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.

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.

Various robotic grippers have been developed over the past several decades for robotic manipulators. Especially, the soft grippers based on the soft pneumatic actuator (SPA) have been studied actively, since it offers more pliable bending motion, inherent compliance, and a simple morphological structure. However, few studies have focused on simultaneously improving the fingertip force and actuation speed within the specified design parameters. In this study, we developed a hybrid gripper that incorporates both soft and rigid components to improve the fingertip force and actuation speed simultaneously based on three design principles: first, the degree of bending is proportional to the ratio of the rigid structure; second, a concave chamber design is preferred for large longitudinal strain; and third, a round shape between soft and rigid materials increases the fingertip force. The suggested principles were verified using the finite element methods. The improved performance of the hybrid gripper was verified experimentally and compared with the performance of a conventional SPAs. The ability of the hybrid gripper to grasp different objects was evaluated and was applied in a teleoperated system. Index Terms-Soft material robotics, grippers and other endeffectors, flexible robots. I. INTRODUCTION R ECENTLY, the limitations of rigid gripper due to the necessity of additional linkages, complicated controls, and so on, have been overcome by the soft gripper [1]. Especially, the soft grippers based on soft pneumatic actuators (SPAs), which offer better compliance, and a higher degree of freedom than the rigid robot, have been actively developed [2]-[9]. Due to the inherent compliance of soft materials, complicated controls and additional structures are not needed with soft grippers, as the proper selection of materials of various stiffness allows for simple control. Furthermore, soft grippers with SPAs are constructed from low-cost and readily-available elastomers.

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.