K.N. Toosi University of TechnologyInternational Journal of Robotics, Theory and Applications2008-714411120250101Kinematics Control of Continuum Robots Based on Screw Theory110212357ENSaeedehShekariCenter of Excellence in Robotics and Control, Advanced Robotics and Automated Systems (ARAS) Lab., Dept of Mechanical Engineering K. N. Toosi University of Technology Tehran, IranArmanGholibeikianCenter of Excellence in Robotics and Control, Advanced Robotics and Automated Systems (ARAS) Lab., Dept of Mechanical Engineering K. N. Toosi University of TechnologyS. Ali AMoosavianCenter of Excellence in Robotics and Control, Advanced Robotics and Automated Systems (ARAS) Lab., Dept of Mechanical Engineering K. N. Toosi University of TechnologyJournal Article20240731Controlling continuum robotic arms presents significant challenges due to their highly nonlinear nature and inherently uncertain and complex structure. This complexity affects the application of continuum arms in various areas such as routing, maneuvering on complex paths, and other applications. This paper addresses a real-time kinematic control of continuum robotic arms using screw theory to develop a controller that offers accuracy, speed, and low computational load for real-time implementation. The inherent flexibility and nonlinear nature of these arms complicate precise position control. To overcome these challenges, we use a PID controller, enhancing the robot's position control capabilities. Experimentally validated results for the designed path demonstrate the controller's effectiveness in improving path tracking and real-time control performance. This controller was implemented on the actual RoboArm system, achieving a 6cm error.https://ijr.kntu.ac.ir/article_212357_09f496405ba20aa90b16a1b5a7c000d4.pdfK.N. Toosi University of TechnologyInternational Journal of Robotics, Theory and Applications2008-714411120250101Evaluation of an Adaptive Neuro-controller for Robotic Hand Prosthesis (PARS)1120226725ENMohammadGohariRoom No.323, Residenza Flavio Pozzuoli,
via Rosini 12, ItalyMonaTahmasebiMarkazi Agricultural and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization (AREEO),YazdanAbbasiArak University of TechnologyJournal Article20250306This paper assesses the performance of a lightweight, compact, portable, and wearable cable-driven robotic hand prosthesis called PARS (Prosthesis Adaptive Robotic System). Initially, a mathematical model was developed, followed by the design and fabrication of a Neuro controller. The functionality of the robotic hand was confirmed through both simulations and experimental tests. The pilot study demonstrated that the proposed Neuro controller effectively tracks various desired joint trajectories and performs well in real-world applications. Experimental results indicated a strong correlation between the robotic hand prosthesis (RHP) and the human hand in terms of vertical position, speed, and acceleration during flexion and extension. The Neuro controller surpassed traditional PID in stability and accuracy. This study underscores the practical potential of developing advanced tools for assisting disabled individuals. However, further improvements are needed to enhance practicality, such as integrating force sensors and making the hardware more compact. Additionally, improving the control software to support simultaneous position and active force control could boost system performance in more complex tasks.https://ijr.kntu.ac.ir/article_226725_034586a47826d5586060e9e2daf5dda2.pdfK.N. Toosi University of TechnologyInternational Journal of Robotics, Theory and Applications2008-714411120250101Optimal Machine Learning based Multiple Impedance Control of a Space Free-Flying Robot2132233034ENAmirhosseinSafdariDepartment of Mechatronics Engineering, School of Intelligent Systems Engineering, College of Interdisciplinary Science and Technology, University of Tehran, Tehran, Iran0009-0007-4689-6518PayamZarafshanSchool of Engineering, Design and Built Environment, Western Sydney University, Sydney, Australia0000-0003-2462-8217KhalilAlipourDepartment of Mechatronics Engineering, School of Intelligent Systems Engineering, College of Interdisciplinary Science and Technology, University of Tehran, Tehran, Iran0000-0003-4456-1179BahramTarvirdizadehDepartment of Mechatronics Engineering, School of Intelligent Systems Engineering, College of Interdisciplinary Science and Technology, University of Tehran, Tehran, Iran0000-0001-9851-3805GuFangSchool of Engineering, Design and Built Environment, Western Sydney University, Sydney, Australia0000-0003-3723-1665Journal Article20250815Multiple Impedance Control (MIC) in Space Free-Flying Robot (SFFR) is necessary to ensure simultaneous accurate tracking and safe interactions; however, the computation related to grasp in these interactions has become a computational bottleneck, which intensifies with increasing Degrees of Freedom (DoF) and makes on-line control and real-time implementation difficult. Although Machine Learning-based Multiple Impedance Control (ML-MIC) has partly reduced this computational burden, the design of the Machine Learning (ML) network still relies on trial-and-error and does not guarantee optimal reduction of computations. In this paper, an Optimal Machine Learning-based Multiple Impedance Control (OML-MIC) is presented, in which the explicit computation related to the grasp matrix is replaced with a nonlinear approximation based on a Radial Basis Function Neural Network (RBFNN), and the network architecture is optimized using a Genetic Algorithm (GA) to minimize computational cost under accuracy constraints. The proposed method systematically determines the optimal network structure and, while preserving the physical dynamics of the grasp, eliminates the need for heavy linear-algebra operations.<br><br>Simulation results for planar manipulation of an object by a dual-arm SFFR show that, while meeting the MIC control specifications, OML-MIC reduces the number of multiplication operators by 73.15%, the number of addition operators by 41.27%, and the hidden-layer computations of ML-MIC by 50%. As a result of the structured optimal design, error analysis with statistical quantitative metrics confirms that accuracy remains within the safe-interaction range. These results indicate that integrating architecture optimization with learning-based control provides a reliable path to precise, real-time interaction on robotic platforms with limited resources.https://ijr.kntu.ac.ir/article_233034_576f0e92201559a7efeeb91a80d6d818.pdfK.N. Toosi University of TechnologyInternational Journal of Robotics, Theory and Applications2008-714411120250501The Complete Design of Lower Limb Extremity Exoskeleton Robot with Capability of Extending a Control Approach to Semi-Active Mode by Hardware in the Loop Method3342233836ENMortezaAhmadi KermanshahiIntelligent Mechanical Systems Research Laboratory, Pardis Branch, Islamic Azad University, Tehran, IranFarzadCheraghpour SamavatiDepartment of Mechanical Engineering, Pardis Campus, Islamic Azad University, Tehran, Iran0000-0003-4526-1282AliGhaffariK. N. Toosi University of TechnologyJournal Article20250602In this paper, a lower limb extremity exoskeleton robot is presented to support people with disabilities in the walking process and rehabilitation. The first section presents the conceptual design of the robot model, which indicates that the robot has seven degrees of freedom. Then the dynamic model of the mechanical system of the exoskeleton has been shown. In order to dynamic simulation, the mechanical model is transferred from the CATIA to MATLAB and simulated in SimMechanics, by applying the system parameters and implementing a complete process of gait cycle. In the following, a combinative controller is designed based on the described system. Finally, the gained results planted on the prototype of the presented system and the given parameters are tested in a loop by placing the control system hardware in a real-time situation. And the results of this approach demonstrated a good response from the control hardware output of the learning system for the semi-active mode in the exoskeleton.https://ijr.kntu.ac.ir/article_233836_e13957c56dc214ca73723c58e9ea79ef.pdf