检索结果-内蒙古大学图书馆

2018 International Conference on Electrical Engineering, Control and Robotics, EECR 2018

作者： Zhang, Jinging Ruan, Xiaogang Dong, Pengfei Zhou, Jing Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing100124 China

The traditional SLAM based on RBPF has the problem of constructing high-precision map which requires large amounts of particles to make the calculation complexity and the phenomenon of particle depletion caused by particle degradation. Aiming at these problems, an improved RBPF particle filter based on adaptive bacterial foraging optimization algorithm and adaptive resampling is proposed for mobile robot SLAM problem. Firstly, the introduction of adaptive bacterial foraging algorithm to RBPF making the distribution of particles before resampling closer to the real situation. Then use the adaptive resampling method makes the newly generated particles closer to the real movement, thereby increasing the robot position estimation accuracy and map creation accuracy. The experimental results show that this method can improve the practicability of the system, reduce the computational complexity, improve the operation speed and get more effective particles while guaranteeing the accuracy of the grid map. © The Authors, published by EDP Sciences, 2018.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Feature selection method based on maximum information coefficient and its application in wastewater treatment processes

Feature selection method based on maximum information coeffi...

引用

2021 China Automation Congress, CAC 2021

作者： Wang, Congcong Chai, Wei Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing100124 China

ISBN: (纸本)9781665426473

High-dimensional data are widely present in machine learning tasks, and various dimensionality reduction methods have emerged to improve model training speed and avoid dimensionality catastrophe. Filter-based feature selection methods are favored for their fast processing speed and lack of dependence on model structure. A filtered feature selection method that combines the maximum information coefficient (MIC) with the feature selection framework of redundancy coefficient gradual up (RCGU) is proposed, and the attention mechanism is introduced into it. The method is verified to be effective in eliminating irrelevant variables and reducing redundant variables through Friedman numerical experiment. Finally, the proposed method is successfully applied to the selection of auxiliary variables for the soft measurement model used in a wastewater treatment plant, and the variables selected by this method improve prediction performance of the model in comparison with other feature selection methods. © 2021 IEEE

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Obstacle avoidance navigation method for robot based on deep reinforcement learning 6

Obstacle avoidance navigation method for robot based on deep...

引用

6th IEEE Information Technology and Mechatronics Engineering Conference, ITOEC 2022

作者： Ruan, Xiaogang Lin, Chenliang Huang, Jing Li, Yufan Beijing University of Technology Faculty of Information Technology Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing100124 China

ISBN: (纸本)9781665431859

Aiming at the navigation problem of mobile robots indoor environment, the traditional navigation algorithm based on D3QN has some problems such as sparse reward and slow training speed of the neural network. This paper proposes a deep reinforcement learning Algorithm (LN-D3QN) based on the D3QN network to realize collision-free autonomous navigation of mobile robots. To improve the efficiency of mobile robot learning and exploration, the Vision Sensor is used to acquire the input data from the environment, and the layer normalization method is used to normalize the input data. An improved reward function is designed, which improves the reward value of the algorithm, optimizes the state space, and alleviates the problem of sparse reward to some extent. The data is stored in a priority experience replay pool, and the network is trained using small batches of data. In addition, we evaluate our method by experiment related to indoor navigation. The experiments show that the robot trained by the improved D3QN algorithm can adapt to the unknown environment more quickly than the basic D3QN algorithm. The network's convergence speed is also improved, and it can complete the obstacle avoidance navigation task more efficiently. © 2022 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Hardware Implementation of On-Chip Learning Neural Network on FPGA 42

Hardware Implementation of On-Chip Learning Neural Network o...

