The area of soft robotics has been subject to intense research efforts in the past two decades and constitutes a paradigm for advanced machine design in future robotic applications. However, standard methods for industrial robotics may be difficult to apply when analyzing soft robots. Deep learning, which has undergone rapid and transformative advancements in recent years, offers a set of powerful tools for analyzing and designing complex soft machines capable of operating in unstructured environments and interacting with humans and objects in a delicate manner. This review summarizes the most important state‐of‐the‐art deep learning architectures classified under supervised, unsupervised, semisupervised, and reinforcement learning scenarios and discusses their main features and benefits for different soft robotic applications, including soft robot manipulators, soft grippers, soft sensors, and e‐skins, as well as bioinspired soft robots. Specific properties of recent deep learning architectures and the usefulness of their features in addressing various types of issues found in soft robotics are analyzed. The existing challenges and future prospects are identified and discussed in view of the enhanced integration of both areas, which improves the performance of next‐generation soft machines operating in real‐world conditions.
In this research paper, we present a comprehensive analysis of the current state of soft robots actuated with pneumatic artificial muscles and emphasise their distinct advantages over rigid robots, including exceptional flexibility, adaptability, and safety. Our study explores the design principles of soft robots, drawing inspiration from biological systems and human hands, and identifies promising avenues for further development. The emergence of hybrid robots is also recognised as a significant advancement, particularly in scenarios requiring high precision. The article explores mathematical models encompassing kinematics, dynamics, and statics, as well as alternative model-free approaches. These theoretical frameworks are instrumental in understanding and manipulating the behaviour of soft robots. However, despite substantial progress, soft robots’ practical application and simulation face limitations, primarily due to the demanding requirements and implementation challenges associated with their deployment. Consequently, this paper highlights the need for continued research and advancements to bridge the gap between the theoretical potential and practical utilisation of soft robots.
Industry 4.0 is affecting almost every area of the industry, and as a result of its effects, systems, technologies, and the way information is processed are being transformed. Its typical feature is transmission of information in the system environment provided by the Internet of Things. All information should be stored and shared through cloud computing. As a result, access to information should be unrestricted. This chapter is focused on Computational Intelligence (CI) in the context of Industry 4.0. Each subchapter provides fundamentals of some paradigms, followed by the use of CI in the concrete paradigm. The ending part of the chapter is focused on connecting theory and practice in a case study, which lists industrial parts recognition by convolutional neural networks for assisted assembly.
This article describes the dynamics of a manipulator with two degrees of freedom, while the dynamic model of the manipulator’s arm is derived using Lagrangian formalism, which considers the difference between the kinetic and potential energy of the system. The compiled dynamic model was implemented in Matlab, taking into account the physical parameters of the manipulator and friction term. Physical parameters were exported from the 3D CAD model. A scheme (model) was compiled in the Simulink, which was used for the subsequent validation process. The outputs of the validations were compared with measured data of joint angles from the system (expected condition) obtained by using gravity tests. For obtaining better results were parameters of the model optimizing by using the Trust Region Algorithm for Nonlinear Least Squares optimization method. Therefore, the aim of the research described in the article is the comparison of the model with the parameters that come from CAD and its improvement by estimating the parameters based on gravitational measurements. The model with estimated parameters achieved an improvement in the results of the Normal Root Mean Square Error compared to the model with CAD parameters. For link 1 was an improvement from 28.49% to 67.93% depending on the initial joint angle, and for link 2, from 63.84% to 66.46%.
This paper uses computational intelligence and machine learning methods to describe experimental modeling performed to approximate the static characteristics of one type of fluidic muscle from the manufacturer FESTO for three different muscle sizes. For the experiments, measured data from the manufacturer and data from a real system (i.e., test device) were used. The measurements, which took place on the experimental equipment, were carried out in two stages (i.e., when the muscle was pressed and when the muscle was relaxed). The resulting measured characteristics were obtained by averaging two values at a given moment. MATLAB® software was used for simulations, in which four models were created: MLP, SVM, ANFIS, and a custom model (i.e., polynomial model). Given that most articles mainly interpret their results graphically when approximating characteristics, in this article, the outputs of the models are also compared with the measured data based on the SSE, NRMSE, SBC, and AIC performance indicators, enabling a more relevant and comprehensive overview of the performance of the individual models. The outputs of the best models described in this article reach an accuracy of 89.90% to 98.74% (all from the MLP group), depending on the muscle size, compared to real measured outputs.
The paper describes the validation of a dynamic model of a planar robotic arm using gravity tests. The drive of the arm (fluid muscles from the manufacturer Festo) was not activated during gravity tests (for the test was used only gravitation of solid). The measured data were obtained under the c...