Milad Azizkhani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Milad Azizkhani has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Yue Chen
Georgia Institute of Technology/Emory University
9 shared publications - Anthony L. Gunderman
Mechanical Engineering Department, University of Arkansas, Fayetteville, AR, USA
4 shared publications - Deqiang Qiu
Department of Radiology and Imaging Sciences Emory University Atlanta Georgia USA
2 shared publications - Yifan Wang
Department of Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA, USA
2 shared publications - Ai-Ping Hu
Georgia Tech Research Institute Atlanta GA USA
1 shared publication Alex Qiu
Department of Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA, USA
1 shared publication
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (10) , 11291-11298
A Complementarity-Based Framework for Soft-Robot Contact Modeling and Planning
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (10) , 11291-11298
A Complementarity-Based Framework for Soft-Robot Contact Modeling and Planning
- 8 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (6) , 6408-6415
Dynamic Task Space Control of Redundant Pneumatically Actuated Soft Robot
Soft robotic manipulators promise manipulation dexterity and compliance, but these properties make them hard to control due to the uncertainties and nonlinearitiesin their dynamics. Towards solving these challenges, this letter proposes a real-time dynamic control approach for a pneumatically actuated redundant soft robotic arm. We first present a computationally-efficient dynamic model designed for real-time control. Next, we introduce a robust adaptive passivity-based control approach that complements the dynamic model to enhance the system's tracking performance under uncertainty. System uncertainties are categorized based on the bounds and behavior of dynamic terms in the model, with dominant stiffness and damping effects compensated by adaptive terms and unmodeled dynamics handled through the robust term. We first develop a control strategy in actuator space, then extend it to task space to encompass position control, orientation control, and simultaneous position and orientation control. To improve tracking performance in task space, we employ a redundancy resolution algorithm, addressing secondary tasks such as maintaining actuators within feasible limits and promoting homogeneous deformations in the robot. We comprehensively assess the performance of the proposed robust adaptive passivity control under various operation speeds, loading conditions, and trajectories. A comparison with recent baselines from the literature highlights how our method achieves both superior tracking performance and robot operation speed.
- 8 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (6) , 6408-6415
Dynamic Task Space Control of Redundant Pneumatically Actuated Soft Robot
Soft robotic manipulators promise manipulation dexterity and compliance, but these properties make them hard to control due to the uncertainties and nonlinearitiesin their dynamics. Towards solving these challenges, this letter proposes a real-time dynamic control approach for a pneumatically actuated redundant soft robotic arm. We first present a computationally-efficient dynamic model designed for real-time control. Next, we introduce a robust adaptive passivity-based control approach that complements the dynamic model to enhance the system's tracking performance under uncertainty. System uncertainties are categorized based on the bounds and behavior of dynamic terms in the model, with dominant stiffness and damping effects compensated by adaptive terms and unmodeled dynamics handled through the robust term. We first develop a control strategy in actuator space, then extend it to task space to encompass position control, orientation control, and simultaneous position and orientation control. To improve tracking performance in task space, we employ a redundancy resolution algorithm, addressing secondary tasks such as maintaining actuators within feasible limits and promoting homogeneous deformations in the robot. We comprehensively assess the performance of the proposed robust adaptive passivity control under various operation speeds, loading conditions, and trajectories. A comparison with recent baselines from the literature highlights how our method achieves both superior tracking performance and robot operation speed.
- 28 February 2025
- Published by ASME International in Journal of Mechanisms and Robotics
- Vol. 17 (7) , 1-23
Soft Robot Kinematic Control Via Manipulability-Aware Redundancy Resolution
This article addresses the kinematic control of a redundant soft robotic arm. Full pose kinematic control of soft robots is challenging because direct application of the classical controllers developed based on rigid robots to soft robots could lead to unreliable or infeasible motions. In this study, we explore the manipulability property of a soft robotic arm and develop an advanced resolved-rate controller that prioritizes position over orientation control and switches its modes and gains based on position and orientation manipulabilities, enabling stable motion even when the robot is close to the singular configurations. The simulation and experimental results indicate that our proposed method outperforms previous methods in terms of both accuracy and smoothness during operation.
