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

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

Matrix decomposition-based parametrization and singularity-free adaptive control of MIMO nonlinear systems

引用

AUTOMATICA 2025年 174卷

作者： Li, Feifei Zhang, Yanjun Sun, Jian Beijing Inst Technol Sch Automat Beijing 100081 Peoples R China Beijing Inst Technol State Key Lab Autonomous Intelligent Unmanned Syst Beijing 100081 Peoples R China

This paper proposes a new matrix decomposition-based adaptive control scheme for multi-input and multi-output (MIMO) continuous-time uncertain nonlinear systems with arbitrary vector relative degrees. Novel matrix decomposition-based parametrization structures are constructed for parameter estimation, upon which singularity-free adaptive control laws with modified parameter update laws are formulated to ensure closed-loop stability and output tracking. state feedback and output feedback are addressed, respectively. The proposed adaptive control scheme exhibits the following characteristics when compared with the existing results: (i) it is applicable for control of a broader class of uncertain MIMO nonlinear systems with arbitrary vector relative degrees;(ii) it requires less knowledge of the uncertain control gain matrix, while still ensuring that the adaptive control law is always non-singular during the process of parameter adaptation;and (iii) it guarantees the desired system performance without involving transient or high-gain issues. The proposed adaptive control scheme is verified by a hypersonic vehicle model simulation. (c) 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.

关键词： Adaptive control Matrix decomposition MIMO nonlinear systems Output tracking Singularity-free

来源：评论

学校读者我要写书评

暂无评论

Multi-modal 6-DoF object pose tracking: integrating spatial cues with monocular RGB imagery

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2025年第2期16卷 1327-1340页

作者： Mei, Yunpeng Wang, Shuze Li, Zhuo Sun, Jian Wang, Gang Beijing Inst Technol State Key Lab Autonomous Intelligent Unmanned Syst Beijing 100081 Peoples R China Beijing Inst Technol Chongqing Innovat Ctr Chongqing 401120 Peoples R China

Accurate six degrees of freedom (6-DoF) pose estimation is crucial for robust visual perception in fields such as smart manufacturing. Traditional RGB-based methods, though widely used, often face difficulties in adapting to dynamic scenes, understanding contextual information, and capturing temporal variations effectively. To address these challenges, we introduce a novel multi-modal 6-DoF pose estimation framework. This framework uses RGB images as the primary input and integrates spatial cues, including keypoint heatmaps and affinity fields, through a spatially aligned approach inspired by the Trans-UNet architecture. Our multi-modal method enhances both contextual understanding and temporal consistency. Experimental results on the Objectron dataset demonstrate that our approach surpasses existing algorithms across most categories. Furthermore, real-world tests confirm the accuracy and practical applicability of our method for robotic tasks, such as precision grasping, highlighting its effectiveness for real-world applications.

关键词： 6-DoF pose estimation Multi-modal learning Spatial-temporal modeling

来源：评论

学校读者我要写书评

暂无评论

Invariant Ellipsoids Method for Homogeneous Leader-Following Consensus Control

引用

IEEE TRANSACTIONS ON CYBERNETICS 2025年第3期55卷 1323-1331页

作者： Wang, Siyuan Duan, Haibin Li, Min Polyakov, Andrey Zheng, Gang Beihang Univ State Key Lab Virtual Real Technol & Syst Beijing 100191 Peoples R China Beijing Inst Technol Natl Key Lab Autonomous Intelligent Unmanned Syst Beijing 100811 Peoples R China Univ Lille NRIA F-59000 Lille France

The invariant ellipsoid methodology focuses on minimizing the invariant/attractive set for a linear control system subjects to bounded external disturbances. In this note, the invariant ellipsoid methodology is adapted to multiagent systems (MASs) by leveraging the generalized homogeneous control. A necessary and sufficient condition for the optimal rejection of external disturbances using a homogeneous control protocol is presented. Compared to linear control protocols, the generalized homogeneous approach yields faster convergence and enhanced accuracy. Theoretical results are validated by the numerical simulations of the multiagent system comprised of unicycle mobile robots (UMRs).

关键词： Ellipsoids Vectors Laplace equations Eigenvalues and eigenfunctions Multi-agent systems Directed graphs Mobile robots Electronic mail Consensus control Virtual reality Generalized homogeneity invariant ellipsoid multiagent system (MAS) unicycle mobile robots (UMRs)

来源：评论

学校读者我要写书评

暂无评论

Data-Based Online Linear Quadratic Gaussian Control From Noisy Data

引用

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL 2025年第0期

作者： Wang, Linqi Liu, Wenjie Li, Yifei Sun, Jian Wang, Gang Beijing Inst Technol State Key Lab Autonomous Intelligent Unmanned Syst Beijing 100081 Peoples R China Chongqing Innovat Ctr Beijing Inst Technol Chongqing Peoples R China

This article addresses the online state estimation and control problems of unknown linear time-invariant systems subject to process and measurement noise. The solution is to design a finite-horizon linear quadratic Gaussian (LQG) controller from noisy data. To this end, relaxed data-based semi-definite programs (SDPs) are proposed, which enable us to construct a robust finite-horizon linear quadratic regulator (LQR) and a robust Kalman filter. Consequently, a robust data-driven finite-horizon LQG controller is designed. When bounded noise is considered, it is shown that the proposed data-driven controller ensures robust global exponential stability (RGES) of the filter and the input-to-state stability (ISS) of the closed-loop system under standard conditions. Finally, numerical examples are provided to demonstrate its effectiveness.

