IEEE/CAA Journal of Automatica Sinica

Parallel Experiments: From The Human Participated to A Virtual-Real Hybrid Paradigm

Peijun Ye, Xiao Xue, Qinghua Ni, Jing Yang, Fei-Yue Wang

2025, 12(8): 1525-1529. doi: 10.1109/JAS.2025.125474

Abstract(76) HTML (3) PDF(10)

Abstract:

Camera Planning for Physical Safety of Outdoor Electronic Devices: Perspective and Analysis

Qin Su, Lei Shu, Gerhard Petrus Hancke, Kai Huang, Edmond Nurellari, Qingsong Zhao, Nikumani Choudhury, Anakhi Hazarika

2025, 12(8): 1530-1543. doi: 10.1109/JAS.2025.125129

Abstract(302) HTML (3) PDF(35)

Abstract:
Camera technology advancement and deployment continue to play a vital role in modern life and production, amongst other capabilities, generating relevant visual information. The challenge of optimizing the use and deployment of camera networks in various applications (e.g., surveillance, traffic monitoring, and public safety to name but just a few) has attracted considerable attention from both academia and industries. Camera planning is the first step in addressing this challenge. The surveillance objectives and scenes of a camera network dictate the modelling and optimization algorithms for camera planning. However, existing reviews have primarily focused on models or optimization algorithms, with insufficient attention given to surveillance scenes. This review aims to bridge this gap by 1) Classifying surveillance scenes into the urban environment and rural outdoor environment and comparing the surveillance requirements and challenges; 2) Summarizing the details of camera coverage optimization in the relevant literature from the perspective of deployment scenes; and 3) Proposing a new surveillance scene—Solar Insecticidal Lamps with the Internet of Things—as a case study to analyze the surveillance requirement and challenges in agricultural outdoor environment. Finally, we state the technical outlook on the physical safety of outdoor electronic devices in agriculture settings and provide insights to draw more attention and effort into this area.

Data-Driven Calibration of Industrial Robots: A Comprehensive Survey

Tinghui Chen, Weiyi Yang, Shuai Li, Xin Luo

2025, 12(8): 1544-1567. doi: 10.1109/JAS.2025.125237

Abstract(141) HTML (4) PDF(28)

Abstract:
Industrial robots, as the fundamental component for intelligent manufacturing, have attracted considerable attention from both academia and industry. Since its absolute positioning accuracy can suffer from collision, wear, elastic, or inelastic deformation during its operation, a data-driven calibration (DDC) model has become a trending technique. It utilizes abundant data to decrease the difficulty in building complex system models, making it an economic and efficient approach to robot calibration. This paper conducts a comprehensive survey of the state-of-the-art DDC models with the following six-fold efforts: a) Summarizing the DDC modeling methods; b) Categorizing the latest progress of DDC optimization algorithms; c) Investigating the publicly available datasets and several typical metrics; d) Evaluating several widely adopted DDC models to demonstrate their calibration performance; e) Introducing the applications of the current DDC models; f) Discussing the progressing trend of DDC models. This paper strives to present a systematic and thorough overview of the existing DDC models from modeling to kinematic parameter optimization, thereby providing some guidance for research in this field.

From Singleton to Collaboration: Robust 3D Cooperative Positioning for Intelligent Connected Vehicles Based on Hybrid Range-Azimuth-Elevation Under Zero-Trust Driving Environments

Zhenyuan Zhang, Heng Qin, Darong Huang, Xin Fang, Mu Zhou, Shenghui Guo

2025, 12(8): 1568-1585. doi: 10.1109/JAS.2024.124698

Abstract(480) HTML (2) PDF(97)

