Breast cancer bone metastasis (BCBM) affects women’s health globally, calling for the development of effective diagnosis and prognosis solutions. While deep learning has exhibited impressive capacities across various healthcare domains, its applicability in BCBM diseases is consistently hindered by the lack of an open, large-scale, deep learning-ready dataset. As such, we introduce the Bone Metastasis (BoneMet) dataset, the first large-scale, publicly available, high-resolution medical resource, which is derived from a well-accepted murine BCBM model. The unique advantage of BoneMet over existing human datasets is repeated sequential scans per subject over the entire disease development phases. The dataset consists of over 67 terabytes of multi-modal medical data, including 2D X-ray images, 3D CT scans, and detailed biological data (e.g., medical records and bone quantitative analysis), collected from more than five hundreds mice spanning from 2019 to 2024. Our BoneMet dataset is well-organized into six components, i.e., Rotation X-Ray, Recon-CT, Seg-CT, Regist-CT, RoI-CT, and MiceMediRec. We further show that BoneMet can be readily adopted to build versatile, large-scale AI models for managing BCBM diseases in terms of diagnosis using 2D or 3D images, prognosis of bone deterioration, and sparse-angle 3D reconstruction for safe long-term disease monitoring. Our preliminary results demonstrate that BoneMet has the potentials to jump-start the development and fine-tuning of AI-driven solutions prior to their applications to human patients. To facilitate its easy access and wide dissemination, we have created the BoneMet package, providing three APIs that enable researchers to (i) flexibly process and download the BoneMet data filtered by specific time frames; and (ii) develop and train large-scale AI models for precise BCBM diagnosis and prognosis. The BoneMet dataset is officially available on Hugging Face Datasets at https://huggingface.co/datasets/BoneMet/BoneMet. The BoneMet package is available on the Python Package Index (PyPI) at https://pypi.org/project/BoneMet. Code and tutorials are available at https://github.com/Tiankuo528/BoneMet.

In this article, a novel approximation free control method was developed for multimotor driving systems with prescribed performance. The developed controller includes multimotor synchronization controller and the load tracking controller. First, the synchronous controller was designed by using the robust integral of the sign of the error to guarantee that all the motors states can converge their average value. Second, to achieve the load tracking control, an approximation free controller was developed based on the prescribed performance function. This method can avoid the function approximators and reduce the reduced computational burden and complexity. With the developed control strategy, the tracking error remains in a prescribed boundary, and the multimotor synchronous error achieves the asymptotic convergence. Finally, comparative experiments are conducted on a four-motor drive system to test the enhanced performance and robustness of the designed controller.

Robot systems, due to their unique flexibility and economy, are widely used in modern industry and intelligent manufacturing. The parameters of the system are unknown, and traditional parameter estimation methods are difficult to achieve fixed time convergence, which leads to extremely position tracking control problem. In addition, the transient and steady-state performance of the robot system is difficult to specify in advance. In this article, a novel composite learning fixed-time (FxT) control strategy is proposed for the robotic systems to deal with these issues. The funnel control (FC) is utilized to transform the original error system into a new error dynamics with transient performance constraints. The two-phase nonsingular FxT sliding mode surface is constructed to avoid the singularity problem. Then, the filter operation is introduced to obtain the expression of parameter estimation error and is used to design the composite learning law. To achieve parameter estimation, a FxT composite learning law based on online historical data and regression extension is proposed, where the interval excitation (IE) is considered in the adaptive law. Finally, the designed adaption is incorporated into the nonsingular FxT sliding mode control to achieve tracking control. Moreover, the comparison of three different controllers is made to demonstrate the benefits of the developed control strategy.

With the development of the Internet of Things (IoT) and 5G/6G technologies, there has been significant interest in the applications of the Internet of Vehicles (IoV) and multiaccess edge computing (MEC) in intelligent transportation systems. The significant increase in the number of vehicles currently accessing the Internet has highlighted the inability of some existing resource-constrained vehicles to adequately meet the demands of computationally intensive and latency-sensitive applications. There is a significant challenge in designing efficient task offloading strategies to enhance the utilization of computational resources and deliver high-quality services to vehicle users. In this article, we propose a four-tier computing architecture with local computing, vehicle-to-vehicle (V2V) computing, MEC computing, and mobile cloud computing (MCC), which can provide heterogeneous computing resources for multiple task vehicles and flexible offloading options of different types of vehicle tasks. We optimize the offloading decision and resource allocation with the objective function of minimizing the system cost. The nonconvex objective function and constraints both contain binary variables, which leads to NP-hard property. To solve this critical problem, we propose an alternating direction method of multipliers (ADMM)-based multivehicle task offloading scheme for IoV-MEC (AMTOS), to transform the nonconvex problem into a convex one by relaxing the binary variables, and provide an approximate optimal solution. Afterward, a binary variable recovery algorithm is used to recover the binary variables. Simulation results show that the algorithm can significantly reduce the system cost, compared with existing literature.

A micro unmanned aerial vehicle (UAV) only equipped with a monocular camera is hard to accomplish a flying task with obstacles avoidance and target tracking simultaneously. In this article, a bionic dynamic path planning algorithm was developed for cooperation of obstacles avoidance and target tracking. An improved bat algorithm (BA) optimized transfer learning convolutional neural network (CNN) and bio-inspired optical flow balance algorithm was combined for obstacles avoidance. The Hawk-eye algorithm with line of sight (LOS) tracking rules is aimed at UAV dynamic tracking with obstacles avoidance. All of perception information, including avoidance and tracking were fused in UAV motion decision phase. The experiments include “obstacles avoidance” and “obstacles avoidance + target tracking” parts. Comparing with manual control and other algorithms, the bionic dynamic path planning algorithm in this article showed certain advantages in success rate, less obstacles collisions, and less major accidents.

