The consensus tracking problem is investigated for a class of multi-agent systems (MASs) under communication constraints. In particular, as a result of the impact of amplitude attenuation and random interference, communication among followers may inevitably suffer from the fading phenomenon. Meanwhile, the controllers may also be subject to malicious deception attacks, which will disrupt the correct operation of the MASs. Thus, the agents can only update their states based on fading information exchanged with their neighbors and the false control input under attacks. The consensus tracking error variables are first designed via the fading signal received from neighbors. Then, an online estimation strategy is introduced to estimate the unknown attacks, based on which the adaptive sliding mode controller is designed to attenuate the effect of the time-varying attacks on MASs. Convergence analysis of the MASs under the designed control strategy is provided by using the Lyapunov stability theory and adaptive sliding mode control method. Finally, the effectiveness of the theoretical results is verified via numerical simulations.
{"title":"Secure consensus control for multi-agent systems under communication constraints via adaptive sliding mode technique","authors":"Mengzhao Ding, Bei Chen","doi":"10.20517/ces.2023.06","DOIUrl":"https://doi.org/10.20517/ces.2023.06","url":null,"abstract":"The consensus tracking problem is investigated for a class of multi-agent systems (MASs) under communication constraints. In particular, as a result of the impact of amplitude attenuation and random interference, communication among followers may inevitably suffer from the fading phenomenon. Meanwhile, the controllers may also be subject to malicious deception attacks, which will disrupt the correct operation of the MASs. Thus, the agents can only update their states based on fading information exchanged with their neighbors and the false control input under attacks. The consensus tracking error variables are first designed via the fading signal received from neighbors. Then, an online estimation strategy is introduced to estimate the unknown attacks, based on which the adaptive sliding mode controller is designed to attenuate the effect of the time-varying attacks on MASs. Convergence analysis of the MASs under the designed control strategy is provided by using the Lyapunov stability theory and adaptive sliding mode control method. Finally, the effectiveness of the theoretical results is verified via numerical simulations.","PeriodicalId":72652,"journal":{"name":"Complex engineering systems (Alhambra, Calif.)","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67657233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents a framework for generating high-definition (HD) map, and then achieves accurate and robust localization by virtue of the map. An iterative approximation based method is developed to generate a HD map in Lanelet2 format. A feature association method based on structural consistency and feature similarity is proposed to match the elements of the HD map and the actual detected elements. The feature association results from the HD map are used to correct lateral drift in the light detection and ranging odometry. Finally, some experimental results are presented to verify the reliability and accuracy of autonomous driving localization.
{"title":"Generation of high definition map for accurate and robust localization","authors":"Zhengjie Huang, Sijie Chen, Xing Xi, Yanzhou Li, Ya Li, Shuanglin Wu","doi":"10.20517/ces.2022.43","DOIUrl":"https://doi.org/10.20517/ces.2022.43","url":null,"abstract":"This paper presents a framework for generating high-definition (HD) map, and then achieves accurate and robust localization by virtue of the map. An iterative approximation based method is developed to generate a HD map in Lanelet2 format. A feature association method based on structural consistency and feature similarity is proposed to match the elements of the HD map and the actual detected elements. The feature association results from the HD map are used to correct lateral drift in the light detection and ranging odometry. Finally, some experimental results are presented to verify the reliability and accuracy of autonomous driving localization.","PeriodicalId":72652,"journal":{"name":"Complex engineering systems (Alhambra, Calif.)","volume":"12 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67657522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, the decentralized tracking control (DTC) problem is investigated for a class of continuous-time nonlinear systems with external disturbances. First, the DTC problem is resolved by converting it into the optimal tracking controller design for augmented tracking isolated subsystems (ATISs). %It is investigated in the form of the nominal system. A cost function with a discount is taken into consideration. Then, in the case of external disturbances, the DTC scheme is effectively constructed via adding the appropriate feedback gain to each ATIS. %Herein, we aim to obtain the optimal control strategy for minimizing the cost function with discount. In addition, utilizing the approximation property of the neural network, the critic network is constructed to solve the Hamilton-Jacobi-Isaacs equation, which can derive the optimal tracking control law and the worst disturbance law. Moreover, the updating rule is improved during the process of weight learning, which removes the requirement for initial admission control. Finally, through the interconnected spring-mass-damper system, a simulation example is given to verify the availability of the DTC scheme.