Abstract:
Reliable and accurate cooperative positioning is vital to intelligent connected vehicles (ICVs), in which vehicle-vehicle relative measurements are integrated to provide stable location-aware services. However, in zero-trust autonomous driving environments, the possibility of measurement failures and malicious communication attacks tends to reduce positioning performance. With this in mind, this paper presents an ultra-wide bandwidth (UWB) based cooperative positioning system with the specific objective of ICV localization in zero-trust driving environments. Firstly, to overcome measurement degradation under non-line-of-sight (NLOS) propagation conditions, this study proposes a decentralized 3D cooperative positioning method based on a distributed Kalman filter (DKF) by integrating relative range-azimuth-elevation measurements, unlike the state-of-the-art methods that rely on only one single relative range information to update motion states. More specifically, in contrast to pioneering studies that mainly focus on the positioning problem arising from only one single type of communication attack (either false data injection (FDI) or denial of service (DoS)), we consider a more challenging case of secure cooperative state estimation under mixed FDI and DoS attacks. To this end, a singular-value decomposition (SVD)-assisted decoupled DKF algorithm is proposed in this work, in which a novel update-triggered inter-vehicular communication mechanism is introduced to ensure robust positioning performance against communication attacks while maintaining low transmission load between individuals. To verify the effectiveness in practical 3D NLOS scenarios, we design an intelligent connected multi-robot platform based on a robot operating system (ROS) and UWB technology. Consequently, extensive experimental results demonstrate its superiority and feasibility by achieving a high positioning accuracy of 0.68 m under adverse attacks, especially in the case of hybrid FDI and DoS attacks. In addition, several critical discussions, including the impact of attack parameters, resilience assessment, and a comparison with event-triggered methods, are provided in this work. Moreover, a demo video has been uploaded in the supplementary materials for a detailed presentation.

Global Sampled-Data Output Feedback Stabilization for Nonlinear Systems via Intermittent Hold

Le Chang, Cheng Fu, Huanjun Zhang

2025, 12(8): 1586-1593. doi: 10.1109/JAS.2024.125019

Abstract(205) HTML (2) PDF(44)

Abstract:
This paper introduces a sampled-data and intermittent-hold controller for nonlinear feedforward systems. The intermittent hold allows the control signal to be held in a portion of each sampled period, which does not require the control to be persistently implemented, and thus has less control time. But, less control time degrades the performance of a continuous-time control system or even destabilizes it, especially when the holding portion is sufficiently small. To tackle this obstacle, we first introduce the notion of activating rate to describe the intermittent hold, and give the sampled-data and intermittent-hold controller based on some tuning parameters. Then it is proved that for any activating rate, these parameters can be designed to achieve the stability of the considered systems under appropriately choosing the sampling size. Finally, simulation examples are given to illustrate the effectiveness of the proposed method.

Deep Reinforcement Learning for Zero-Shot Coverage Path Planning With Mobile Robots

José Pedro Carvalho, A. Pedro Aguiar

2025, 12(8): 1594-1609. doi: 10.1109/JAS.2024.125064

Abstract(537) HTML (3) PDF(131)

Abstract:
The ability of mobile robots to plan and execute a path is foundational to various path-planning challenges, particularly Coverage Path Planning. While this task has been typically tackled with classical algorithms, these often struggle with flexibility and adaptability in unknown environments. On the other hand, recent advances in Reinforcement Learning offer promising approaches, yet a significant gap in the literature remains when it comes to generalization over a large number of parameters. This paper presents a unified, generalized framework for coverage path planning that leverages value-based deep reinforcement learning techniques. The novelty of the framework comes from the design of an observation space that accommodates different map sizes, an action masking scheme that guarantees safety and robustness while also serving as a learning-from-demonstration technique during training, and a unique reward function that yields value functions that are size-invariant. These are coupled with a curriculum learning-based training strategy and parametric environment randomization, enabling the agent to tackle complete or partial coverage path planning with perfect or incomplete knowledge while generalizing to different map sizes, configurations, sensor payloads, and sub-tasks. Our empirical results show that the algorithm can perform zero-shot learning scenarios at a near-optimal level in environments that follow a similar distribution as during training, outperforming a greedy heuristic by sixfold. Furthermore, in out-of-distribution environments, our method surpasses existing state-of-the-art algorithms in most zero-shot and all few-shot scenarios, paving the way for generalizable and adaptable path-planning algorithms.

