Search for: All records

Abstract Bio-inspired soft-robots are nowadays found their place in many applications due to its flexibility, compliance and adaptivity to unstructured environment. The main intricate part of such bio-inspired soft robots are soft pneumatic actuators (SPA) which replicate or mimic the limbs and muscles. The soft actuators are pneumatically actuated and provide bending motion in most cases. However, many engineering and medical applications need axially expanding soft pneumatic actuators to deal with delicate objects. Various studies have put forward designs for SPA with axial deformation, but the majority of them have limited axial deformation, constraining motion and less overall efficacy which limit the scope of utilization. The common practice to enhance the axial deformation of SPA is by incorporating directionally customized reinforcement using fibres or by other means like yarns, fabrics, etc These types of reinforcements are generally embedded to SPA during fabrication and may not have capability for any correction or modification later on hence lack the customization. This paper presents a novel method of radial reinforcement for the enhancement of axial deformation of SPAs with provision of customization. The present study aims to enhance and/or customize the axial deformation of SPA by incorporating external and detachable reinforcement in the form of annulus shaped cap ring. The investigation encompasses the design and attachment of four distinct cap ring geometries to SPA at different locations. Experimental results affirm that cap ring reinforcement bolster the radial stiffness, curbing lateral deformation while permitting axial deformation of soft pneumatic actuators. Out of 64 distinct configurations, the one with full reinforcement, featuring four cap rings of maximum size, yields a remarkable 169% increase in pure axial deformation compared to unreinforced cases. It is also observed that by varying the number and placement locations of cap rings the pure axial deformation can be customized. This novel insight not only propels soft pneumatic actuation technology but also heralds prospects for highly agile and versatile robotic systems which can be used in medical, prosthetics, pharmaceutical and other industries. 

Artificial Intelligence (AI) is poised to revolutionize numerous aspects of human life, with healthcare among the most critical fields set to benefit from this transformation. Medicine remains one of the most challenging, expensive, and impactful sectors, with challenges such as information retrieval, data organization, diagnostic accuracy, and cost reduction. AI is uniquely suited to address these challenges, ultimately improving the quality of life and reducing healthcare costs for patients worldwide. Despite its potential, the adoption of AI in healthcare has been slower compared to other industries, highlighting the need to understand the specific obstacles hindering its progress. This review identifies the current shortcomings of AI in healthcare and explores its possibilities, realities, and frontiers to provide a roadmap for future advancements. 

People use their hands for intricate tasks like playing musical instruments, employing myriad touch sensations to inform motor control. In contrast, current prosthetic hands lack comprehensive haptic feedback and exhibit rudimentary multitasking functionality. Limited research has explored the potential of upper limb amputees to feel, perceive, and respond to multiple channels of simultaneously activated haptic feedback to concurrently control the individual fingers of dexterous prosthetic hands. This study introduces a novel control architecture for three amputees and nine additional subjects to concurrently control individual fingers of an artificial hand using two channels of context-specific haptic feedback. Artificial neural networks (ANNs) recognize subjects’ electromyogram (EMG) patterns governing the artificial hand controller. ANNs also classify the directions objects slip across tactile sensors on the robotic fingertips, which are encoded via the vibration frequency of wearable vibrotactile actuators. Subjects implement control strategies with each finger simultaneously to prevent or permit slip as desired, achieving a 94.49% ± 8.79% overall success rate. Although no statistically significant difference exists between amputees’ and non-amputees’ success rates, amputees require more time to respond to simultaneous haptic feedback signals, suggesting a higher cognitive load. Nevertheless, amputees can accurately interpret multiple channels of nuanced haptic feedback to concurrently control individual robotic fingers, addressing the challenge of multitasking with dexterous prosthetic hands.