Effective policy optimization in multiagent reinforcement learning (MARL) necessitates extensive exploration of high-dimensional state-action spaces. However, such exploration may not only trigger unsafe states but also compromise system stability, posing significant challenges for deployment in safety-critical systems. To address this challenge, this article proposes a safety-stability layer that integrates robust control barrier functions (RCBFs) and input-to-state stable control Lyapunov functions (ISS-CLFs) for multiagent systems operating in unknown environments with uncertain dynamics. Furthermore, by integrating safety-stability constraints with a MARL framework, during the training phase, we exclusively focus on goal-reaching objectives to expand the policy network's exploration space, while in the deployment phase, policy outputs are filtered through a real-time safety-stability layer. In addition, an event-triggered mechanism for action compensation calculation is designed based on safety condition assessments to conserve computational resources. Finally, the effectiveness of the proposed method is validated through simulation experiments in dynamic multiunicycle environments. The results demonstrate that our approach not only ensures strict adherence to safety constraints but also significantly enhances the task execution efficiency of multiagent systems.

Accurate modeling of dynamic systems is essential for robotics, enhancing system perception and control performance. This work tackles causal modeling challenges for mobile robots under complex uncertainties, including internal model inaccuracies and external environmental disturbances. Unlike first-principle or purely data-driven methods, we propose Pet-NODE, an advanced Neural Ordinary Differential Equation (NODE) framework that integrates physical priors with temporal features for high-fidelity system modeling. To further embed domain knowledge, we introduce a novel loss function with self-prediction objectives, ensuring adherence to physical principles. Extensive experiment evaluations, including ablation studies and comparisons against Nominal model, K-NODE and PI-TCN methods, demonstrate Pet-NODE’s robustness, interpretability, and superior localization accuracy on a self-collected wheeled robot dataset.

Unmanned Aerial Vehicles (UAVs) are gaining attention for inspections due to their improved safety, efficiency, and accuracy, alongside reduced costs and environmental risks. Visual servoing is crucial for autonomous UAV flight in GPS-degraded environments, guiding the UAV by minimizing errors between observed and desired visual features. This study focuses on Image-Based Visual Servoing (IBVS) control for quadrotor UAVs under complex dynamics and environmental disturbances. A nonlinear model predictive control (MPC) framework is first integrated with visual servoing to handle dynamics nonlinearity, control optimality, and constraints. To address uncertainties and disturbances, a Generalized Extended State Observer (GESO) is incorporated into the MPC, forming the Disturbance-Resilient (DR-) MPC. The GESO estimates the lumped disturbance to improve model predictions within the MPC horizon. The proposed algorithm is validated in a realistic Gazebo environment for UAV pipeline inspection in 3D scenarios, showing better control accuracy and reduced inspection time compared to three baseline methods: IBVS, IBVS-MPC(K) with kinematics, and IBVS-MPC(D) with dynamics.1

Model Predictive Path Integral (MPPI) controllers are drawing increasing attention for their ability to efficiently handle complex systems by leveraging GPU acceleration while with flexible prediction models and cost functions. However, their performance generally degrades with low-quality prediction models and unknown external disturbances. Existing methods that rely solely on feedforward disturbance compensation are limited by the assumption of matched disturbances, which rarely holds in practice due to the complex lumped disturbances. To this end, we propose a novel Disturbance-Aware (DA-) MPPI framework, which seamlessly integrates an Extended high-order Sliding Mode Observer (ESMO) into MPPI. The ESMO provides accurate estimates of uncertainties and external disturbances, which are directly incorporated into the MPPI rolling dynamics to improve prediction and therefore tracking control performance. The proposed algorithm is verified against the baseline MPPI in AirSim simulation environment by stochastic simulation. Comparatively statistical experiments show that incorporating ESMO within the MPPI framework significantly enhances tracking performance, with the RMSE reduction in term of mean by 8.0%, 17.7%, 6.17%, 12.9% and in term of standard variance by 11.5%, 26.0%, 10.4%, and 9.2% in four representative scenarios. The effects of target velocity and prediction horizon on control performance are also systematically evaluated. These results validate the robustness and accuracy of the DA-MPPI controller in complex and uncertain environments.1

