A Soft Sensor-Based Three-Dimensional (3-D) Finger Motion Measurement System.

In this study, a soft sensor-based three-dimensional (3-D) finger motion measurement system is proposed. The sensors, made of the soft material Ecoflex, comprise embedded microchannels filled with a conductive liquid metal (EGaln). The superior elasticity, light weight, and sensitivity of soft sensors allows them to be embedded in environments in which conventional sensors cannot. Complicated finger joints, such as the carpometacarpal (CMC) joint of the thumb are modeled to specify the location of the sensors. Algorithms to decouple the signals from soft sensors are proposed to extract the pure flexion, extension, abduction, and adduction joint angles. The performance of the proposed system and algorithms are verified by comparison with a camera-based motion capture system.

A Sensorized Soft Robotic Hand with Adhesive Fingertips for Multimode Grasping and Manipulation.

Soft robotic grippers excel at achieving conformal and reliable contact with objects without the need for complex control algorithms. However, they still lack in grasp and manipulation abilities compared with human hands. In this study, we present a sensorized multi-fingered soft gripper with bioinspired adhesive fingertips that can provide both fingertip-based adhesion grasping and finger-based form closure grasping modes. The gripper incorporates mushroom-like microstructures on its adhesive fingertips, enabling robust adhesion through uniform load shearing. A single fingertip exhibits a maximum load capacity of 4.18 N against a flat substrate. The soft fingers have multiple joints, and each joint can be independently actuated through pneumatic control. This enables diverse bending motions and stable grasping of various objects, with a maximum load capacity of 28.29 N for three fingers. In addition, the soft gripper is equipped with a kirigami-patterned stretchable sensor for motion monitoring and control. We demonstrate the effectiveness of our design by successfully grasping and manipulating a diverse range of objects with varying shapes, sizes, and curvatures. Moreover, we present the practical application of our sensorized soft gripper for remotely controlled cooking.

A Hybrid Jamming Structure Combining Granules and a Chain Structure for Robotic Applications.

To allow versatile manipulation of soft robots made of compliant materials with limited force transmission, variable stiffness has been actively developed, which has become one of the most important factors in soft robotics. Variable stiffness is usually achieved by a jamming mechanism using layers, granules, or chain structures, through vacuum pressure or cable-driven mechanism due to its simple and rapid actuation. However, such jamming mechanisms are not suitable for actual robotic applications that require large supporting forces or drastic changes in stiffness. In this article, a hybrid jamming structure that combines granules and a rigid chain structure is proposed to simultaneously increase the average stiffness change in all directions and the maximum force in a certain direction. The improved performance of the proposed structure was compared to that of conventional granular and chain jamming structures. Based on the analytical model of the proposed structure, the principles for designing the hybrid jamming structure were derived and experimentally verified. Finally, based on the hybrid jamming structures, a multilink hybrid jamming structure was developed as a wearable system to assist the upper limbs and a robotic arm structure.

Review of machine learning methods in soft robotics.

Soft robots have been extensively researched due to their flexible, deformable, and adaptive characteristics. However, compared to rigid robots, soft robots have issues in modeling, calibration, and control in that the innate characteristics of the soft materials can cause complex behaviors due to non-linearity and hysteresis. To overcome these limitations, recent studies have applied various approaches based on machine learning. This paper presents existing machine learning techniques in the soft robotic fields and categorizes the implementation of machine learning approaches in different soft robotic applications, which include soft sensors, soft actuators, and applications such as soft wearable robots. An analysis of the trends of different machine learning approaches with respect to different types of soft robot applications is presented; in addition to the current limitations in the research field, followed by a summary of the existing machine learning methods for soft robots.

Consistent and Reproducible Direct Ink Writing of Eutectic Gallium-Indium for High-Quality Soft Sensors.

Given the need for stretchable sensors, many studies have been conducted on eutectic gallium-indium, which has superior properties as a conductive ink. However, it has remained a challenge to manufacture sensors in a consistent and reproducible manner because conventional mold-based fabrication still depends highly on manual techniques. To overcome this limitation, the direct ink writing was used in this study, focusing on improving the stability of writing by exploring issues related to failure and ensuring the consistency of the microchannel by selecting appropriate process variables, including the syringe material. As a result, multiple sensors produced under the same manufacturing conditions had similar behaviors. This fabrication technique improved the accuracy of manufacturing a microchannel, and its behavior was predicted successfully by a simple mathematical model, which was confirmed by nondestructive inspections of the microchannel. In developing a one-piece glove-type sensor without an assembly process, the efficiency of the fabrication technique was also emphasized.

Quantitative evaluation of hand functions using a wearable hand exoskeleton system.

To investigate, improve, and observe the effect of rehabilitation therapy, many studies have been conducted on evaluating the motor function quantitatively by developing various types of robotic systems. Even though the robotic systems have been developed, functional evaluation of the hand has been rarely investigated, because it is difficult to install a number of actuators or sensors to the hand due to limited space around the fingers. Therefore, in this study, a hand exoskeleton was developed to satisfy the required specifications for evaluating the hand functions including spasticity of finger flexors, finger independence, and multi-digit synergy and algorithms to evaluate such functions were proposed. The hand exoskeleton was composed with the four 4-bar linkages, two motors, and three loadcells for each finger, and it was able to flex/extend the metacarpal (MCP) and proximal interphalangeal(PIP) joints independently while measuring the pulling force at each phalanx. Using the hand exoskeleton, the hand functions of the three healthy subject were evaluated and the experimental results were analyzed.