Journal of Automation and Intelligence最新文献

Large language models for robotics: Opportunities, challenges, and perspectives 机器人的大型语言模型：机遇、挑战和前景

Journal of Automation and Intelligence Pub Date : 2025-03-01 DOI: 10.1016/j.jai.2024.12.003

Jiaqi Wang , Enze Shi , Huawen Hu , Chong Ma , Yiheng Liu , Xuhui Wang , Yincheng Yao , Xuan Liu , Bao Ge , Shu Zhang

{"title":"Large language models for robotics: Opportunities, challenges, and perspectives","authors":"Jiaqi Wang , Enze Shi , Huawen Hu , Chong Ma , Yiheng Liu , Xuhui Wang , Yincheng Yao , Xuan Liu , Bao Ge , Shu Zhang","doi":"10.1016/j.jai.2024.12.003","DOIUrl":"10.1016/j.jai.2024.12.003","url":null,"abstract":"<div><div>Large language models (LLMs) have undergone significant expansion and have been increasingly integrated across various domains. Notably, in the realm of robot task planning, LLMs harness their advanced reasoning and language comprehension capabilities to formulate precise and efficient action plans based on natural language instructions. However, for embodied tasks, where robots interact with complex environments, text-only LLMs often face challenges due to a lack of compatibility with robotic visual perception. This study provides a comprehensive overview of the emerging integration of LLMs and multimodal LLMs into various robotic tasks. Additionally, we propose a framework that utilizes multimodal GPT-4V to enhance embodied task planning through the combination of natural language instructions and robot visual perceptions. Our results, based on diverse datasets, indicate that GPT-4V effectively enhances robot performance in embodied tasks. This extensive survey and evaluation of LLMs and multimodal LLMs across a variety of robotic tasks enriches the understanding of LLM-centric embodied intelligence and provides forward-looking insights towards bridging the gap in Human-Robot-Environment interaction.</div></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"4 1","pages":"Pages 52-64"},"PeriodicalIF":0.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143696747","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}

引用次数: 0

Welcoming the new spring, inspiring the future — New year’s greetings from Journal of Automation and Intelligence 迎新春，启未来——《自动化与智能学报》新年贺词

Journal of Automation and Intelligence Pub Date : 2025-03-01 DOI: 10.1016/j.jai.2025.01.003

Yongduan Song (Editor-in-Chief)

引用次数: 0

Distributed algorithms for aggregative games with multiple uncertain Euler–Lagrange systems over switching networks 交换网络上多个不确定欧拉-拉格朗日系统聚集博弈的分布式算法

Journal of Automation and Intelligence Pub Date : 2025-03-01 DOI: 10.1016/j.jai.2024.12.006

Zhaocong Liu, Jie Huang

引用次数: 0

Saturation-tolerant prescribed control of MIMO nonlinear systems with actuator faults 带有执行器故障的多输入多输出非线性系统的容饱和规定控制

Journal of Automation and Intelligence Pub Date : 2025-03-01 DOI: 10.1016/j.jai.2024.09.002

Hao Lei , Ruihang Ji , Dongyu Li , Shuzhi Sam Ge

{"title":"Saturation-tolerant prescribed control of MIMO nonlinear systems with actuator faults","authors":"Hao Lei , Ruihang Ji , Dongyu Li , Shuzhi Sam Ge","doi":"10.1016/j.jai.2024.09.002","DOIUrl":"10.1016/j.jai.2024.09.002","url":null,"abstract":"<div><div>This paper addresses the tracking control problem of a class of multiple-input–multiple-output nonlinear systems subject to actuator faults. Achieving a balance between input saturation and performance constraints, rather than conducting isolated analyses, especially in the presence of frequently encountered unknown actuator faults, becomes an interesting yet challenging problem. First, to enhance the tracking performance, Tunnel Prescribed Performance (TPP) is proposed to provide narrow tunnel-shape constraints instead of the common over-relaxed trumpet-shape performance constraints. A pair of non-negative signals produced by an auxiliary system is then integrated into TPP, resulting in Saturation-tolerant Prescribed Performance (SPP) with flexible performance boundaries that account for input saturation situations. Namely, SPP can appropriately relax TPP when needed and decrease the conservatism of control design. With the help of SPP, our developed Saturation-tolerant Prescribed Control (SPC) guarantees finite-time convergence while satisfying both input saturation and performance constraints, even under serious actuator faults. Simulations are conducted to illustrate the effectiveness of the proposed SPC.</div></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"4 1","pages":"Pages 10-20"},"PeriodicalIF":0.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143696749","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}