Lane detection plays a crucial role in automated driving technology. However, current lane detection algorithms primarily focus on daily scenes, such as cars on urban roads and highways, while limited research addresses closed scenes, such as rubber tire gantries (RTGs) in ports. In this study, we propose a novel lane detection method based on explicit feature learning (EFL) to address this gap. Compared to general scenes, RTG lane lines in port exhibit distinctive characteristics, including regular straight-shaped features, relative spatial stability, and severe wear from heavy RTGs. There is also a higher requirement on algorithm precision while with a limited dataset size. To effectively address these challenges, we proposed PortLaneNet, which introduces an EFL network for better feature extraction, coupled with a shape loss function for improved evaluation and supervision. The multiscale feature extraction of the EFL network improves the model's global perception ability to cope with the loss of features caused by the severe wear of the port lane lines. The improved shape loss function strengthens the linearity of the model's inference results to adapt to the shape characteristics of port lane lines. To improve the model's spatial feature extraction capability, an adaptive channel attention mechanism is also introduced, which embeds spatial positional information of rows. The proposed method is evaluated on a self-collected dataset under various challenging environments, where extensively comparative experiments against six state-of-the-art algorithms with various backbones show that the proposed PortLaneNet demonstrates better detection performance in terms of F1 score, precision, and recall while with computation efficiency suitable for real-time applications.

This article aims to derive an adaptive optimal speed regulator for permanent magnet synchronous motors (PMSMs) affected by both disturbances and actuator faults. Load torque is first modeled as a mismatched disturbance, where its estimation via a disturbance observer is drawn to construct an error system. Then, optimal speed regulation problem for PMSM is equivalently transformed into an optimal control problem for the error system. Given the presence of model variable couplings, an adaptive dynamic programming method is adopted to derive the optimal controller, where a critic neural network (NN) and an actor NN are used to approximate the cost function and the optimal controller, respectively. Notably, this article addresses the simultaneous occurrence of disturbances and actuator faults within the optimal control framework by designing separate treatments. Eventually, a composite controller, fulfilling optimality, robustness and safety constraints, is presented with rigorous proof via Lyapunov method. The proposed method is substantiated through both comparative numerical examples and experimental validation on a PMSM platform.

Because of its excellent efficiency, compact dimen-sions, and accurate control features, Permanent Magnet Syn-chronous Motor (PMSM) are experiencing widespread applications across various industries. By accurately characterizing the dynamic behavior of PMSM systems through system identi-fication, engineers can ensure that PMSM motors reach their maximum potentials and meet the stringent requirements of modern industrial and technical systems while reducing energy consumption and maintenance costs. The traditional recursive least squares method is sensitive to noises, and unable to accu-rately identify parameters in complex environments. Pure data-driven models lack interpretability and require complex model architecture and computational costs. To this end, this work draws knowledge-informed neural ordinary differential equations (NODEs) for system identification, which embeds system prior knowledge into the NODEs for more efficient and accurate model learning. Comparative simulations show that this method not only obtains a higher-precision system model, but also significantly reduces the amount of training data and computation costs.

With the continuous development of the wind power industry, variable-speed wind turbines (VSWT) are moving towards large-scale, and their applications have been expanded to offshore areas. However, the operating environment of offshore wind farm is even more harsh, and the potential torsional vibration of the drivetrain caused by disturbances in the offshore wind farm may introduce fatigue damage to the VSWT, resulting in unexpected faults that may lead to prolonged shutdown of the VSWT and loss of power generation efficiency. This study proposes a torsional vibration suppression strategy based on unknown input observer and sliding mode control. The proposed suppression strategy provides an appropriate electromagnetic torque compensation for the generator to mitigate disturbances in the whole control system. The effectiveness of the proposed strategy is validated by extensive simulation studies.

