Adilet Toleshev
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Adilet Toleshev has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Sharafatdin Yessirkepov
Department of Robotics, School of Engineering and Digital Sciences, Nazarbayev University, Astana, Kazakhstan
4 shared publications - Yerbolat Igembay
Department of Robotics and Technical Means of Automation, Satbayev University, Almaty 050013, Kazakhstan
4 shared publications - Aiman Ozhikenova
Satbayev University
3 shared publications - Ali Kaiyrdykozha2 shared publications
- Assylbek Ozhiken
RSE “Institute of Mechanics and Engineering named after Academician U.A. Dzholdasbekova”, Kazakhstan
2 shared publications Aibek Niyetkaliyev
1 shared publication
Latest Publications
- Open Access
A geometry-guided sizing and static force modeling protocol for compact antagonistic cable-driven joints
- Open Access
- 30 August 2026
- Published by National Scientific Center of Traumatology and Orthopaedics named after Academician N.D. Batpenov in Traumatology and Orthopаedics of Kazakhstan
- p. jto063
Real-Time Inverse Kinematics for a Two-Degree-of-Freedom Upper-Limb Rehabilitation Exoskeleton
Traditional numerical methods for solving inverse kinematics in rehabilitation exoskeletons often suffer from high computational latency and struggle with dynamic torque optimization during high-frequency real-time control loops. Objective: Evaluation and testing a two-stage physics-informed feedforward neural network framework for solving the inverse kinematics of a 2-DOF upper-limb exoskeleton while simultaneously minimizing static gravitational joint torques. Methods. An off-line multi-start optimization routine was used to generate a workspace dataset of 99,208 optimal configurations; a feedforward architecture with 135,814 parameters incorporating a custom differentiable physical gravity layer was then trained to predict joint angles and correct residual loads. Results. Across a test set of 14,882 points, the model achieved a mean spatial positioning error of 0.385 cm (3.85 mm) with an approximate inference latency of 2.0 ms per sample, supporting closed-loop control frequencies up to 500 Hz without relying on resource-intensive online quadratic programming. Conclusions. The proposed physics-informed learning approach effectively combines high spatial accuracy, energy-efficient torque distribution, and deterministic execution speed, providing a lightweight, low-latency control solution for wearable upper-limb rehabilitation robotics.
- 30 August 2026
- Published by National Scientific Center of Traumatology and Orthopaedics named after Academician N.D. Batpenov in Traumatology and Orthopаedics of Kazakhstan
- p. jto063
Open AccessReal-Time Inverse Kinematics for a Two-Degree-of-Freedom Upper-Limb Rehabilitation Exoskeleton
Traditional numerical methods for solving inverse kinematics in rehabilitation exoskeletons often suffer from high computational latency and struggle with dynamic torque optimization during high-frequency real-time control loops. Objective: Evaluation and testing a two-stage physics-informed feedforward neural network framework for solving the inverse kinematics of a 2-DOF upper-limb exoskeleton while simultaneously minimizing static gravitational joint torques. Methods. An off-line multi-start optimization routine was used to generate a workspace dataset of 99,208 optimal configurations; a feedforward architecture with 135,814 parameters incorporating a custom differentiable physical gravity layer was then trained to predict joint angles and correct residual loads. Results. Across a test set of 14,882 points, the model achieved a mean spatial positioning error of 0.385 cm (3.85 mm) with an approximate inference latency of 2.0 ms per sample, supporting closed-loop control frequencies up to 500 Hz without relying on resource-intensive online quadratic programming. Conclusions. The proposed physics-informed learning approach effectively combines high spatial accuracy, energy-efficient torque distribution, and deterministic execution speed, providing a lightweight, low-latency control solution for wearable upper-limb rehabilitation robotics.
- Open Access
- 15 July 2026
- Published by Elsevier in SSRN Electronic Journal
A Geometry-Guided Sizing and Static Force Modeling Protocol for Compact Antagonistic Cable-Driven Joints
This article outlines a customizable geometric optimization, force modeling, and experimental evaluation of a compact, 3D-printed antagonistic cable-driven robotic elbow joint intended for upper-limb medical rehabilitation. Cable-driven parallel manipulators (CDPRs) offer significant advantages for wearables by minimizing distal mass and inertia, though they require meticulous tension and workspace management to ensure cables remain taut without structural or cable-link collisions. The proposed single-degree-of-freedom joint uses a biologically inspired dual-cable architecture alongside a unique Bowden cable sheath routing mechanism to mitigate cable interference and expand the operational workspace. Analytical models for inverse kinematics and static equilibrium were formulated to define optimal geometric parameters, establishing that a base-to-platform distance of h = 240 mm with a platform diameter D = 80 mm balances a 135° flexion range of motion with efficient actuator demands. Implementing a hardware-in-the-loop control loop via MATLAB/Simulink, the architecture combines position and force-bounded strategy. Experimental validations on the physical prototype demonstrate excellent agreement between theoretical predictions and empirical measurements for both cable displacements and tension control.