DKAMFormer: Domain Knowledge-Augmented Multiscale Transformer for Remaining Useful Life Prediction of Aeroengine

Song Fu, Yue Wang, Lin Lin, Minghang Zhao, Lizheng Zu, Yifan Lu, Feng Guo, Shiwei Suo, Yikun Liu, Sihao Zhang, Shisheng Zhong

2025, 12(8): 1610-1635. doi: 10.1109/JAS.2025.125126

Abstract(337) HTML (3) PDF(48)

Abstract:
Transformers have achieved promising results on aeroengine remaining useful life (RUL) prediction, but they still have several limitations: 1) Aeroengine domain knowledge, which contains rich information that can reflect the aeroengine’s health statue, is largely ignored in modeling process; 2) Traditional transformer ignores the valuable degradation information from other time scales. To address these issues, a novel domain knowledge-augmented multiscale transformer (DKAMFormer) is developed by integrating domain knowledge and multiscale learning to improve the prognostic performance and reliability. First, to obtain rich and professional aeroengine domain knowledge, multiple detail and complete knowledge graphs (KGs) are established based on the working principle of aeroengine, including aeroengine structure, components working characteristics and sensor parameters. Second, the domain knowledge contained in KGs is convert to embedded vector by KG representative learning, which are then utilized to strengthen and enrich the original multidimensional time-series (MTS) monitoring data, aiming to intergrade domain knowledge and monitoring data to train DKAMFormer. Third, to learn rich and complementary degradation features, a novel multiscale time scale-guided self-attention (MTSGSA) mechanism is designed, which maps original MTS into different time-scale feature spaces, and then employs multiple independent self-attention head to extract the degradation features from different time-scale spaces. Finally, through a series of comparative experiments on the public CMAPSS and N-CMAPSS datasets and compared with 17 SOTA methods, the developed DKAMFormer significantly improves the RUL prediction performance under multiple operation conditions and degradation modes.

Unified Output Feedback Based Prescribed Performance Consensus Tracking Control of Heterogeneous Multi-Agent Systems

Dahui Luo, Yujuan Wang, Frank L. Lewis, Yongduan Song

2025, 12(8): 1636-1647. doi: 10.1109/JAS.2024.125094

Abstract(190) HTML (2) PDF(56)

Abstract:
This paper proposes an output-feedback based prescribed performance consensus tracking control methodology for a class of heterogeneous multi-agent systems (HMASs) with inconsistent system structure, where the performance behavior is allowed to be different from that of each other. Both the heterogeneous system structures and the nonidentical performance requirements make the control problem much more challenging than that of MASs with identical structure and performance requirement. This is mainly due to the coupling effect of the system dynamics and performance restriction of each agent in the cooperative control action. The key to solve this problem is to introduce a dual-phase performance-guaranteed method, in which the consensus tracking error is decomposed into auxiliary tracking error and filter tracking error and then the whole performance control is decomposed into two phases. By confining the two errors respectively, the practical tracking error can be proved to be explicitly confined within an arbitrarily given performance envelope by merely adjusting the design parameters rather than modifying control structure. Moreover, the prescribed performance control (PPC) result is not only uniform with any initial conditions and design parameters, allowing it to be global, but also unifying both the global and semi-global result into one frame, distinguishing itself from most existing PPC works where either only global or only semi-global result is guaranteed. Finally, the effectiveness of the proposed control scheme is confirmed by the simulation conducted on a group of tunnel-diode circuits (TDC).

