检索结果-内蒙古大学图书馆

Embodied intelligence in RO/RO logistic terminal:autonomous intelligent transportation robot architecture

Science China(Information Sciences) 2025年第5期68卷 153-169页

作者： Yongkang XU Runjiao BAO Lin ZHANG Junzheng WANG Shoukun WANG School of Automation Beijing Institute of Technology National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology

In this paper, an autonomous intelligent transportation robot equipped with intelligent perception and autonomous planning modules is proposed to meet the requirements of roll-on/roll-off(RO/RO) logistics terminals for the autonomous transportation of various types of finished vehicles. Based on the robot operating system(ROS) framework and a modular design approach, the robot integrates several key components, including a visual perception module, an autonomous planning module, a motion control module, an execution module, and an energy module. First, an improved convex hull algorithm efficiently extracts point cloud data, enhancing the efficiency of point cloud processing and addressing the issue of excessive target data. Three different evaluation methods were employed to determine the optimal bounding box of the target vehicle and to obtain its pose state. Second, improved proximal policy optimization(PPO) and generalized advantage estimation(GAE) algorithms, which are utilized in this paper, were implemented to autonomously plan collisionfree trajectories for robots, facilitating their movement from an initial position to the target transportation location, and subsequently to the final placement position. Finally, physical experiments confirmed that the robot effectively mimics the three fundamental components of humanoid functionality: perception, cognition, and action, thus enabling autonomous and intelligent handling of complex vehicle transportation tasks. These demonstrations validate the feasibility and effectiveness of the proposed robot.

关键词： embodied intelligence transportation robot RO/RO logistic terminal detection autonomous planning

来源：评论

学校读者我要写书评

暂无评论

Coalition formation problem: a capability-centric analysis and general model

引用

Science China(Information Sciences) 2024年第11期67卷 180-193页

作者： Jie CHEN Miao GUO Bin XIN Qing WANG Shengyu LU Yipeng WANG Yulong DING School of Automation Beijing Institute of Technology National Key Lab of Autonomous Intelligent Unmanned Systems Department of Control Science and Engineering Tongji University

Coalition formation(CF) refers to reasonably organizing robots and/or humans to form coalitions that can satisfy mission requirements, attracting more and more attention in many fields such as multirobot collaboration and human-robot collaboration. However, the analysis on CF problems remains *** provide a valuable study reference for researchers interested in CF, this paper proposed a capabilitycentric analysis of the CF problem. The key problem elements of CF are firstly extracted by referencing the concepts of the 5W1H method. That is, objects(who) form coalitions(what) to accomplish missions(why) by aggregating capabilities(how) in a specific environment(where-when). Then, a multi-view analysis of these elements and their correlation in terms of capabilities is proposed through various logic diagrams, structure charts, etc. Finally, to facilitate a deeper understanding of capability-centric CF, a general mathematical model is constructed, demonstrating how the different concepts discussed in this analysis contribute to the overall model.

关键词： coalition formation capability aggregation capability metric mission requirement environmental effect

来源：评论

学校读者我要写书评

暂无评论

Inexact proximal gradient algorithm with random reshuffling for nonsmooth optimization

引用

Science China(Information Sciences) 2025年第1期68卷 219-237页

作者： Xia JIANG Yanyan FANG Xianlin ZENG Jian SUN Jie CHEN National Key Lab of Autonomous Intelligent Unmanned Systems School of AutomationBeijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center School of Electronic and Information Engineering Tongji University

Proximal gradient algorithms are popularly implemented to achieve convex optimization with nonsmooth regularization. Obtaining the exact solution of the proximal operator for nonsmooth regularization is challenging because errors exist in the computation of the gradient; consequently, the design and application of inexact proximal gradient algorithms have attracted considerable attention from researchers. This paper proposes computationally efficient basic and inexact proximal gradient descent algorithms with random reshuffling. The proposed stochastic algorithms take randomly reshuffled data to perform successive gradient descents and implement only one proximal operator after all data pass through. We prove the convergence results of the proposed proximal gradient algorithms under the sampling-without-replacement reshuffling *** computational errors exist in gradients and proximal operations, the proposed inexact proximal gradient algorithms can converge to an optimal solution neighborhood. Finally, we apply the proposed algorithms to compressed sensing and compare their efficiency with some popular algorithms.

关键词： proximal operator random reshuffling inexact computation compressed sensing nonsmooth optimization

来源：评论

学校读者我要写书评

暂无评论

MC-NeRF: Multi-Camera Neural Radiance Fields for Multi-Camera Image Acquisition systems

引用

IEEE Transactions on Visualization and Computer Graphics 2025年第5期31卷 2725-2735页

作者： Gao, Yu Su, Lutong Liang, Hao Yue, Yufeng Yang, Yi Fu, Mengyin Beijing Institute of Technology School of Automation Beijing China Beijing Institute of Technology National Key Lab of Autonomous Intelligent Unmanned Systems Beijing China

