Flexible joints are the integral drive and control components for manipulators in interaction applications. Ensuring optimal performance while implementing torque control is crucial to maintaining stability during interactions. However, the system is susceptible to numerous disturbances, such as motor inaccuracies, nonlinearity caused by friction, and hysteresis. These disturbances are distributed across the motor-side, reduction gear, and load-side, leading to limitations in system performance, including response speed and steady-state accuracy. This paper proposes a disturbance compensation method combined with dual torque sensors and an improved disturbance observer (DOB). Two torque sensors are installed on the fixed side and load-side, respectively. These sensors are utilized to measure the load-side disturbances without considering accuracy models. Furthermore, an improved DOB is designed based on one of the torque sensors to estimate the motor-side disturbances. The disturbance compensator and feedback controller are introduced as the control algorithms for the flexible joint to achieve high-precision torque control. The robust stability of the proposed method is analyzed. Finally, several comparative experiments are conducted under various conditions. The results demonstrate that the proposed method enhances torque control performances and backdrivability compared with the traditional methods. Note to Practitioners—Generally, lots of nonlinear disturbances in the flexible joint system are distributed across low-speed/high-torque and high-speed/low-torque ports. These disturbances will lead to limitations in torque control performance. To address the problem above, this paper focuses on integrating dual torque sensors with an improved DOB. Specifically, two torque sensors are installed on the fixed side of the reduction gear and load-side, respectively. This enables the real-time measurement and calculation of load-side disturbances. On the other hand, considering the torque sensor mounted at the fixed side and motor-side model, an improved DOB is designed to estimate the motor-side disturbances. Subsequently, the closed-loop control architecture is designed based on the torque sensor attached to the load. The complex modeling process can be reduced by installing and applying torque sensors. The model and parameter errors are not considered, and the torque control performance is improved. The research outcome of this paper provides an effective approach that can be used to achieve stable and rapid torque tracking, as well as effortless human-robot interaction. The proposed method still has good torque tracking performance in the case of a large load.

For conventional linear-in-parameter (LIP) dynamic model of industrial robots, redundant terms in multivariate polynomials (MVPs) are strongly coupled and more difficult to eliminate than the redundant parameters. In this work, by analyzing the mapping from linearized chain kinematics to Lagrange dynamics, the linear-in-multivariate-polynomial (LI-MVP) model is formed. Subsequently, a bilinearized dynamics is derived in both LI-MVP and LIP formulations, so that redundant MVPs and inertial parameters are concurrently eliminated. In addition, all the MVPs are encoded into a numeric matrix within a monoid, where a binary operation is defined to replace symbolic Kronecker products for efficient derivation of LI-MVP model. Eventually, by rearranging the encoded matrix with respect to total degrees of variate, the symbolic LIP model is directly restored with decoded MVPs in Horner forms, which can further reduce the number of multiplications during torque computation. Simulations and experiments on serial industrial robots in both model derivation and torque calculation demonstrate the effectiveness of proposed methods.

High-quality and diverse datasets are crucial for supervised learning in industrial defect detection, yet collecting such data remains challenging. Synthetic data generation offers a promising solution for data augmentation, but traditional methods struggle with controlling key semantic features, leading to domain gaps that impair downstream performance. To address these challenges, we introduce DD-Aug, a novel data augmentation pipeline that integrates Cinema 4-D (C4D) and stable diffusion (SD) to generate photorealistic synthetic images. C4D is used to model key semantic features, such as contours, textures, and lighting conditions, while SD performs style transfer to increase the realism of generated images and reduce the domain gap. DD-Aug translates human visual knowledge into synthetic images, offering precise control over semantic features while adhering to physical rules and reducing the need for complex prompt engineering. This approach enhances generalization, making it particularly suitable for challenging industrial imaging conditions. By balancing semantic consistency and data diversity, DD-Aug significantly improves the quality of synthetic data. Our evaluations on the deformable defect bearing dataset (NBBD) demonstrate that DD-Aug surpasses other generative augmentation methods, yielding a 2.5%–10% improvement in detection accuracy across multiple advanced object detectors compared to models without augmentation. These results demonstrate DD-Aug's potential to significantly advance industrial defect detection through improved synthetic data quality and performance.

It remains a challenge to improve the accuracy of impedance rendering while ensuring stability under strong impacts during human-robot interaction. In this work, we aim to render the desired impedance for the flexible joint under an admittance control scheme with prescribed performance function (PPF). Specially, Gaussian kernels are introduced as the slack terms for PPF, so that the control stability can be maintained in the presence of abrupt external torques. Meanwhile, a narrower error envelope is yielded when such torques are absent, which also improves the fidelity of the desired impedance model. To achieve the prescribed tracking performance of the inner position loop, a two-stage backstepping control is proposed by defining two first-order composite error surfaces bridged by a second-order dynamic surface. This promulgates the minimum number of backstepping stages under the available state feedback, thus avoiding “explosion of terms.” In addition, dual-adaptive neural networks are incorporated into the backstepping control to compensate for the matched and unmatched disturbances. Real-time experiments are conducted to validate the appeal of the proposed method.

This paper proposes an improved stability observer to obtain the interaction state in real-time for physical human-robot-environment interaction (pHREI). Firstly, a stability observer is designed to effectively avoid the misjudgment caused by the phase advance or delay of the filter. Then, the variable admittance control algorithm is designed according to the value of the observer. Finally, a comparative experiment is carried out. The results show that the proposed method can effectively reduce the oscillation when the operator drags the robot into contact with the environment.

Removing the parameter redundancy in the kinematic error model does improve the robustness of parameter identification. However, this does not help much on saving the calculation time on the error compensation process, which is closely related to the data structure used for representing rigid-body motion. Compared with the homogenous transformation matrix (HTM), the unit dual quaternion (UDQ) can describe the rigid-body motion in term of an array with eight entries, thus it is a conducive data structure for efficient kinematic computation. In this article, the exponential and logarithm mappings of an UDQ are defined explicitly so that the relationship between finite and instantaneous motions is set up under the exponential coordinate. Thereafter, by defining the adjoint operator of UDQ to transform the twist under different frames, the linearized kinematic error models are built with the local product-of-exponentials (POE) formula. This facilitates the upcoming parameter identification and error compensation processes. Especially, the counts of elementary operations are evaluated throughout the compensation processes, which shows the number of arithmetic operations are greatly reduced compared with using the POE formula based on the HTM. Additionally, the simple data structure in term of 1-D arrays saves the data dispatch time when performing adjoint operations. These make the developed model suitable for calibration of the articulated robot with a long sequence of trajectories. Experiments on a 6-degree-of-freedom industrial robot validate the effectiveness of the proposed approach.

The ten papers in this special section aim gather the latest research and development works on design, sensing, and intelligent control of robotics and mechatronics systems resulting from the emerging information sharing and design technologies.

A new four degrees-of-freedom (DOF) parallel manipulator that can produce 3-DOF translations and 1-DOF rotation (3T1R), has been proposed in this paper. It has two identical limbs connected to the moving platform through passive revolute joints, and each limb has two identical branches driven by a pair of base mounted collinear prismatic joints. Due to such a unique “4-2-1” kinematic structure, the 4-DOF parallel manipulator has the advantages of simple kinematics, large workspace, high speed, and high positioning accuracy. These advantages make it an appropriate candidate for high-speed and high-precision pick-and-place operations. To validate the proposed parallel manipulator design, mobility analysis is conducted based on the screw theory. Other critical design analysis issues, such as displacement, singularity, and workspace analyses, have been addressed in details.