LTDNet: A Lightweight Text Detector for Real-Time Arbitrary-Shape Traffic Text Detection

Runmin Wang, Yanbin Zhu, Ziyu Zhu, Lingxin Cui, Zukun Wan, Anna Zhu, Yajun Ding, Shengyou Qian, Changxin Gao, Nong Sang

2025, 12(8): 1648-1660. doi: 10.1109/JAS.2024.125022

Abstract(244) HTML (3) PDF(51)

Abstract:
Traffic text detection plays a vital role in understanding traffic scenes. Traffic text, a distinct subset of natural scene text, faces specific challenges not found in natural scene text detection, including false alarms from non-traffic text sources, such as roadside advertisements and building signs. Existing state-of-the-art methods employ increasingly complex detection frameworks to pursue higher accuracy, leading to challenges with real-time performance. In response to this issue, we propose a real-time and efficient traffic text detector named LTDNet, which strikes a balance between accuracy and real-time capabilities. LTDNet integrates three essential techniques to address these challenges effectively. First, a cascaded multilevel feature fusion network is employed to mitigate the limitations of lightweight backbone networks, thereby enhancing detection accuracy. Second, a lightweight feature attention module is introduced to enhance inference speed without compromising accuracy. Finally, a novel point-to-edge distance vector loss function is proposed to precisely localize text instance boundaries within traffic contexts. The superiority of our method is validated through extensive experiments on five publicly available datasets, demonstrating its state-of-the-art performance. The code will be released at https://github.com/runminwang/LTDNet.

Synthesis of Optimal Stealthy Attacks Against Diagnosability in Labeled Petri Nets

Ruotian Liu, Agostino Marcello Mangini, Maria Pia Fanti

2025, 12(8): 1661-1672. doi: 10.1109/JAS.2025.125156

Abstract(160) HTML (4) PDF(12)

Abstract:
This paper addresses the diagnosability analysis problem under external malicious attacks of a networked discrete event system modeled by labeled Petri net. In particular, we focus on a stealthy replacement attack to alter or corrupt the observation of the system, in which the transition labels are replaced by others or empty string, and its attack stealthiness requires that the corrupted observations should be contained in the behavior of system. The aim of this work is, from an attacker viewpoint, to design a stealthy replacement attack for violating the diagnosability of system. To this end, we first build a new structure, called complete unfolded verifier, with the notion of a predefined elementary unsound path that leads to the violation of diagnosability, which is used to enumerate all the potential attacked paths to be transformed into elementary unsound ones. Then an optimal attack synthesis problem in terms of minimum energy cost is formulated by determining whether an elementary unsound path is generated via solving a set of integer nonlinear programming problems. Finally, we show that the nonlinear programming problems can be transformed into integer linear programming problems by introducing additional linear constraints. Examples are used to illustrate the proposed attack strategy.

A Homotopy Method for Continuous-Time Model-Free LQR Control Based on Policy Iteration

Wenwu Fan, Junlin Xiong

2025, 12(8): 1673-1682. doi: 10.1109/JAS.2025.125132

Abstract(267) HTML (3) PDF(30)

Abstract:
In recent years, reinforcement learning control theory has been well developed. However, model-free value iteration needs many iterations to achieve the desired precision, and model-free policy iteration requires an initial stabilizing control policy. It is significant to propose a fast model-free algorithm to solve the continuous-time linear quadratic control problem without an initial stabilizing control policy. In this paper, we construct a homotopy path on which each point corresponds to an linear quadratic regulator problem. Based on policy iteration, model-based and model-free homotopy algorithms are proposed to solve the optimal control problem of continuous-time linear systems along the homotopy path. Our algorithms are speeded up using first-order differential information and do not require an initial stabilizing control policy. Finally, several practical examples are used to illustrate our results.