- 28 February 2025
- Published by ASME International in Journal of Mechanisms and Robotics
- Vol. 17 (7) , 1-23
Soft Robot Kinematic Control Via Manipulability-Aware Redundancy Resolution
This article addresses the kinematic control of a redundant soft robotic arm. Full pose kinematic control of soft robots is challenging because direct application of the classical controllers developed based on rigid robots to soft robots could lead to unreliable or infeasible motions. In this study, we explore the manipulability property of a soft robotic arm and develop an advanced resolved-rate controller that prioritizes position over orientation control and switches its modes and gains based on position and orientation manipulabilities, enabling stable motion even when the robot is close to the singular configurations. The simulation and experimental results indicate that our proposed method outperforms previous methods in terms of both accuracy and smoothness during operation.
- 16 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (2) , 2064-2071
Kinetostatics and Retention Force Analysis of Soft Robot Grippers With External Tendon Routing
Soft robots (SR) are a class of continuum robots that enable safe human interaction with task versatility beyond rigid robots. This has resulted in their rapid adoption in a number of applications that require manipulation of delicate and irregular objects. Despite their advantages, SR grippers typically require case-specific experimental characterization for shape and gripper retention force estimation. This letter presents a kinetostatic modeling approach based on strain energy minimization subject to mechanics and geometric constraints for shape estimation of SR grippers with external tendon routing (ETR), including those with composite structures. Additionally, Castigliano's First Theorem is used to estimate the retention force of the gripper. These models are evaluated across four different ETR SR grippers. The mechanics model predicted the fingertip position and orientation with an accuracy of 1.06 $\pm$ 0.62 mm (1.79% $\pm$ 1.05% of length) and 3.58$^{\circ } \pm \text{2.82}^{\circ }$ with respect to tendon force and 0.72 $\pm$ 0.45 mm (1.22% $\pm$ 0.76% of length) and 2.86$^{\circ } \pm \text{2.11}^{\circ }$ with respect to tendon retraction. The retention force of the gripper was predicted with an average error of 0.20 $\pm$ 0.12 N.
- 16 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (2) , 2064-2071
Kinetostatics and Retention Force Analysis of Soft Robot Grippers With External Tendon Routing
Soft robots (SR) are a class of continuum robots that enable safe human interaction with task versatility beyond rigid robots. This has resulted in their rapid adoption in a number of applications that require manipulation of delicate and irregular objects. Despite their advantages, SR grippers typically require case-specific experimental characterization for shape and gripper retention force estimation. This letter presents a kinetostatic modeling approach based on strain energy minimization subject to mechanics and geometric constraints for shape estimation of SR grippers with external tendon routing (ETR), including those with composite structures. Additionally, Castigliano's First Theorem is used to estimate the retention force of the gripper. These models are evaluated across four different ETR SR grippers. The mechanics model predicted the fingertip position and orientation with an accuracy of 1.06 $\pm$ 0.62 mm (1.79% $\pm$ 1.05% of length) and 3.58$^{\circ } \pm \text{2.82}^{\circ }$ with respect to tendon force and 0.72 $\pm$ 0.45 mm (1.22% $\pm$ 0.76% of length) and 2.86$^{\circ } \pm \text{2.11}^{\circ }$ with respect to tendon retraction. The retention force of the gripper was predicted with an average error of 0.20 $\pm$ 0.12 N.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 29 (3) , 1714-1725
Modeling and Control of an MR-Safe Pneumatic Radial Inflow Motor and Encoder (PRIME)
Magnetic resonance (MR) conditional actuators and encoders are the key components for MR-guided robotic systems. In this article, we present the modeling and control of our MR-safe pneumatic radial inflow motor and encoder. A comprehensive model is developed that considers the primary dynamic elements of the system, including: 1) motor dynamics, 2) pneumatic transmission line dynamics, and 3) valve dynamics. After model validation, we present a simplified third order model that facilitates design of a first order sliding mode controller (TO-SMC). Finally, the motor hardware is tested in a 7T MRI. No image distortion or artifacts were observed. We posit the MR-safe motor and dynamic model will lower the entry barriers for researchers interested in MR-guided robots and promote wider adoption of MR-guided robotic systems.