This paper aims to investigate the disturbance estimation mechanism of extended state observer (ESO) from a new perspective: a time-delay estimation (TDE) interpretation. By drawing the concept of input-output linearization, ESO is transformed into an equivalent TDE form in frequency domain. The establishment of this relationship can lead to an improved understanding of ESO’s principle. In addition, ESO’s parameters for disturbance estimation are given with explicitly physical meanings. Furthermore, theoretical analysis from this perspective also results in a quantitative relationship between ESO estimation performance and its two tuning parameters including control gain$b_{0}$and bandwidth$\omega _{o}$. Theoretical results are evaluated by using an all-clamped plate structure with an inertial actuator, which is considered to be a typical benchmark for active vibration control. Extensive comparative experiments validate algorithm effectiveness. Note to Practitioners—This paper was focused on the ability of extended state observer (ESO) to estimate total disturbances. The controlled system is a typical benchmark for active vibration control consisting of an all-clamped plate structure with an inertial actuator. The model uncertainties and external disturbances that bothers the system is compensated by the real-time estimation of the ESO. In order to facilitate practical engineering applications, the distinct physical meanings of ESO parameters are expounded with the help of the relationship between ESO and time delay estimation (TDE) established in frequency domain. Moreover, the influence of parameters control gain$b_{0}$and bandwidth$\omega _{o}$on ESO is qualitatively established. Therefore, the engineer can avoid fall into a trial-and-error strategy that could be laborious and time-consuming. Thus, this paper proposed a convenient way for practitioners interested in developing anti-disturbance control strategies based on ESO. The simplicity and the partial-model-based characteristics are also profitable in practice. Potential applications include robotic systems, smart structures and electrical drives. In the future, the improvements of ESO based on the proposed method to deal with the intractable disturbances should be taken in an effort.

Agriculture is facing severe challenges from crop stresses, threatening its sustainable development and food security. This article exploits aerial visual perception for yellow rust disease monitoring, which seamlessly integrates state-of-the-art techniques and algorithms, including unmanned aerial vehicle sensing, multispectral imaging, vegetation segmentation, and deep learning U-Net. A field experiment is designed by infecting winter wheat with yellow rust inoculum, on top of which multispectral aerial images are captured by DJI Matrice 100 equipped with RedEdge camera. After image calibration and stitching, multispectral orthomosaic is labeled for system evaluation by inspecting high-resolution RGB images taken by Parrot Anafi Drone. The merits of the developed framework drawing spectral-spatial information concurrently are demonstrated by showing improved performance over purely spectral-based classifier by the classical random forest algorithm. Moreover, various network input band combinations are tested, including three RGB bands and five selected spectral vegetation indices, by sequential forward selection strategy of wrapper algorithm.

This article involves the adaptive inverse control of a coupled vessel-riser system with input backlash and system uncertainties. By introducing an adaptive inverse dynamics of backlash, the backlash control input is divided into a mismatch error and an expected control command, and then a novel adaptive inverse control strategy is established to eliminate vibration, tackle backlash, and compensate for system uncertainties. The bounded stability of the controlled system is analyzed and demonstrated by exploiting the Lyapunov's criterion. The simulation comparison experiments are finally presented to verify the feasibility and effectiveness of the control algorithm.

Early driver intention prediction plays a significant role in intelligent vehicles. Drivers exhibit various driving characteristics impairing the performance of conventional algorithms using all drivers' data indiscriminatingly. This paper develops a personalized driver intention prediction system at unsignalized T intersections by seamlessly integrating clustering and classification. Polynomial regression mixture (PRM) clustering and Akaike's information criterion are applied to individual drivers trajectories for learning in-depth driving behaviors. Then, various classifiers are evaluated to link low-level vehicle states to high-level driving behaviors. CART classifier with Bayesian optimization excels others in accuracy and computation. The proposed system is validated by a real-world driving dataset. Comparative experimental results indicate that PRM clustering can discover more in-depth driving behaviors than manually defined maneuver due to its fine ability in accounting for both spatial and temporal information; the proposed framework integrating PRM clustering and CART classification provides promising intention prediction performance and is adaptive to different drivers.

In model-based fault detection and isolation (FDI) systems, fault indicating signals (FISs) such as residuals and fault estimates are corrupted by various noises, uncertainties and variations. It becomes challenging to verify whether an FDI system still works or not in real life applications. It is also challenging to select a threshold so that false alarm rate and missed detection rate are kept low depending on real operation conditions. This paper proposes solutions to the aforementioned problems by quantitatively analyzing the effect of uncertainties on FIS. The problems are formulated into reachability analysis problem for uncertain systems. The reachable sets of FIS are calculated under normal and selected faulty cases, respectively. From these reachable sets, the effectiveness of an FDI system can be qualitatively verified under described uncertainties. A dedicated threshold can be further chosen to be robust to all possible described uncertainties. As a by-product, the minimum detectable fault can also be quantitatively determined by checking the intersection of the computed reachable sets. The proposed approach is demonstrated by evaluating an FDI algorithm of a motor in the presence of parameter uncertainties, unknown load, and sensor noises, where a fault estimation-based approach is adopted to diagnose amplifier, velocity, and current sensor faults.