{"title":"Decentralized tracking control design based on intelligent critic for an interconnected spring-mass-damper system","authors":"Wenqian Fan, Aohua Liu, Ding Wang","doi":"10.20517/ces.2023.04","DOIUrl":"https://doi.org/10.20517/ces.2023.04","url":null,"abstract":"In this paper, the decentralized tracking control (DTC) problem is investigated for a class of continuous-time nonlinear systems with external disturbances. First, the DTC problem is resolved by converting it into the optimal tracking controller design for augmented tracking isolated subsystems (ATISs). %It is investigated in the form of the nominal system. A cost function with a discount is taken into consideration. Then, in the case of external disturbances, the DTC scheme is effectively constructed via adding the appropriate feedback gain to each ATIS. %Herein, we aim to obtain the optimal control strategy for minimizing the cost function with discount. In addition, utilizing the approximation property of the neural network, the critic network is constructed to solve the Hamilton-Jacobi-Isaacs equation, which can derive the optimal tracking control law and the worst disturbance law. Moreover, the updating rule is improved during the process of weight learning, which removes the requirement for initial admission control. Finally, through the interconnected spring-mass-damper system, a simulation example is given to verify the availability of the DTC scheme.","PeriodicalId":72652,"journal":{"name":"Complex engineering systems (Alhambra, Calif.)","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67657193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As under-constrained systems, four-wheel-independent-drive (4WID) electric vehicles have more driving degrees of freedom. In this context, reasonable control and distribution of driving or braking torque to each wheel is extremely important from the vehicle safety perspective. However, it is difficult to provide the optimal wheel torque because of the time-varying characteristics and typical over-actuated nature of the system. In light of these challenges, a novel hierarchical control scheme comprising a top- and bottom-level controller is proposed herein. First, for the top-level controller, a time-varying model-predictive-control (TV-MPC) controller is designed based on an extended 3-degree-of-freedom (3-DOF) reference vehicle model. The total driving force and additional yaw moment can be obtained using the TV-MPC. Second, for the bottom-level controller, the torque expression of each wheel is determined using the equal-adhesion-rate-rule -based algorithm. The co-simulation results obtained herein indicate that the proposed control scheme can effectively improve vehicle safety.
{"title":"Nonlinear hierarchical control for four-wheel-independent-drive electric vehicle","authors":"Xiang Chen, Y. Qu, Taowen Cui, Jin Zhao","doi":"10.20517/ces.2022.50","DOIUrl":"https://doi.org/10.20517/ces.2022.50","url":null,"abstract":"As under-constrained systems, four-wheel-independent-drive (4WID) electric vehicles have more driving degrees of freedom. In this context, reasonable control and distribution of driving or braking torque to each wheel is extremely important from the vehicle safety perspective. However, it is difficult to provide the optimal wheel torque because of the time-varying characteristics and typical over-actuated nature of the system. In light of these challenges, a novel hierarchical control scheme comprising a top- and bottom-level controller is proposed herein. First, for the top-level controller, a time-varying model-predictive-control (TV-MPC) controller is designed based on an extended 3-degree-of-freedom (3-DOF) reference vehicle model. The total driving force and additional yaw moment can be obtained using the TV-MPC. Second, for the bottom-level controller, the torque expression of each wheel is determined using the equal-adhesion-rate-rule -based algorithm. The co-simulation results obtained herein indicate that the proposed control scheme can effectively improve vehicle safety.","PeriodicalId":72652,"journal":{"name":"Complex engineering systems (Alhambra, Calif.)","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67657116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Reinforcement learning with Takagi-Sugeno-Kang fuzzy systems","authors":"Eric Zander, Ben van Oostendorp, B. Bede","doi":"10.20517/ces.2023.11","DOIUrl":"https://doi.org/10.20517/ces.2023.11","url":null,"abstract":"","PeriodicalId":72652,"journal":{"name":"Complex engineering systems (Alhambra, Calif.)","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67657276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article investigates the practical stabilization problem of random quarter-car active suspension systems. An adaptive dynamic event-trigger strategy is proposed to stabilize the states of vehicle suspension in response to system uncertainty and controller area network resource constraints. Moreover, the model of random active suspension systems is extended to the general random robot systems; the controller is developed with the aid of a double dynamic surface filter, immersion and invariance (I&I) techniques, and event-triggered mechanisms. The results show that the semi-global stability of error systems is achieved, and there are some improvements in triggering times and adaptive estimation performance under the control framework. Finally, simulation comparison results are provided to prove the advantages of the proposed scheme.