- 13 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 29 (3) , 1714-1725
Modeling and Control of an MR-Safe Pneumatic Radial Inflow Motor and Encoder (PRIME)
Magnetic resonance (MR) conditional actuators and encoders are the key components for MR-guided robotic systems. In this article, we present the modeling and control of our MR-safe pneumatic radial inflow motor and encoder. A comprehensive model is developed that considers the primary dynamic elements of the system, including: 1) motor dynamics, 2) pneumatic transmission line dynamics, and 3) valve dynamics. After model validation, we present a simplified third order model that facilitates design of a first order sliding mode controller (TO-SMC). Finally, the motor hardware is tested in a 7T MRI. No image distortion or artifacts were observed. We posit the MR-safe motor and dynamic model will lower the entry barriers for researchers interested in MR-guided robots and promote wider adoption of MR-guided robotic systems.
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (11) , 7495-7502
Concentric Tube Robot Redundancy Resolution via Velocity/Compliance Manipulability Optimization
Concentric Tube Robots (CTR) have the potential to enable effective minimally invasive surgeries. While extensive modeling and control work have been proposed in the past decade, limited efforts have been made to improve the path tracking performance from the perspective of manipulability, which can be critical to generate safe motion and feasible actuator commands. In this letter, we propose a gradient-based redundancy resolution framework that optimizes velocity/compliance manipulability-based performance indices during path tracking for a kinematically redundant CTR. We efficiently calculate the gradients of manipulabilities by propagating the first- and second-order derivatives of state variables of the Cosserat rod model along the CTR arc length, reducing the gradient computation time by 68% compared to the finite difference method. Task-specific performance indices are optimized by projecting the gradient into the null-space of path tracking. Simulation results show that the proposed method is able to accomplish the required tasks while commonly used redundancy resolution approaches underperform or even fail.
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (11) , 7495-7502
Concentric Tube Robot Redundancy Resolution via Velocity/Compliance Manipulability Optimization
Concentric Tube Robots (CTR) have the potential to enable effective minimally invasive surgeries. While extensive modeling and control work have been proposed in the past decade, limited efforts have been made to improve the path tracking performance from the perspective of manipulability, which can be critical to generate safe motion and feasible actuator commands. In this letter, we propose a gradient-based redundancy resolution framework that optimizes velocity/compliance manipulability-based performance indices during path tracking for a kinematically redundant CTR. We efficiently calculate the gradients of manipulabilities by propagating the first- and second-order derivatives of state variables of the Cosserat rod model along the CTR arc length, reducing the gradient computation time by 68% compared to the finite difference method. Task-specific performance indices are optimized by projecting the gradient into the null-space of path tracking. Simulation results show that the proposed method is able to accomplish the required tasks while commonly used redundancy resolution approaches underperform or even fail.
- Open Access
Concentric Tube Robot Redundancy Resolution via Velocity/Compliance Manipulability Optimization
Concentric Tube Robots (CTR) have the potential to enable effective minimally invasive surgeries. While extensive modeling and control schemes have been proposed in the past decade, limited efforts have been made to improve the trajectory tracking performance from the perspective of manipulability , which can be critical to generate safe motion and feasible actuator commands. In this paper, we propose a gradient-based redundancy resolution framework that optimizes velocity/compliance manipulability-based performance indices during trajectory tracking for a kinematically redundant CTR. We efficiently calculate the gradients of manipulabilities by propagating the first- and second-order derivatives of state variables of the Cosserat rod model along the CTR arc length, reducing the gradient computation time by 68\% compared to finite difference method. Task-specific performance indices are optimized by projecting the gradient into the null-space of trajectory tracking. The proposed method is validated in three exemplary scenarios that involve trajectory tracking, obstacle avoidance, and external load compensation, respectively. Simulation results show that the proposed method is able to accomplish the required tasks while commonly used redundancy resolution approaches underperform or even fail.
Open AccessConcentric Tube Robot Redundancy Resolution via Velocity/Compliance Manipulability Optimization
Concentric Tube Robots (CTR) have the potential to enable effective minimally invasive surgeries. While extensive modeling and control schemes have been proposed in the past decade, limited efforts have been made to improve the trajectory tracking performance from the perspective of manipulability , which can be critical to generate safe motion and feasible actuator commands. In this paper, we propose a gradient-based redundancy resolution framework that optimizes velocity/compliance manipulability-based performance indices during trajectory tracking for a kinematically redundant CTR. We efficiently calculate the gradients of manipulabilities by propagating the first- and second-order derivatives of state variables of the Cosserat rod model along the CTR arc length, reducing the gradient computation time by 68\% compared to finite difference method. Task-specific performance indices are optimized by projecting the gradient into the null-space of trajectory tracking. The proposed method is validated in three exemplary scenarios that involve trajectory tracking, obstacle avoidance, and external load compensation, respectively. Simulation results show that the proposed method is able to accomplish the required tasks while commonly used redundancy resolution approaches underperform or even fail.