Awareness of driver workload (DW) plays a paramount role in enhancing driving safety and convenience for intelligent vehicles. The DW prediction systems proposed so far learn either from individual driver's data (termed personalized system) or existing drivers' data indiscriminately (termed average system). As a result, they either do not work or lead to a limited performance for new drivers without labeled data. To this end, we develop clustering-aided approaches exploiting group characteristics of the existing drivers' data. Two clustering aided predictors are proposed. The first is clustering-aided regression (CAR) model, where the regression model for the cluster with the highest likelihood is adopted. The second is clustering-aided multiple model regression model, where the concept of multiple models is further augmented to CAR. A recent dataset from real-world driving experiments is adopted to validate the algorithms. Comparative results against the conventional average system demonstrate that by incorporating clustering information, both the proposed approaches significantly improve workload prediction performance.

Adapting in-vehicle systems (e.g., advanced driver assistance systems and in-vehicle information systems) to individual drivers' workload can enhance both safety and convenience. To make this possible, it is a prerequisite to infer driver workload so that adaptive aiding can be provided to the driver at the right time and in an appropriate manner. Rather than developing an average model for all drivers, a personalized driver workload inference (PDWI) system considering individual drivers driving characteristics is developed using machine learning techniques via easily accessed vehicle related measurements (VRMs). The proposed PDWI system comprises two stages. In offline training, individual drivers workload is first automatically splitted into different categories according to its inherent data characteristics using fuzzy C-means (FCM) clustering. Then an implicit mapping between VRMs and different levels of workload is constructed via classification algorithms. In online implementation, VRMs samples are classified into different clusters, consequently driver workload type can be successfully inferred. A recently collected dataset from real-world naturalistic driving experiments is drawn to validate the proposed PDWI system. Comparative experimental results indicate that the proposed framework integrating FCM clustering and support vector machine classifier provides a promising workload recognition performance in terms of accuracy, precision, recall, F1-score, and prediction time. The interindividual differences in term of workload are also identified and can be accommodated by the proposed framework due to its adaptiveness.

Since the landmark work of R. E. Kalman in the 1960s, considerable efforts have been devoted to time series state space models for a large variety of dynamic estimation problems. In particular, parametric filters that seek analytical estimates based on a closed-form Markov–Bayes recursion, e.g., recursion from a Gaussian or Gaussian mixture (GM) prior to a Gaussian/GM posterior (termed ‘Gaussian conjugacy’ in this paper), form the backbone for a general time series filter design. Due to challenges arising from nonlinearity, multimodality (including target maneuver), intractable uncertainties (such as unknown inputs and/or non-Gaussian noises) and constraints (including circular quantities), etc., new theories, algorithms, and technologies have been developed continuously to maintain such a conjugacy, or to approximate it as close as possible. They had contributed in large part to the prospective developments of time series parametric filters in the last six decades. In this paper, we review the state of the art in distinctive categories and highlight some insights that may otherwise be easily overlooked. In particular, specific attention is paid to nonlinear systems with an informative observation, multimodal systems including Gaussian mixture posterior and maneuvers, and intractable unknown inputs and constraints, to fill some gaps in existing reviews and surveys. In addition, we provide some new thoughts on alternatives to the first-order Markov transition model and on filter evaluation with regard to computing complexity.

A new continuous dynamic sliding-mode control (CDSMC) method is proposed for high-order mismatched disturbance attenuation in motion control systems using a high-order sliding-mode differentiator. First, a new dynamic sliding surface is developed by incorporating the information of the estimates of disturbances and their high-order derivatives. A CDSMC law is then designed for a general motion control system with both high-order matched and mismatched disturbances, which can attenuate the effects of disturbances from the system output. The proposed control method is finally applied for the airgap control of a MAGnetic LEViation (MAGLEV) suspension vehicle. Simulation results show that the proposed method exhibits promising control performance in the presence of high-order matched and mismatched disturbances.