引用

42nd Chinese Control Conference, CCC 2023

作者： Bi, Lanyue Zhu, Xiaoqing Ruan, Xiaogang Nan, Borui Beijing University of Technology Faculty of Information Technology Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing100124 China

ISBN: (纸本)9789887581543

Animals achieve precise locomotion through learning and practice, and many scholars are investigating how animals acquire new skills. Deep Reinforcement Learning (DRL) is often employed in skill learning and locomotion in robotics. However, the relationship between the learning process and neural networks or DRL remains unclear. In this paper, we propose a framework of backpropagation (BP) network based on matrix multiplication, which is implemented and visualized on a Field Programmable Gate Array (FPGA). This allows us to track changes in each neuron by analyzing nonlinear signals. By considering each register in the FPGA as a neuron, we can plot the weights of joints, which provides insights into the learning rules. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Soft-sensors Based on Gaussian Process Regression for Wastewater Treatment Plants 11

Soft-sensors Based on Gaussian Process Regression for Wastew...

引用

11th IEEE Data Driven Control and Learning systems Conference, DDCLS 2022

作者： Liu, Tong Chai, Wei Wang, Congcong Beijing University of Technology Faculty of Information Technology Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing100124 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

For wastewater treatment plants, a large number of process variables are demanded to monitor the operation of the system. Given the problem that some key water quality variables are difficult to get in real-time, a soft-sensor technology is devised to get the value of these variables. For a soft-sensor model, choosing the appropriate input variables will have a great impact on its performance. In this paper, automatic relevance determination (ARD) method which based on Gaussian process regression (GPR) is proposed to select the appropriate input variables. The ARD method considers the nonlinear mapping relationship from input variables to the output variable. Moreover, the wastewater treatment plant is modeled by GPR, which requires fewer model parameters and can give a confidence interval. Finally, an example of the wastewater treatment plant is used to prove the effectiveness of the method. © 2022 IEEE.

关键词： Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

Dynamic modeling of a cubical robot balancing on its corner 3

Dynamic modeling of a cubical robot balancing on its corner

引用

3rd International Conference on Mechanical, Electronic and Information Technology Engineering, ICMITE 2017

作者： Chen, Zhigang Ruan, Xiaogang Li, Yuan Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing100124 China

Aiming at the problem of self-balancing control of a cubical robot, this paper makes a research on the dynamic modeling of the cubical robot balancing on its corner. Using the prototype of cubical robot we built as the research object, the dynamic model is derived with Lagrangian method on foundation of analysis of coordinate transformation relation of cubical robot. The correctness of the model is verified in theory by numerical simulation. The controller, designed based on reaction torque characteristic of inertia wheels, is used in balance control of the cubical robot. The effectiveness of the controller is verified again with the obtained expect effect. The dynamic model developed and controller can provide a base for further study of balance control of a cubical robot. © The Authors, published by EDP Sciences, 2017.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Trot Gait Control for Unstructured Terrain of Quadruped Robots Based on VMC 42

Trot Gait Control for Unstructured Terrain of Quadruped Robo...

引用

42nd Chinese Control Conference, CCC 2023

作者： Nan, Borui Zhu, Xiaoqing Ruan, Xiaogang Bi, Lanyue Beijing University of Technology Faculty of Information Technology Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing100124 China

ISBN: (纸本)9789887581543

Legged robots possess redundant degrees of freedom and multiple footholds, making them highly promising for applications in disaster rescue, material transportation, and planet exploration. However, most previous studies have focused on continuous terrains, whereas walking in unstructured terrains such as plum-blossom piles present higher demands on robot posture control. This paper proposes a quadrupedal robot for gait control during walking in plum-blossom piles. The overall control process of the method is presented, followed by an analysis of the gait control of the quadruped robot. This includes the use of a PD controller to simulate the spring damping effect, the stability control of the robot's body through control target decomposition, and the gait control of individual legs using Jacques' matrix support phase control, combined with trajectory control to complete the swing phase of gait control. Additionally, an acceleration function is introduced to provide a buffering effect for posture adjustments of the quadruped robot. The proposed approach is evaluated using Webots simulation software, including simulation settings, results, and their interpretation. The results demonstrate the successful realization of motion control in complex terrains. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Piles

来源：评论

学校读者我要写书评

暂无评论

A Novel Multi-Objective Non-Dominated Sorting Beluga Whale Optimization Algorithm for WFGD Process 13

A Novel Multi-Objective Non-Dominated Sorting Beluga Whale O...