- Open Access
Design, Modeling, and Redundancy Resolution of Soft Robot for Effective Harvesting
Blackberry harvesting is a labor-intensive and costly process, consuming up to 50\% of the total annual crop hours. This paper presents a solution for robotic harvesting through the design, manufacturing, integration, and control of a pneumatically actuated, kinematically redundant soft arm with a tendon-driven soft robotic gripper. The hardware design is optimized for durability and modularity for practical use. The harvesting process is divided into four stages: initial placement, fine positioning, grasp, and move back to home position. For initial placement, we propose a real-time, continuous gain-scheduled redundancy resolution algorithm for simultaneous position and orientation control with joint-limit avoidance. The algorithm relies solely on visual feedback from an eye-to-hand camera and achieved a position and orientation tracking error of $0.64\pm{0.27}$ mm and $1.08\pm{1.5}^{\circ}$, respectively, in benchtop settings. Following accurate initial placement of the robotic arm, fine positioning is achieved using a combination of eye-in-hand and eye-to-hand visual feedback, reaching an accuracy of $0.75\pm{0.36}$ mm. The system's hardware, feedback framework, and control methods are thoroughly validated through benchtop and field tests, confirming feasibility for practical applications.Open AccessDesign, Modeling, and Redundancy Resolution of Soft Robot for Effective Harvesting
Blackberry harvesting is a labor-intensive and costly process, consuming up to 50\% of the total annual crop hours. This paper presents a solution for robotic harvesting through the design, manufacturing, integration, and control of a pneumatically actuated, kinematically redundant soft arm with a tendon-driven soft robotic gripper. The hardware design is optimized for durability and modularity for practical use. The harvesting process is divided into four stages: initial placement, fine positioning, grasp, and move back to home position. For initial placement, we propose a real-time, continuous gain-scheduled redundancy resolution algorithm for simultaneous position and orientation control with joint-limit avoidance. The algorithm relies solely on visual feedback from an eye-to-hand camera and achieved a position and orientation tracking error of $0.64\pm{0.27}$ mm and $1.08\pm{1.5}^{\circ}$, respectively, in benchtop settings. Following accurate initial placement of the robotic arm, fine positioning is achieved using a combination of eye-in-hand and eye-to-hand visual feedback, reaching an accuracy of $0.75\pm{0.36}$ mm. The system's hardware, feedback framework, and control methods are thoroughly validated through benchtop and field tests, confirming feasibility for practical applications. - 10 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (4) , 1897-1904
Dynamic Control of Soft Robotic Arm: An Experimental Study
The objective of this letter is to investigate the dynamic control of a soft robotic arm. First, a modular soft robotic hardware and an affordable actuator-space encoder were presented. We then discussed the soft robot modeling, and adaptive passivity control strategy with stability proof. The proposed controller was tested in different operation scenarios, and compared to the standard PD feedback linearization control and passivity control. In all experimental settings, the adaptive passivity control scheme was able to achieve superior performance, even with significant modeling uncertainties and disturbances. The theoretical analysis and experimental validations of the proposed controller will pave the way toward the practical implementations of the soft robotic system in the dynamic scenarios.
- 10 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (4) , 1897-1904
Dynamic Control of Soft Robotic Arm: An Experimental Study
The objective of this letter is to investigate the dynamic control of a soft robotic arm. First, a modular soft robotic hardware and an affordable actuator-space encoder were presented. We then discussed the soft robot modeling, and adaptive passivity control strategy with stability proof. The proposed controller was tested in different operation scenarios, and compared to the standard PD feedback linearization control and passivity control. In all experimental settings, the adaptive passivity control scheme was able to achieve superior performance, even with significant modeling uncertainties and disturbances. The theoretical analysis and experimental validations of the proposed controller will pave the way toward the practical implementations of the soft robotic system in the dynamic scenarios.