Most existing adaptive control designs for nonlinear pure-feedback systems have been derived based on backstepping or dynamic surface control (DSC) methods, requiring full system states to be measurable. The neural networks (NNs) or fuzzy logic systems (FLSs) used to accommodate uncertainties also impose demanding computational cost and sluggish convergence. To address these issues, this paper proposes a new output-feedback control for uncertain pure-feedback systems without using backstepping and function approximator. A coordinate transform is first used to represent the pure-feedback system in a canonical form to evade using the backstepping or DSC scheme. Then the Levant's differentiator is used to reconstruct the unknown states of the derived canonical system. Finally, a new unknown system dynamics estimator with only one tuning parameter is developed to compensate for the lumped unknown dynamics in the feedback control. This leads to an alternative, simple approximation-free control method for pure-feedback systems, where only the system output needs to be measured. The stability of the closed-loop control system, including the unknown dynamics estimator and the feedback control is proved. Comparative simulations and experiments based on a PMSM test-rig are carried out to test and validate the effectiveness of the proposed method.

Although adaptive control design with function approximators, for example, neural networks (NNs) and fuzzy logic systems, has been studied for various nonlinear systems, the classical adaptive laws derived based on the gradient descent algorithm with σ -modification or e -modification cannot guarantee the parameter estimation convergence. These nonconvergent learning methods may lead to sluggish response in the control system and make the parameter tuning complex. The aim of this paper is to propose a new learning strategy driven by the estimation error to design the alternative adaptive laws for adaptive control of nonlinear servo systems. The parameter estimation error is extracted and used as a new leakage term in the adaptive laws. By using this new learning method, the convergence of both the estimated parameters and the tracking error can be achieved simultaneously. The proposed learning algorithm is further tailored to retain finite-time convergence. To handle unknown nonlinearities in the servomechanisms, an augmented NN with a new friction model is used, where both the NN weights and some friction model coefficients are estimated online via the proposed algorithms. Comparisons with the σ -modification algorithm are addressed in terms of convergence property and robustness. Simulations and practical experiments are given to show the superior performance of the suggested adaptive algorithms.

This paper proposes an adaptive funnel control (FC) scheme for servo mechanisms with an unknown dead-zone. To improve the transient and steady-state performance, a modified funnel variable, which relaxes the limitation of the original FC (e.g., systems with relative degree 1 or 2), is developed using the tracking error to replace the scaling factor. Then, by applying the error transformation method, the original error is transformed into a new error variable which is used in the controller design. By using an improved funnel function in a dynamic surface control procedure, an adaptive funnel controller is proposed to guarantee that the output error remains within a predefined funnel boundary. A novel command filter technique is introduced by using the Levant differentiator to eliminate the "explosion of complexity" problem in the conventional backstepping procedure. Neural networks are used to approximate the unknown dead-zone and unknown nonlinear functions. Comparative experiments on a turntable servo mechanism confirm the effectiveness of the devised control method.

This article presents a new adaptive parameter estimation method and the corresponding control design for nonlinear servo mechanisms with friction compensation. A continuous friction model is employed to capture the friction dynamics of servo mechanisms. Then, the unknown system parameters including friction model parameters are online estimated via the derived adaptive law. Hence, a new adaptive law is proposed to achieve faster and more accurate parameter estimation over classical adaptive laws so as to suppress the undesired transient dynamics. For this purpose, an auxiliary filter is introduced to extract the estimation error for driving the parameter updating law. Moreover, an adaptive control is designed in conjunction with a robust integral of the sign of the error feedback term to address the bounded disturbances and enhance the tracking precision. Simulations and experiments are given to validate the efficiency of the developed control scheme.

Most function approximator (e.g., neural network or fuzzy system) based control designs can only prove uniform ultimate boundedness of the controlled system due to the unavoidable approximation errors. Moreover, the transient response of conventional adaptive control may be sluggish because high-gain learning is not preferable for guaranteeing system safety. To address these issues, this paper proposes and experimentally validates an alternative robust adaptive control for servo mechanisms with unknown dynamics and bounded disturbances. This control can guarantee asymptotic tracking error convergence in the steady-state, while the transient response can also be prescribed by using an improved prescribed performance function. An echo state network augmented by a smooth friction model is used to accommodate the unknown nonlinearities. The residual approximation error and other bounded disturbances are compensated by using a robust integral of sign of the error term. Comparative experiments based on a practical turntable servo mechanism are conducted to validate the effectiveness of the proposed control scheme and show improved control performance.

In this paper, an approximation-free funnel feedback controller is proposed for a class of nonlinear servomechanisms to achieve prescribed tracking error performance. An improved funnel function is proposed to guarantee the transient and asymptotic behavior of the tracking error within a given funnel boundary. The proposed funnel function removes the imposed assumption used in conventional funnel controls (e.g., systems with relative degree one or two) and avoids the potential singularity problem in prescribed performance controls. Moreover, an extended state observer (ESO) is used to address the effect of unknown dynamics in the control system (e.g., friction and disturbances), where the ESO parameters can be easily designed based on the control system bandwidth. The stability of the proposed control system with ESO and funnel function is analyzed via the Lyapunov theory. Comparative simulations and experimental results are conducted based on a practical turntable servomechanisms to validate the efficacy of the proposed method.