{"title":"Dynamic event-triggered practical stabilization of random suspension system based on immersion and invariance","authors":"Cun Yang, Zhaojing Wu, Likang Feng","doi":"10.20517/ces.2023.25","DOIUrl":"https://doi.org/10.20517/ces.2023.25","url":null,"abstract":"This article investigates the practical stabilization problem of random quarter-car active suspension systems. An adaptive dynamic event-trigger strategy is proposed to stabilize the states of vehicle suspension in response to system uncertainty and controller area network resource constraints. Moreover, the model of random active suspension systems is extended to the general random robot systems; the controller is developed with the aid of a double dynamic surface filter, immersion and invariance (I&I) techniques, and event-triggered mechanisms. The results show that the semi-global stability of error systems is achieved, and there are some improvements in triggering times and adaptive estimation performance under the control framework. Finally, simulation comparison results are provided to prove the advantages of the proposed scheme.","PeriodicalId":72652,"journal":{"name":"Complex engineering systems (Alhambra, Calif.)","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135058931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Review on key technologies of green power supply for port microgrid","authors":"","doi":"10.20517/ces.2022.46","DOIUrl":"https://doi.org/10.20517/ces.2022.46","url":null,"abstract":"","PeriodicalId":72652,"journal":{"name":"Complex engineering systems (Alhambra, Calif.)","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67657069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nicholas Ernest, Timothy Arnett, Zachariah Phillips
Explainable AI is a topic at the forefront of the field currently for reasons involving human trust in AI, correctness, auditing, knowledge transfer, and regulation. AI that is developed with reinforcement learning (RL) is especially of interest due to the non-transparency of what was learned from the environment. RL AI systems have been shown to be "brittle" with respect to the conditions it can safely operate in, and therefore ways to show correctness regardless of input values are of key interest. One way to show correctness is to verify the system using Formal Methods, known as Formal Verification. These methods are valuable, but costly and difficult to implement, leading most to instead favor other methodologies for verification that may be less rigorous, but more easily implemented. In this work, we show methods for development of an RL AI system for aspects of the strategic combat game Starcraft 2 that is performant, explainable, and formally verifiable. The resulting system performs very well on example scenarios while retaining explainability of its actions to a human operator or designer. In addition, it is shown to adhere to formal safety specifications about its behavior.
{"title":"Formal verification of Fuzzy-based XAI for Strategic Combat Game","authors":"Nicholas Ernest, Timothy Arnett, Zachariah Phillips","doi":"10.20517/ces.2022.54","DOIUrl":"https://doi.org/10.20517/ces.2022.54","url":null,"abstract":"Explainable AI is a topic at the forefront of the field currently for reasons involving human trust in AI, correctness, auditing, knowledge transfer, and regulation. AI that is developed with reinforcement learning (RL) is especially of interest due to the non-transparency of what was learned from the environment. RL AI systems have been shown to be \"brittle\" with respect to the conditions it can safely operate in, and therefore ways to show correctness regardless of input values are of key interest. One way to show correctness is to verify the system using Formal Methods, known as Formal Verification. These methods are valuable, but costly and difficult to implement, leading most to instead favor other methodologies for verification that may be less rigorous, but more easily implemented. In this work, we show methods for development of an RL AI system for aspects of the strategic combat game Starcraft 2 that is performant, explainable, and formally verifiable. The resulting system performs very well on example scenarios while retaining explainability of its actions to a human operator or designer. In addition, it is shown to adhere to formal safety specifications about its behavior.","PeriodicalId":72652,"journal":{"name":"Complex engineering systems (Alhambra, Calif.)","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67657128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Anoop Sathyan, Abraham Itzhak Weinberg, Kelly Cohen
This paper presents the use of two popular explainability tools called Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP) to explain the predictions made by a trained deep neural network. The deep neural network used in this work is trained on the UCI Breast Cancer Wisconsin dataset. The neural network is used to classify the masses found in patients as benign or malignant based on 30 features that describe the mass. LIME and SHAP are then used to explain the individual predictions made by the trained neural network model. The explanations provide further insights into the relationship between the input features and the predictions. SHAP methodology additionally provides a more holistic view of the effect of the inputs on the output predictions. The results also present the commonalities between the insights gained using LIME and SHAP. Although this paper focuses on the use of deep neural networks trained on UCI Breast Cancer Wisconsin dataset, the methodology can be applied to other neural networks and architectures trained on other applications. The deep neural network trained in this work provides a high level of accuracy. Analyzing the model using LIME and SHAP adds the much desired benefit of providing explanations for the recommendations made by the trained model.