Neural Radiance Fields (NeRF) use multi-view images for 3D scene representation, demonstrating remarkable performance. As one of the primary sources of multi-view images, multi-camera systems encounter challenges such as varying intrinsic parameters and frequent pose changes. Most previous NeRF-based methods assume a unique camera and rarely consider multi-camera scenarios. Besides, some NeRF methods that can optimize intrinsic and extrinsic parameters still remain susceptible to suboptimal solutions when these parameters are poor initialized. In this paper, we propose MC-NeRF, a method for joint optimization of both intrinsic and extrinsic parameters alongside NeRF, allowing individual camera parameters for each image. First, we analyze the coupling issue that arises from the joint optimization between intrinsics and extrinsics, and propose a decoupling constraint utilizing auxiliary images. To further address the degenerate cases in the decoupling process, we introduce an efficient auxiliary image acquisition scheme to mitigate these effects. Furthermore, recognizing that most existing datasets are designed for a unique camera, we provided a new dataset that includes both simulated data and real-world data. Experiments demonstrate the effectiveness of our method in scenarios where each image corresponds to different camera parameters. Specifically, our approach outperforms the baselines favorably in terms of intrinsics estimation, extrinsics estimation, scale estimation, and rendering quality. The Code and supplementary materials are available at https://***/MC-NeRF. © 1995-2012 IEEE.

关键词： Volume rendering

来源：评论

学校读者我要写书评

暂无评论

Evolutionary state Estimation-Based Multi-Strategy Jellyfish Search Algorithm for Multi-UAV Cooperative Path Planning

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on intelligent Vehicles 2024年 1-19页

作者： Meng, Kai Chen, Chen Wu, Tongyu Xin, Bin Liang, Minmin Deng, Fang State Key Lab of Autonomous Intelligent Unmanned Systems School of Automation Beijing Institute of Technology Beijing China School of Materials Science and Engineering Beijing Institute of Technology Beijing China

Path planning is crucial for the successful mission execution of unmanned aerial vehicles (UAVs). However, planning feasible paths becomes challenging due to constraints imposed by complex environments and the inherent maneuverability of UAVs, particularly in large-scale scenarios involving multiple UAVs ( multi-UAV). This paper addresses the multi-UAV cooperative path planning problem, formulating it as a constrained optimization problem and proposing the evolutionary state estimation-based multi-strategy jellyfish search (ESE-MSJS) algorithm to search for high-quality paths. In the proposed algorithm, a switching framework based on evolutionary state estimation is constructed to prevent ineffective searches and enhance suitability for path planning. Within this framework, three distinct update modes are developed for each individual, enabling a more efficient and flexible selection of appropriate learning strategies. In addition, a neighborhood topology-based elite example learning strategy is employed to increase population diversity, and a best information guiding-driven adaptive scaling factor strategy exploits the surrounding space, strengthening local search capabilities. The Gaussian barebone mechanism is introduced to balance exploration and exploitation. To effectively cope with intricate constraints, a dynamic $\alpha$-level comparison strategy is incorporated into the individual update stage of the ESE-MSJS. Experimental results demonstrate that ESE-MSJS outperforms state-of-the-art algorithms regarding accuracy, feasibility, and stability, proving to be an effective method for multi-UAV cooperative path planning in complex environments. IEEE

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Adaptive PI Control Based Stability Margin Configuration of Aircraft Control systems with Unknown System Parameters and Time Delay

引用

Journal of systems Science & Complexity 2024年第4期37卷 1507-1525页

作者： ZHANG Zhibing ZHOU Dapeng WANG Yeguang GAO Wanxin ZHANG Yanjun AVIC Shenyang Aircraft Design and Research Institute Shenyang 110035China School of Automation Beijing Institute of TechnologyBeijing 100081China State Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of TechnologyBeijing 100081China

The stability margin is a vital indicator for assessing the safety level of aircraft control *** should maintain sufficient stability margin to ensure safety during flight,especially in the process of large maneuver *** stability margin is generally quantified by the Bode diagram,which strictly depends on the system parameters and the open-loop transfer ***,due to the uncertain flight environments,transmission delays of sensors and mode switchings,etc.,there exist large parameter and structure uncertainties in the aircraft control systems,which make it difficult to precisely configure the stability margin to the desired value by the usual control *** address this problem,an indirect adaptive control strategy is proposed in this paper,where an adaptive PI control law with the capability of self-configuration of stability margin is *** developed control law not only achieves stable time-varying command tracking in the time domain,but also is able to automatically configure the phase margin and gain margin in the frequency ***,the simulation of the one-degree-of-freedom roll rate control model of the air vehicle verifies the validity of the proposed control method.