引用

13th IEEE Data Driven Control and Learning systems Conference, DDCLS 2024

作者： Xu, Junheng Wang, Kang Li, Xiaoli Beijing University of Technology Faculty of Information Technology Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing100124 China

ISBN: (纸本)9798350361674

The operation of coal-fired power plants emits a significant amount of SO2, causing a considerable environmental challenge. Wet flue gas desulfurization (WFGD) is the mostly used desulfurization method in current practice for address this issue, however, the simultaneous optimization of desulfurization efficiency and cost remains challenging. Aiming to achieve optimal performance and reduce the computational complexity, this paper proposes a novel multi-objective non-dominated sorting beluga whale optimization (NSBWO) algorithm to concurrently optimize desulfurization efficiency and cost. Derived from the NSGA-II framework, the NSBWO algorithm adopts the beluga whale algorithm to generate offspring instead of the conventional genetic algorithm used in the original algorithm. This modification alleviates the concerns about performance dependence on user-defined parameters, enhancing its performance in multi-objective optimization. Experimental results demonstrate that, compared to classical algorithms, NSBWO exhibits superior overall performance and faster convergence speed. Finally, the algorithm is applied to real-world data sourced from the flue gas desulfurization system of a 1000MW coal-fired power plant unit. The obtained results validate the algorithm's effectiveness in optimizing both the efficiency and cost of the wet flue gas desulfurization system. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Policy iteration-based adaptive optimal control for Markov jump systems: a transition-probability-free asynchronous approach

引用

Science China(Information Sciences) 2024年第11期67卷 363-364页

作者： Weidi CHENG Chengcheng REN Shuping HE Changyin SUN Key Laboratory of Intelligent Computing and Signal Processing (Ministry of Education) School of Electrical Engineering and Automation Anhui University Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and Automation Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Engineering Research Center of Autonomous Unmanned System Technology (Ministry of Education) School of Artificial Intelligence Anhui University

The controller and filter design problems of Markov jump systems(MJSs) have gained significant attention over the past few decades. These studies include various aspects,including stochastic stabilization [1], optimal tracking control [2], and dissipative filter design [3]. Although numerous publications address the optimal controller design for MJSs, the issue of hidden MJSs, particularly those with mismatched jumping modes between the system and the controller, has rarely been explored.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Self-alignment for strapdown INS using real-time adaptive filter 7

Self-alignment for strapdown INS using real-time adaptive fi...

引用

7th IEEE Chinese Guidance, Navigation and Control Conference, CGNCC 2016

作者： Jian, Zhao Fu-Jun, Pei Hong-Yun, Liu Beijing Key Laboratory of Computational Intelligence and Intelligent System School of Electronic Information and Control Engineering Beijing University of Technology 100124 China

ISBN: (纸本)9781467383189

As it is difficult to get an accurate mathematical noise model under various dynamic interference conditions, Strap-down Inertial Navigation system (SINS) was difficult to realize self-alignment. Although the fuzzy adaptive Kalman filter can be used to realize the SINS self-alignment, the algorithm complexity is high and the error term is unstable. To solve this problem, a novel self-alignment method using real-time adaptive filter was developed in this paper. This method is based on the theory of fuzzy adaptive adjustment and used the filter stability as the criterion. The exponential function was used to replace the fuzzy inference calculation, which eliminated the complex process of fuzzy, fuzzy inference and de-fuzzy. The stability and accuracy of the adaptive filter was also improved. Finally, the simulation process was used to test the algorithm of this method, and the results demonstrated that the self-alignment using real-time adaptive filter method reduced the complexity of the algorithm and had better stability and alignment accuracy. © 2016 IEEE.

关键词： Adaptive filters

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：