No abstract

No abstract

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.

Virtual reality (VR) has been widely used for training, gaming, and entertainment, and the value of VR is continually increasing as a contact‐free technology. For an immersive VR experience, measuring finger movements and providing appropriate feedback to the hand are as important as visual information, given the necessity of the hands for activities in daily life. Thus, a hand‐worn VR device with motion sensors and haptic feedback is desirable. In this paper, a multimodal sensing and feedback glove is developed with soft, stretchable, lightweight, and compact sensor and heater sheets manufactured by direct ink writing (DIW) of liquid metal, eutectic gallium‐indium (eGaIn). In the sensor sheet, ten sensors and three vibrators are embedded to measure finger movements and provide vibro‐haptic feedback. The other heater sheet provides thermo‐haptic sensation in accurate and rapid manner via model‐based feedback control even under stretched conditions. The multimodal sensing and feedback glove allows users to feel the contact status and discriminate materials with different temperature. Performance of the proposed multimodal glove is verified under VR environments including touching and pushing two blocks of different materials and grabbing a heated metal ball submerged in hot water.