Integrated Locomotion and Deformation of a Magnetic Soft Robot: Modeling, Control, and Experiments

Soft robots have recently attracted increased attention because their characteristics of low‐cost fabrication, durability, and deformability make them uniquely suited for applications in bio‐integrated systems. Being fundamentally different from traditional rigid robots, soft robots exhibit properties of infinite degrees of freedom (DOF) and nonlinear materials properties that require innovations in control systems. With the rapid development of materials science, robotics, and artificial intelligence, the diversification of actuator mechanisms and algorithms has enabled a wide range of unique control strategies. This review summarizes the basics of actuator mechanisms and control strategies, including open‐loop control, closed‐loop control, and autonomous control, and discusses their implementation from diversified perspectives. Control strategies are evaluated based on their compatibility with materials sets, application goals, and implementation route. The emerging directions are forecasted from the perspectives of interfacing between controller and actuator, underactuated control strategies, and implementation of artificial intelligence (AI).

Section: Open-loop Controlmentioning

confidence: 99%

Control Strategies for Soft Robot Systems

Wang

Chortos

2022

“…[44][45][46][47][48] Driven by external power, the ultrasoft liquid bodies allow navigation through narrow and restricted regions much smaller than their original dimensions. [49][50][51] These small-scale machines have been applied for robotic and biomedical applications, such as targeted delivery, cargo transportation, and fluidic manipulation in microfluidics. [52][53][54][55][56] This review summarizes the recent research achievements on liquid-bodied miniature machines with a focus on their magnetic control methods and microrobotic applications (Figure 1).…”

Section: Introductionmentioning

confidence: 99%

“…[ 44–48 ] Driven by external power, the ultrasoft liquid bodies allow navigation through narrow and restricted regions much smaller than their original dimensions. [ 49–51 ] These small‐scale machines have been applied for robotic and biomedical applications, such as targeted delivery, cargo transportation, and fluidic manipulation in microfluidics. [ 52–56 ]…”

Section: Introductionmentioning

confidence: 99%

Reconfigurable Liquid‐Bodied Miniature Machines: Magnetic Control and Microrobotic Applications

Wang

Xiang

Lang

et al. 2023

Soft miniature machines demonstrate multimodal actuation and morphology change capabilities in narrow spaces smaller than their dimension. The wirelessly controlled soft‐bodied features make them promising candidates for microrobotic manipulation and targeted operation in a noninvasive manner. Liquid‐bodied machine offers an ultrasoft body with extreme deformability owing to its fluid nature, enabling adaptive navigation with smooth contact with objects and environmental restrictions. Over the last decade of development, significant research progress has been achieved in wirelessly controlling liquid‐bodied machines for diverse manipulation applications. Herein, an overview of the recent research results in magnetic control methods and diverse microrobotic applications of liquid‐bodied machines is provided. Considering the control mechanisms and application challenges, ferrofluid‐based, liquid metal‐based, and liquid marble‐based machines are mainly discussed with a brief discussion on droplet‐based machines. The connection between control methods and applications is highlighted with a detailed analysis of machine–object and machine–environment interactions. The current challenges and research opportunities on liquid‐bodied miniature machines are outlined, aiming at designing intelligent liquid‐bodied machine‐based microrobotic systems and promoting the development of small‐scale robotics.

“…[26][27][28] Deformation calculation based on mechanical models such as finite-element method (FEM) suffers from inherent limitations including long calculation time and requirements for parameter iteration to obtain the optimal control parameters. [29][30][31] Therefore, an inverse kinematics model for obtaining the actuation field parameters according to the specific path trajectory still remains a challenge. [27,28,32] In the past decades, machine learning-based methods have been widely used to achieve higher precision control with lower computational costs.…”

Section: Introductionmentioning

confidence: 99%

Data‐Driven Navigation of Ferromagnetic Soft Continuum Robots Based on Machine Learning

Sun

Zhang

et al. 2023

Ferromagnetic soft continuum robots (FSCRs) have great potential in biomedical applications due to their miniaturization and remote control capabilities. However, to direct the FSCR accurately and effectively, it is critical to realize inverse kinematics control in navigation, which is difficult for existing mechanical models. Herein, with the path segmentation strategy, an automatic method to navigate the FSCR in different paths based on machine learning is developed. A data‐driven artificial neural network (ANN) model to guide the steering of the magnetically responsive tip is presented. Using parametric simulations as the training data, the ANN model shows good generalization performance to predict control parameters. Moreover, the basic framework of the learning model remains effective when the FSCR materials change, which shows high scalability and is important for adapting to various environments. The study presents a promising strategy for guiding FSCRs in the narrow and tortuous vasculature, which is essential for many biomedical operations.