关键词： Adaptive control aircraft control parameter uncertainty stability margin configuration

来源：评论

学校读者我要写书评

暂无评论

Data-driven consensus control of fully distributed event-triggered multi-agent systems

引用

Science China(Information Sciences) 2023年第5期66卷 147-161页

作者： Yifei LI Xin WANG Jian SUN Gang WANG Jie CHEN School of Automation Beijing Institute of Technology The State Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center Department of Control Science and Engineering Tongji University

This study investigates the consensus control issue in discrete-time linear multi-agent systems(MASs) using data-driven control under undirected communication networks. To alleviate the communication burden, an adaptive event-triggered control strategy involving only local information is proposed and a model-based stability condition is derived that guarantees the asymptotic consensus of MASs. Furthermore,a data-based consensus condition for unknown MASs is established by combining a data-based system representation with the model-based stability condition, using only pre-collected noisy input-state data instead of the accurate system information a priori. Specifically, both model-based and data-driven event-triggered controllers can be utilized without requiring any global information. The validity and correctness of the controllers and associated theoretical results are demonstrated via numerical simulations.

关键词： distributed control event-triggered control data-driven control discrete-time MASs

来源：评论

学校读者我要写书评

暂无评论

Event-triggered consensus control of heterogeneous multi-agent systems: model-and data-based approaches

引用

Science China(Information Sciences) 2023年第9期66卷 151-167页

作者： Xin WANG Jian SUN Fang DENG Gang WANG Jie CHEN School of Automation Beijing Institute of Technology National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology Chongqing Innovation Center Department of Control Science and Engineering Tongji University

This article addresses the model-and data-based event-triggered consensus of heterogeneous leader/follower multi-agent systems(MASs). A dynamic periodic transmission protocol is developed to alleviate the communication and computational burden, where the followers can interact locally with neighbors to approach the dynamics of the leader. Capitalizing on a discrete-time looped-functional, a model-based consensus condition for the closed-loop MASs is derived as linear matrix inequalities(LMIs), along with a design method for obtaining distributed event-triggered controllers and the associated triggering *** collecting noise-corrupted state-input measurements in offline open-loop experiments, a data-based leader/follower MAS representation is derived and employed to address the data-driven consensus control problem without explicit MAS models. This result is subsequently generalized to guarantee an H∞-consensus control performance. Finally, a simulation example is given to corroborate the efficiency of the proposed distributed triggering scheme and the data-driven consensus controller.

关键词： data-driven control multi-agent system consensus looped-functional LMI

来源：评论

学校读者我要写书评

暂无评论

A Triple Network Knowledge Learning Framework for Particle Swarm Optimization 13

A Triple Network Knowledge Learning Framework for Particle S...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Zhang, Zhao Wang, Lingda Chen, Chen School of Automation Beijing Institute of Technology National Key Lab of Autonomous Intelligent Unmanned Systems Beijing China

ISBN: (纸本)9798350308365

Evolutionary computing (EC), as a metaheuristic algorithm, is widely applied in optimization problems due to its effectiveness. During the optimization process of EC, a large amount of data will be generated, which contains rich information on the evolutionary process. Mining and utilizing these data can learn promising evolutionary knowledge to assist the EC algorithms in achieving more efficient evolution. First, we analyze in detail the key differences in collecting experience and guiding evolution between particle swarm optimization (PSO) and differential evolution (DE) in the existing knowledge learning framework. Then, we propose a triple network knowledge learning (TNKL) framework to mitigate the limitations and boost knowledge learning for PSO-based algorithms. In the TNKL framework, the successful evolution experience of the current particle, the historical best position, and the global best position are collected. Three neural networks learn different knowledge from these experiences and give appropriate evolution directions. The TNKL framework then comprehensively considers these directions according to the evolution stage to guide particle evolution. Finally, we integrate the TNKL framework with PSO and its state-of-the-art variants. The benchmark function experimental results verify the effectiveness and efficiency of the TNKL framework. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Deep Reinforcement Learning Tracking Algorithm Based on Task Decomposition 4

A Deep Reinforcement Learning Tracking Algorithm Based on Ta...

引用

4th International Conference on Industrial automation, Robotics and Control Engineering, IARCE 2024

作者： Yang, Kun Shen, Ao Xu, Nengwei Chen, Chen School of Automation Beijing Institute of Technology The National Key Lab of Autonomous Intelligent Unmanned Systems Beijing China

ISBN: (纸本)9798350380323

The active tracking technology of unmanned aerial vehicles (UAVs) has significant applications in fields such as military operations, environmental monitoring, disaster response and traffic management. However, two major challenges greatly affect the performance of UAV active tracking in practical scenarios: (1) The presence of uncertain obstacles in the environment, which may cause issues such as occlusion and collisions, severely affects the UAV's tracking ability. (2) The randomness of target behavior can result in degraded tracking algorithm performance or even tracking failures. To address these challenges, this paper proposes a novel deep reinforcement learning algorithm based on task decomposition, which integrates the advantages of traditional heuristic methods and machine learning approaches. Firstly, a parallel neural module network is designed to decompose the UAV active tracking task into two sub-tasks: obstacle avoidance and target tracking. This task decomposition effectively reduces the complexity of the problem. Secondly, a two-stage curriculum learning framework is introduced, where the policy network of the agent is gradually trained by adjusting random obstacles to enhance training efficiency and algorithm performance. Finally, multiple simulation environments with random targets and obstacles are constructed to validate the stability and robustness of the proposed algorithm, demonstrating that it can effectively achieve tracking and obstacle avoidance in unknown environments. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：