{"title":"Interpretable AI for bio-medical applications.","authors":"Anoop Sathyan, Abraham Itzhak Weinberg, Kelly Cohen","doi":"10.20517/ces.2022.41","DOIUrl":"https://doi.org/10.20517/ces.2022.41","url":null,"abstract":"<p><p>This paper presents the use of two popular explainability tools called Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP) to explain the predictions made by a trained deep neural network. The deep neural network used in this work is trained on the UCI Breast Cancer Wisconsin dataset. The neural network is used to classify the masses found in patients as benign or malignant based on 30 features that describe the mass. LIME and SHAP are then used to explain the individual predictions made by the trained neural network model. The explanations provide further insights into the relationship between the input features and the predictions. SHAP methodology additionally provides a more holistic view of the effect of the inputs on the output predictions. The results also present the commonalities between the insights gained using LIME and SHAP. Although this paper focuses on the use of deep neural networks trained on UCI Breast Cancer Wisconsin dataset, the methodology can be applied to other neural networks and architectures trained on other applications. The deep neural network trained in this work provides a high level of accuracy. Analyzing the model using LIME and SHAP adds the much desired benefit of providing explanations for the recommendations made by the trained model.</p>","PeriodicalId":72652,"journal":{"name":"Complex engineering systems (Alhambra, Calif.)","volume":"2 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10074303/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9625387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we examine the stability of highly nonlinear switched stochastic systems (SSSs) with time-varying delays, where the switching time instants are deterministic rather than stochastic. Herein, the boundedness of the global solution is first proven for highly nonlinear SSSs via the average dwell time (ADT) method and multiple Lyapunov function (MLF) approach. Then, the stability criteria for qth moment exponential stability and almost surely exponential stability are presented. The main difficulty lies in the presence of switching and time-varying delay terms, which prevents the validation of existing methods. New inequality techniques have been developed to counteract the effects of switching signals and time-varying delays. Finally, an example is provided to verify the effectiveness of the results.
{"title":"Stability analysis for highly nonlinear switched stochastic systems with time-varying delays","authors":"Jing Sun, Haibo Wang","doi":"10.20517/ces.2022.48","DOIUrl":"https://doi.org/10.20517/ces.2022.48","url":null,"abstract":"In this paper, we examine the stability of highly nonlinear switched stochastic systems (SSSs) with time-varying delays, where the switching time instants are deterministic rather than stochastic. Herein, the boundedness of the global solution is first proven for highly nonlinear SSSs via the average dwell time (ADT) method and multiple Lyapunov function (MLF) approach. Then, the stability criteria for qth moment exponential stability and almost surely exponential stability are presented. The main difficulty lies in the presence of switching and time-varying delay terms, which prevents the validation of existing methods. New inequality techniques have been developed to counteract the effects of switching signals and time-varying delays. Finally, an example is provided to verify the effectiveness of the results.","PeriodicalId":72652,"journal":{"name":"Complex engineering systems (Alhambra, Calif.)","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67657080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：