- 15 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Geometry-Guided Sizing and Static Force Modeling Protocol for Compact Antagonistic Cable-Driven Joints
This article outlines a customizable geometric optimization, force modeling, and experimental evaluation of a compact, 3D-printed antagonistic cable-driven robotic elbow joint intended for upper-limb medical rehabilitation. Cable-driven parallel manipulators (CDPRs) offer significant advantages for wearables by minimizing distal mass and inertia, though they require meticulous tension and workspace management to ensure cables remain taut without structural or cable-link collisions. The proposed single-degree-of-freedom joint uses a biologically inspired dual-cable architecture alongside a unique Bowden cable sheath routing mechanism to mitigate cable interference and expand the operational workspace. Analytical models for inverse kinematics and static equilibrium were formulated to define optimal geometric parameters, establishing that a base-to-platform distance of h = 240 mm with a platform diameter D = 80 mm balances a 135° flexion range of motion with efficient actuator demands. Implementing a hardware-in-the-loop control loop via MATLAB/Simulink, the architecture combines position and force-bounded strategy. Experimental validations on the physical prototype demonstrate excellent agreement between theoretical predictions and empirical measurements for both cable displacements and tension control.
- Open Access
- 28 February 2026
- Published by National Scientific Center of Traumatology and Orthopaedics named after Academician N.D. Batpenov in Traumatology and Orthopаedics of Kazakhstan
- Vol. 77 (1) , jto037
Kinematic Performance Assessment of a Cable-Driven Elbow–Wrist Exoskeleton for Upper Limb Rehabilitation
The aim: To evaluate the kinematic performance of a cable-driven elbow-wrist exoskeleton intended for upper limb rehabilitation in orthopaedic and post-traumatic conditions. Methods. A four-degree-of-freedom cable-driven exoskeleton was designed to assist elbow flexion-extension and multi-axis wrist motion. To reduce distal inertia and minimize joint misalignment commonly associated with rigid transmission systems, a cable-based actuation architecture was implemented. The elbow mechanism was configured as a single-degree-of-freedom joint powered by two antagonistic motors enabling bidirectional torque generation and modulation of joint stiffness through co-contraction principles. The wrist module provided three rotational degrees of freedom actuated by four tendons, where three cables-controlled roll and pitch motions and a diagonally oriented cable enabled yaw rotation. Kinematic modeling was performed using homogeneous transformation matrices to establish forward and inverse kinematic relationships from the proximal fixation point to the distal platform. Numerical simulations were conducted in MATLAB, followed by experimental validation on a scaled prototype. Cable displacement responses were compared with theoretical inverse kinematic predictions throughout the operational workspace. Results. The developed system demonstrated consistent agreement between theoretical modeling and experimental measurements. The elbow module achieved controlled flexion and extension within a range from minus sixty to sixty degrees, with stable bidirectional motion and predictable cable displacement patterns. The wrist mechanism preserved smooth multi-axis rotation and maintained mechanical transparency across roll, pitch, and yaw movements without evidence of kinematic singularities within the tested workspace. Experimental results confirmed accurate mapping between joint angles and cable actuation lengths, supporting the validity of the proposed kinematic model. Conclusion. The proposed cable-driven elbow–wrist exoskeleton demonstrates reliable kinematic performance and reduced mechanical inertia compared to rigid transmission systems. The validated modeling framework establishes a foundation for the future implementation of hybrid position and torque control strategies in orthopaedic upper limb rehabilitation technologies.
- 28 February 2026
- Published by National Scientific Center of Traumatology and Orthopaedics named after Academician N.D. Batpenov in Traumatology and Orthopаedics of Kazakhstan
- Vol. 77 (1) , jto037
Open AccessKinematic Performance Assessment of a Cable-Driven Elbow–Wrist Exoskeleton for Upper Limb Rehabilitation
The aim: To evaluate the kinematic performance of a cable-driven elbow-wrist exoskeleton intended for upper limb rehabilitation in orthopaedic and post-traumatic conditions. Methods. A four-degree-of-freedom cable-driven exoskeleton was designed to assist elbow flexion-extension and multi-axis wrist motion. To reduce distal inertia and minimize joint misalignment commonly associated with rigid transmission systems, a cable-based actuation architecture was implemented. The elbow mechanism was configured as a single-degree-of-freedom joint powered by two antagonistic motors enabling bidirectional torque generation and modulation of joint stiffness through co-contraction principles. The wrist module provided three rotational degrees of freedom actuated by four tendons, where three cables-controlled roll and pitch motions and a diagonally oriented cable enabled yaw rotation. Kinematic modeling was performed using homogeneous transformation matrices to establish forward and inverse kinematic relationships from the proximal fixation point to the distal platform. Numerical simulations were conducted in MATLAB, followed by experimental validation on a scaled prototype. Cable displacement responses were compared with theoretical inverse kinematic predictions throughout the operational workspace. Results. The developed system demonstrated consistent agreement between theoretical modeling and experimental measurements. The elbow module achieved controlled flexion and extension within a range from minus sixty to sixty degrees, with stable bidirectional motion and predictable cable displacement patterns. The wrist mechanism preserved smooth multi-axis rotation and maintained mechanical transparency across roll, pitch, and yaw movements without evidence of kinematic singularities within the tested workspace. Experimental results confirmed accurate mapping between joint angles and cable actuation lengths, supporting the validity of the proposed kinematic model. Conclusion. The proposed cable-driven elbow–wrist exoskeleton demonstrates reliable kinematic performance and reduced mechanical inertia compared to rigid transmission systems. The validated modeling framework establishes a foundation for the future implementation of hybrid position and torque control strategies in orthopaedic upper limb rehabilitation technologies.