test specimen is precisely at the location of the critical section of the bending moment on the actuator housing due to the tension in the driving tendon. Therefore, the resulting loadcell can acquire a signal proportional to the prosthetic’s grasping force. A PI controller is implemented and tested using this force sensing approach. The experiment design includes a flexible test object, which serves to visually demonstrate the force controller’s performance through the deformation that the test object experiences. Setpoints corresponding to “light”, “medium”, and “hard” grasps were tested with pinch, tripod, and full grasps and the results of these tests are documented in this manuscript. The developed controller was found to have an accuracy of ±2%. Additionally, the deformation of the test object increased proportionally with the given grasp force setpoint, with almost no deformation during the light grasp test, slight deformation during the medium grasp test, and relatively large deformation of the test object during the hard grasp test.

show abstract

“…The sEMG signals of 15 different finger movements were classified with a 99.52% accuracy. However, these methods do not take the grip into account when studying the grip of an object by hand, and the grip size is important when the user grabs the object with a manipulator [17][18][19]. For grip estimation, Ma et al [20] collected sEMG signals in the forearm multi-channel, the grip was collected by a force sensor, and predictive models were built using a gene expression programming algorithm and neural network to predict grip.…”

Section: Introductionmentioning

confidence: 99%

A Grip Strength Estimation Method Using a Novel Flexible Sensor under Different Wrist Angles

Wang

Zheng

Yang

et al. 2022

Sensors

View full text Add to dashboard Cite

It is a considerable challenge to realize the accurate, continuous detection of handgrip strength due to its complexity and uncertainty. To address this issue, a novel grip strength estimation method oriented toward the multi-wrist angle based on the development of a flexible deformation sensor is proposed. The flexible deformation sensor consists of a foaming sponge, a Hall sensor, an LED, and photoresistors (PRs), which can measure the deformation of muscles with grip strength. When the external deformation squeezes the foaming sponge, its density and light intensity change, which is detected by a light-sensitive resistor. The light-sensitive resistor extended to the internal foaming sponge with illuminance complies with the extrusion of muscle deformation to enable relative muscle deformation measurement. Furthermore, to achieve the speed, accuracy, and continuous detection of grip strength with different wrist angles, a new grip strength-arm muscle model is adopted and a one-dimensional convolutional neural network based on the dynamic window is proposed to recognize wrist joints. Finally, all the experimental results demonstrate that our proposed flexible deformation sensor can accurately detect the muscle deformation of the arm, and the designed muscle model and convolutional neural network can continuously predict hand grip at different wrist angles in real-time.

show abstract

Current-Sensor-Based Contact Stiffness Detection for Prosthetic Hands

Cited by 14 publications

References 42 publications

Object stiffness recognition and vibratory feedback without ad-hoc sensing on the Hannes prosthesis: A machine learning approach

Object stiffness recognition and vibratory feedback without ad-hoc sensing on the Hannes prosthesis: A machine learning approach

An Improved Approach for Grasp Force Sensing and Control of Upper Limb Soft Robotic Prosthetics

A Grip Strength Estimation Method Using a Novel Flexible Sensor under Different Wrist Angles

Contact Info

Product

Resources

About