Cable-driven redundant manipulators feature a slender structure, large workspace, and flexible motion, making them suitable for operation in confined spaces. However, their positioning accuracy and load capacity are limited, thus restricting their overall performance. This article focuses on a novel linkage quaternion joint and proposes a variable stiffness optimization method to improve positional accuracy, enhance load capacity, and ensure safer interaction through null-space motion. First, a simplified analytical stiffness model is developed to reduce computational complexity and improve efficiency. Next, a null-space variable stiffness optimization method is introduced, with multidirectional composite flexibility as the evaluation metric. Iterative vectors are designed to enable bidirectional continuous control of the end-effector stiffness. Finally, experiments are conducted to validate the performance. The results demonstrate that the proposed variable stiffness optimization method significantly improves positioning accuracy, load capacity, and compliance, thereby broadening the applicability of cable-driven redundant manipulators.

Dynamic movement primitives (DMPs) have been widely applied in robot motion planning and control. However, in some special cases, original discrete DMP fails to generalize proper trajectories. Moreover, it is difficult to produce trajectories on the curved surface. To solve the above problems, a modified DMP method is proposed for robot control by adding the scaling factor and force coupling term. First, the adjusted cosine similarity is defined to assess the similarity of the generalized trajectory with respect to the demonstrated trajectory. By optimizing the similarity, the trajectories can be generated in all situations. Next, by adding the force coupling term derived from adaptive admittance control to the transformation system of the original DMP, the controller achieves the force control ability. Then, the modified DMP-based robot control system is developed. The stability and convergence of the system are proved. Finally, the high precisions of the proposed method are verified by simulations and experiments. The method is significant for trajectory learning and generalization on the curved surface.

Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing a multi-task medical image registration data set for comprehensive characterisation of deformable registration algorithms. A continuous evaluation will be possible at https://learn2reg.grand-challenge.org. Learn2Reg covers a wide range of anatomies (brain, abdomen, and thorax), modalities (ultrasound, CT, MR), availability of annotations, as well as intra- and inter-patient registration evaluation. We established an easily accessible framework for training and validation of 3D registration methods, which enabled the compilation of results of over 65 individual method submissions from more than 20 unique teams. We used a complementary set of metrics, including robustness, accuracy, plausibility, and runtime, enabling unique insight into the current state-of-the-art of medical image registration. This paper describes datasets, tasks, evaluation methods and results of the challenge, as well as results of further analysis of transferability to new datasets, the importance of label supervision, and resulting bias. While no single approach worked best across all tasks, many methodological aspects could be identified that push the performance of medical image registration to new state-of-the-art performance. Furthermore, we demystified the common belief that conventional registration methods have to be much slower than deep-learning-based methods.

Deformable registration is fundamental to longitudinal and population-based image analyses. However, it is challenging to precisely align longitudinal infant brain MR images of the same subject, as well as cross-sectional infant brain MR images of different subjects, due to fast brain development during infancy. In this paper, we propose a recurrently usable deep neural network for the registration of infant brain MR images. There are three main highlights of our proposed method. (i) We use brain tissue segmentation maps for registration, instead of intensity images, to tackle the issue of rapid contrast changes of brain tissues during the first year of life. (ii) A single registration network is trained in a one-shot manner, and then recurrently applied in inference for multiple times, such that the complex deformation field can be recovered incrementally. (iii) We also propose both the adaptive smoothing layer and the tissue-aware anti-folding constraint into the registration network to ensure the physiological plausibility of estimated deformations without degrading the registration accuracy. Experimental results, in comparison to the state-of-the-art registration methods, indicate that our proposed method achieves the highest registration accuracy while still preserving the smoothness of the deformation field. The implementation of our proposed registration network is available onlinehttps://github.com/Barnonewdm/ACTA-Reg-Net.

Over the past few decades, the nonlinear output regulation (NOR) theory has attracted extensive attentions in control society. However, few experimental results have been reported about the NOR theory. This article first presents experimental results on discrete-time NOR problem for a linear motor driven inverted pendulum (LMDIP) system. To solve this problem, it is essential to find the solution of the complicated discrete regulator equations (DREs). Moreover, the friction force commonly exists in mechanical systems and cannot be neglected for control systems requiring high precision tracking performance. We present a novel discrete-time controller by combining neural network (NN) approach and friction-feedforward compensation mechanism. Finally, we verify the proposed control algorithm by experiment and make some comparisons with the linear controller.

Much recently, an internal model approach from output regulation theory has been adopted to solve the speed tracking control problem of the permanent magnet synchronous motor (PMSM) system on simulation level. A striking advantage of this approach is that it can achieve multiple goals including trajectory tracking, disturbance rejection, and robustness simultaneously. This article further studies a position tracking control problem of the PMSM system under nonlinear load torque disturbance. A nonlinear internal model based output feedback controller is proposed, which can achieve exact position tracking and allow certain parameter uncertainties. Besides simulation results, a real-time experimental setup is built and experimental results are provided to illustrate the effectiveness of the proposed controller. It is worth mentioning that the proposed controller can lead to a high precision position tracking performance under nonlinear load torque disturbance.

In recent years, the tracking problem of spherical inverted pendulum (SIP) system with multi-input, multi-output nature and unstable zero dynamics has been well addressed based on continuous-time nonlinear output regulation (NOR) theory. For the convenience of digital implementation, this paper further investigates the approximate NOR problem of the SIP system in discrete-time framework. The key for solving the discrete-time NOR problem lies in how to solve a set of algebraic functional equations known as discrete regulator equations (DRE). Since the equations are very complicated, the accurate solution of the DRE can not be obtained. In this paper, we first show that the DRE associated with the SIP system are solvable by center manifold theorem and then use neural network approach to tackle with the tracking problem. Finally, we compare our method with polynomial approximation method.

This paper addresses the prognosis problem for hybrid systems with intermittent faults and uncertain parameters. First, a diagnostic hybrid bond graph in linear fractional form is used to model the uncertain hybrid system to generate the mode-dependent adaptive thresholds for fault detection purpose. Then, a global combinative fault signature matrix integrating independent and dependent augmented global analytical redundancy relations is proposed to improve the system fault isolability under the multiple-fault condition. After the possible fault set is isolated, an adaptive reinforcement unscented Kalman filter is introduced to identify the intermittent fault magnitude, where an auxiliary indicator is used to capture the fault appearing and disappearing time steps. To describe the degradation trend of the intermittent fault, a dynamic model with a mode-dependent degradation coefficient is used. Taking the variation of the degradation coefficient into account, an event-based sequential prognosis method is proposed, where the prognoser is only reactivated if the discrete event representing mode change is observed and its associated conditions are satisfied. Finally, the key concept of the proposed method is verified by experimental studies.