引用次数: 0

Adaptive regulation-based Mutual Information Camouflage Poisoning Attack in Graph Neural Networks 基于自适应调节的图神经网络互信息伪装中毒攻击

Journal of Automation and Intelligence Pub Date : 2025-03-01 DOI: 10.1016/j.jai.2024.12.001

Jihui Yin , Taorui Yang , Yifei Sun , Jianzhi Gao , Jiangbo Lu , Zhi-Hui Zhan

{"title":"Adaptive regulation-based Mutual Information Camouflage Poisoning Attack in Graph Neural Networks","authors":"Jihui Yin , Taorui Yang , Yifei Sun , Jianzhi Gao , Jiangbo Lu , Zhi-Hui Zhan","doi":"10.1016/j.jai.2024.12.001","DOIUrl":"10.1016/j.jai.2024.12.001","url":null,"abstract":"<div><div>Studies show that Graph Neural Networks (GNNs) are susceptible to minor perturbations. Therefore, analyzing adversarial attacks on GNNs is crucial in current research. Previous studies used Generative Adversarial Networks to generate a set of fake nodes, injecting them into a clean GNNs to poison the graph structure and evaluate the robustness of GNNs. In the attack process, the computation of new node connections and the attack loss are independent, which affects the attack on the GNN. To improve this, a Fake Node Camouflage Attack based on Mutual Information (FNCAMI) algorithm is proposed. By incorporating Mutual Information (MI) loss, the distribution of nodes injected into the GNNs become more similar to the original nodes, achieving better attack results. Since the loss ratios of GNNs and MI affect performance, we also design an adaptive weighting method. By adjusting the loss weights in real-time through rate changes, larger loss values are obtained, eliminating local optima. The feasibility, effectiveness, and stealthiness of this algorithm are validated on four real datasets. Additionally, we use both global and targeted attacks to test the algorithm’s performance. Comparisons with baseline attack algorithms and ablation experiments demonstrate the efficiency of the FNCAMI algorithm.</div></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"4 1","pages":"Pages 21-28"},"PeriodicalIF":0.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143696949","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}

引用次数: 0

Global prescribed performance control for lane-keeping of automated vehicles considering input saturation 考虑输入饱和的自动驾驶车辆车道保持全局预定性能控制

Journal of Automation and Intelligence Pub Date : 2025-03-01 DOI: 10.1016/j.jai.2024.12.004

Zhibang Si , Yujuan Wang , Qing Chen , Manling Wu

引用次数: 0

Reinforcement learning with soft temporal logic constraints using limit-deterministic generalized Büchi automaton 基于极限确定性广义b<s:1> chi自动机的软时间逻辑约束强化学习

Journal of Automation and Intelligence Pub Date : 2025-03-01 DOI: 10.1016/j.jai.2024.12.005

Mingyu Cai , Zhangli Zhou , Lin Li , Shaoping Xiao , Zhen Kan

{"title":"Reinforcement learning with soft temporal logic constraints using limit-deterministic generalized Büchi automaton","authors":"Mingyu Cai , Zhangli Zhou , Lin Li , Shaoping Xiao , Zhen Kan","doi":"10.1016/j.jai.2024.12.005","DOIUrl":"10.1016/j.jai.2024.12.005","url":null,"abstract":"<div><div>This paper investigates control synthesis for motion planning under conditions of uncertainty, specifically in robot motion and environmental properties, which are modeled using a probabilistic labeled Markov decision process (PL-MDP). To address this, a model-free reinforcement learning (RL) approach is designed to produce a finite-memory control policy that meets complex tasks specified by linear temporal logic (LTL) formulas. Recognizing the presence of uncertainties and potentially conflicting objectives, this study centers on addressing infeasible LTL specifications. A relaxed LTL constraint enables the agent to adapt its motion plan, allowing for partial satisfaction by accounting for necessary task violations. Additionally, a new automaton structure is introduced to increase the density of accepting rewards, facilitating deterministic policy outcomes. The proposed RL framework is rigorously analyzed and prioritizes two key objectives: (1) satisfying the acceptance condition of the relaxed product MDP, and (2) minimizing long-term violation costs. Simulation and experimental results are presented to demonstrate the framework’s effectiveness and robustness.</div></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"4 1","pages":"Pages 39-51"},"PeriodicalIF":0.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143696951","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}