A Hierarchical Stochastic Network Approach for Fault Diagnosis of Complex Industrial Processes

Mingjie Lv, Yonggang Li, Huanzhi Gao, Bei Sun, Keke Huang, Chunhua Yang, Weihua Gui

2025, 12(8): 1683-1701. doi: 10.1109/JAS.2025.125249

Abstract(141) HTML (3) PDF(21)

Abstract:
Complex industrial processes present typical uncertainty due to fluctuations in the composition of raw materials and frequently changing operating conditions. This poses three challenges for precise fault diagnosis, including random noise interference, less distinguishability between multi-class faults, and the new fault emerging. To address these issues, this study formulates fault diagnosis in uncertain industrial processes as a multi-level refined fault diagnosis problem. A hierarchical stochastic network approach is proposed to refine fault diagnosis of multi-class faults. This method considers the augmentation of fault categories as naturally following a hierarchical structure. At each hierarchical stage, stochastic network methods are designed according to the sources of uncertainty. For fault feature extraction, a doubly stochastic attention-based variational graph autoencoder is introduced to suppress noise during the message-passing process, ensuring the extraction of high-quality fault features and providing the provision of differentiated information. Subsequently, multiple stochastic configuration networks are deployed to realize multi-level fault diagnosis from coarse to fine granularity via a hierarchical structure rather than treating all faults equally. This approach effectively enhances the precision of multi-class fault diagnosis and ensures its robust generalization capability. Finally, the feasibility and effectiveness of the proposed method are validated using two industrial processes. The results demonstrate that the proposed method can effectively suppress the random noise interference and adapt to the emergence of small samples and imbalanced extreme fault-type data, achieving a satisfactory fault diagnosis performance.

Improving Control Performance by Cascading Observers: Case of ADRC With Cascade ESO

Ahmed T.-E. Benyahia, Momir Stanković, Rafal Madonski, Oluleke Babayomi, Stojadin M. Manojlović

2025, 12(8): 1702-1712. doi: 10.1109/JAS.2024.124995

Abstract(265) HTML (4) PDF(54)

Abstract:
In this paper, we show the performance benefits of connecting multiple observers within a control system. We focus here on a particular observer-based control approach, namely the active disturbance rejection control (ADRC) with cascade extended state observer (ESO). For this framework, we analyze the control performance in terms of quality of observer estimation, reference tracking, disturbance rejection, sensitivity to measurement noise/unmodeled dynamics, and overall stability. A comprehensive frequency response analysis is performed to study the influence of cascading the observers on the selected quality criteria. To make the inquiry beneficial also to practitioners, FPGA-in-the-loop tests are conducted using a guided missiles gimbaled seeker. They validate the theoretical findings in discrete-time settings, where the sampling time and hardware resource requirements become a factor. The results of the investigation are distilled into guidelines for prospective users on when and how a cascade observer structure can be useful for controls.

An Emulation Approach to Semi-Global Robust Output Regulation for a Class of Nonlinear Uncertain Systems

Jieshuai Wu, Maobin Lu, Fang Deng, Jie Chen

2025, 12(8): 1713-1723. doi: 10.1109/JAS.2024.125085

Abstract(214) HTML (4) PDF(29)

Abstract:
In this paper, we investigate the semi-global robust output regulation problem of a class of nonlinear networked control systems. By the emulation approach, we propose a class of sampled-data output feedback control laws to solve this problem. In particular, we first develop a general sampled-data dynamic output feedback control law and characterize the closed-loop system by a hybrid system. Then, we design the internal model based on the sampled error output of the system. Based on the internal model principle, we convert the semi-global robust output regulation problem into a semi-global robust stabilization problem of an augmented hybrid system composed of the internal model and the original system. By proposing the sampled error output feedback control law and by means of Lyapunov analysis, we obtain the maximum allowable transmission interval for sampling and show that semi-global robust stabilization of the augmented hybrid system can be achieved by the proposed sampled-data control law and thus leading to the solution of the semi-global robust output regulation problem. Finally, we apply the proposed control approach to two practical applications to verify the effectiveness of the proposed control approach.