关键词： data-driven control finite-horizon linear quadratic Gaussian noisy data semi-definite program state estimation

来源：评论

学校读者我要写书评

暂无评论

Network Topology Optimization for Energy-Efficient Control

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2025年第1期12卷 423-432页

作者： Zhu, Qihui Chen, Shenwen Zhang, Jingbin Yan, Gang Du, Wenbo Beihang Univ Sch Elect & Informat Engn State Key Lab CNS ATM Beijing 100191 Peoples R China Tongji Univ Sch Phys Sci & Engn Shanghai 200092 Peoples R China Tongji Univ Natl Key Lab Autonomous Intelligent Unmanned Syst Shanghai 200092 Peoples R China

Controlling the dynamics of complex networks with only a few driver nodes is a significant objective for system control. However, the energy required for control becomes prohibitively large when the fraction of driver nodes is small. Previous methods to reduce control energy have mainly focused on increasing the number or altering the placement of driver nodes. In this paper, a novel approach is proposed to reduce control energy by rewiring networks while keeping the number of driver nodes unchanged. We model network rewiring to an optimization problem and develop a memetic algorithm to solve it accurately and efficiently. Specifically, we introduce a connectivity-preserving crossover operator to avoid searching in invalid solution space and design a local search operator to accelerate the convergence of the algorithm according to the network heterogeneity. Experimental results on both synthetic networks and real networks demonstrate the effectiveness of the proposed approach. Notably, our findings reveal that networks with low control energy tend to exhibit a acore-chaina structure, where control nodes and high-weight edges form a densely connected core, while other nodes and edges form independent chains connected to the core's boundaries. We further analyze the statistical description and formation mechanism of this structure.

关键词： Controllability Optimization Complex networks Biological cells Aerospace electronics Memetics Costs Convergence Transportation Control theory Combinatorial optimization network controllability control energy K-core decomposition

来源：评论

学校读者我要写书评

暂无评论

state Estimation With Nonlinear Inequality Constraints for Small Celestial Body Flexible Landing

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC systems 2025年第2期61卷 4155-4167页

作者： Cui, Pingyuan Chen, Zelong Ge, Dantong Zhu, Shengying Cui, Shisheng Beijing Inst Technol Sch Aerosp Engn Beijing 100081 Peoples R China Beijing Inst Technol Minist Ind & Informat Technol Key Lab Autonomous Nav Control Deep Space Explorat Beijing 100081 Peoples R China Beijing Inst Technol Sch Automat Beijing 100081 Peoples R China Beijing Inst Technol State Key Lab Autonomous Intelligent Unmanned Syst Beijing 100081 Peoples R China

Compared to rigid landers, a flexible lander can reduce the landing risks in small celestial body missions by taking advantage of its soft structure. In this article, we focus on the autonomous navigation problem of the flexible lander. Particularly, we consider the utilization of the additional information provided by the inherent state constraints of the landing system, i.e., the flexible deformation constraints, into the design of the navigation filter. To involve such nonlinear inequality constraints, we develop a constrained filtering algorithm with theoretically guaranteed performance. By exploiting the geometrical relationship between the state estimates and the constraint region, we establish the estimation refinement theorem. This theorem presents the sufficient condition for improving estimation accuracy through the inclusion of constraints. Guided by this theorem, we devise a constrained filter where a maximum margin separating hyperplane is optimized to refine the state estimate. Further, we demonstrate that the constrained estimation error is exponentially bounded. At last, we validate the proposed filter through a 433 Eros-based flexible landing simulation.

关键词： Deformation Navigation Information filters Optical filters Estimation error autonomous robots Surface topography state estimation Filtering theory Filtering algorithms autonomous navigation estimation refinement theorem flexible landing inequality constraints stability of nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Cooperative spheroidal coverage control of multi-agent systems in 3D non-convex environments☆

引用

AUTOMATICA 2025年 176卷

作者： Zou, Jiayu Zhang, Hai-Tao Xing, Ning Liu, Xingjian Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Engn Res Ctr Autonomous Intelligent Unmanned Syst MOE Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol State Key Lab Intelligent Mfg Equipment & Technol Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Inst Artificial Intelligence Wuhan 430074 Peoples R China

The optimal configuration of multi-agent systems (MASs) has long been a challenging task to fulfill abundant three-dimensional (3D) non-convex coverage operations. This brief proposes a spheroidal coverage control scheme, where a spheroidal partition protocol is designed with a distributed estimator to ensure an equitable workload in each sub-region. Afterwards, a distributed control law is developed to asymptotically deploy each agent to the associated optimal configuration. Significantly, the analytical challenge of the present design lies in the convergence analysis of the three-level cascading systems induced by the proposed spheroidal partition protocol. Finally, numerical simulation is conducted to verify the effectiveness of the present spheroidal coverage control method. (c) 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.

关键词： Multi-agent systems Collaborative systems Networked control systems autonomous systems

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：