引用次数: 0

Enhancing the generalization capability of 2D array pointer networks through multiple teacher-forcing knowledge distillation 通过多次教师强制知识蒸馏提高二维数组指针网络的泛化能力

Journal of Automation and Intelligence Pub Date : 2025-03-01 DOI: 10.1016/j.jai.2024.12.007

Qidong Liu , Xin Shen , Chaoyue Liu , Dong Chen , Xin Zhou , Mingliang Xu

{"title":"Enhancing the generalization capability of 2D array pointer networks through multiple teacher-forcing knowledge distillation","authors":"Qidong Liu , Xin Shen , Chaoyue Liu , Dong Chen , Xin Zhou , Mingliang Xu","doi":"10.1016/j.jai.2024.12.007","DOIUrl":"10.1016/j.jai.2024.12.007","url":null,"abstract":"<div><div>The Heterogeneous Capacitated Vehicle Routing Problem (HCVRP), which involves efficiently routing vehicles with diverse capacities to fulfill various customer demands at minimal cost, poses an NP-hard challenge in combinatorial optimization. Recently, reinforcement learning approaches such as 2D Array Pointer Networks (2D-Ptr) have demonstrated remarkable speed in decision-making by modeling multiple agents’ concurrent choices as a sequence of consecutive actions. However, these learning-based models often struggle with generalization, meaning they cannot seamlessly adapt to new scenarios with varying numbers of vehicles or customers without retraining. Inspired by the potential of multi-teacher knowledge distillation to harness diverse knowledge from multiple sources and craft a comprehensive student model, we propose to enhance the generalization capability of 2D-Ptr through Multiple Teacher-forcing Knowledge Distillation (MTKD). We initially train 12 unique 2D-Ptr models under various settings to serve as teacher models. Subsequently, we randomly sample a teacher model and a batch of problem instances, focusing on those where the chosen teacher performed best. This teacher model then solves these instances, generating high-reward action sequences to guide knowledge transfer to the student model. We conduct rigorous evaluations across four distinct datasets, each comprising four HCVRP instances of varying scales. Our empirical findings underscore the proposed method superiority over existing learning-based methods in terms of both computational efficiency and solution quality.</div></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"4 1","pages":"Pages 29-38"},"PeriodicalIF":0.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143696950","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}

引用次数: 0

Model predictive control for unprotected left-turn based on sequential convex programming 基于序列凸规划的无保护左转弯模型预测控制

Journal of Automation and Intelligence Pub Date : 2024-12-01 DOI: 10.1016/j.jai.2024.10.001

Changlong Hao, Yuan Zhang, Yuanqing Xia

引用次数: 0

Industry demand response in dispatch strategy for high-proportion renewable energy power system 高比例可再生能源发电系统调度策略中的行业需求响应

Journal of Automation and Intelligence Pub Date : 2024-12-01 DOI: 10.1016/j.jai.2024.08.002

Xinxin Long , Zhixian Ni , Yuanzheng Li , Tao Yang , Zhigang Zeng , Mohammad Shahidehpour , Tianyou Chai

{"title":"Industry demand response in dispatch strategy for high-proportion renewable energy power system","authors":"Xinxin Long , Zhixian Ni , Yuanzheng Li , Tao Yang , Zhigang Zeng , Mohammad Shahidehpour , Tianyou Chai","doi":"10.1016/j.jai.2024.08.002","DOIUrl":"10.1016/j.jai.2024.08.002","url":null,"abstract":"<div><div>On the power supply side, renewable energy (RE) is an important substitute to traditional energy, the effective utilization of which has become one of the major challenges in risk-constrained power system operations. This paper proposes a risk-based power dispatching strategy considering the demand response (DR) and RE utilization in the stochastic optimal scheduling of parallel manufacturing process (PMP) in industrial manufacturing enterprises (IME). First, the specific production behavior model of PMP is formulated to characterize the flexibility of power demand. Then, a two-step strategic model is proposed to comprehensively quantify multiple factors in the optimal scheduling of DR in PMP loads considering risk-based power system dispatch, thermal generators, wind power integration. Case studies are based on the modified IEEE 24-bus power system, which verify the effectiveness of the proposed strategy in optimally coordinating IME assets with generation resources for promoting the RE utilization, as well as the impacts of power transmission risk on decision performance.</div></div>","PeriodicalId":100755,"journal":{"name":"Journal of Automation and Intelligence","volume":"3 4","pages":"Pages 191-201"},"PeriodicalIF":0.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143142843","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}

引用次数: 0