检索结果-内蒙古大学图书馆

作者： Zhu, Hao You, Qing Chen, Wenjie School of Automation Beijing Institute of Technology Beijing100081 China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing100081 China

A lot of vision systems have been embedded in devices around us, like mobile phones, vehicles and UAVs. Many of them still need interactive operations of human users. However, specifying accurate object information could be a challenging task due to video jitters caused by camera shakes and target motions. In this paper, we first collect practical hand drawn bounding boxes on real-life videos which are captured by hand-held cameras and UAV-based cameras. We give a deep look into human-computer interactive operations on unstable images. The collected data shows that human input suffers heavy deviations which are harmful to interaction accuracy. To achieve robust interactions on unstable platforms, we propose a target-focused video stabilization method which utilizes a proposal-based object detector and a tracking-based motion estimation component. This method starts with a single manual click and outputs stabilized video stream in which the specified target stays almost stationary. Our method removes not only camera jitters but also target motions simultaneously, therefore offering an comfortable environment for users to do further interactive operations. The experiments demonstrate that the proposed method effectively eliminates image vibrations and significantly increases human input accuracy. © Copyright 2018 The Institute of Electronics Information and Communication Engineers.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

CFSeRec: A Contrastive Framework for Sequential Recommendation 42

CFSeRec: A Contrastive Framework for Sequential Recommendati...

引用

42nd Chinese control Conference, CCC 2023

作者： Wang, Tong Dai, Yaping Shao, Shuai School of Automation Beijing Institute of Technology Beijing100081 China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing100081 China

ISBN: (纸本)9789887581543

In sequential recommender systems, the main problems are the long-tailed distribution of data and noise interference. A Contrastive Framework for Sequential Recommendation (CFSeRec) is proposed to solve these two problems respectively. Token shuffling and adversarial attack data augmentation methods are used in the framework to improve the quality and quantity of training data, so that the long-tailed problem is mitigated. Through the application of projection head method, the sequence representation becomes more general and robust, rather than just adapted to the task of contrastive learning. Therefore, the impact of noise on sequence recommender systems is effectively alleviated. Experiments on four public datasets show that CFSeRec achieves state-of-the-art performance in the metrics of hit ratio and normalized discounted cumulative gain, when comparing to the seven previous frameworks. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Flow-rate Characteristics Measurement of Regulators Based on the Pressure Response in an Isothermal Tank

引用

Chinese Journal of Mechanical Engineering 2009年第5期22卷 633-638页

作者： FAN Wei ZHANG Hongli WANG Tao PENG Guangzheng ONEYAMA Naotake Education Ministry Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology Beijing 100081 China School of Automation Beijing Institute of Technology Beijing 100081 China Electrical Engineering College Xinjiang University Urumchi 830046 China SMC Tsukuba Technical Center Ibaraki-ken 300-2493 Japan

Regulators are important components in pneumatic system, and their flow-rate characteristics are the key parameters for designers. According to the correlatively international standard and national standard of China, which describe the flow-rate characteristics measurement method of pneumatic regulators, the pressure and the flow are measured point by point, and then the flow-rate characteristics curve is plotted point to point. This method has some disadvantages, such as equipment complexity, much air consumption, and low efficiency. To settle the problems presented above, this paper puts forward a new high efficient and energy saving flow-rate characteristics measurement method of regulators, which is based on the pressure response when charging and discharging to an isothermal tank without any flow meters. The measurement principle, the system and the steps are introduced. And the tracking differentiator is used for the data processing of the pressure difference. Two typical kinds of regulators were experimentally investigated, and their flow-rate characteristics curves were obtained with the new and the conventional method, respectively. Comparatively, it＇s proved that this new method is feasible because it is not only able to meet the demand of the measurement precision, but also to save energy and improve efficiency. Compared to the conventional method, the new method takes only about 1/10 amount of time and consumes about only 1/30 amount of air. Hopefully it will be able to serve as an international standard of flow-rate characteristics measurement method of regulators.

关键词： regulator flow-rate characteristics isothermal tank charging and discharging once pressure response tracking differentiator energy saving and high efficiency

来源：评论

学校读者我要写书评

暂无评论

A Cell Potential and Motion Pattern Driven Multi-robot Coverage Path Planning Algorithm 14th

A Cell Potential and Motion Pattern Driven Multi-robot Cover...

引用

14th International Conference on Bio-inspired Computing: Theories and Applications, BIC-TA 2019

作者： Xu, Meng Xin, Bin Dou, Lihua Gao, Guanqiang School of Automation State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9789811534249

This paper proposes an intelligent "Cell Potential and Motion Pattern driven Coverage (CPMPC)" algorithm to solve a cooperative coverage path planning problem for multiple robots in two-dimensional target environment. The target environment is divided into cell areas according to the detection range of robot, and the cell matrix is given correspondingly. The values in the cell matrix are defined as cell potential, which represents the number of times each cell is detected by robots. The priority of the robot’s neighbor cell is called the motion pattern. At different moments, robots can choose within different motion patterns. Genetic algorithm (GA) is used to optimize the combination of motion patterns. By taking account obstacle avoidance and collision avoidance into consideration, the CPMPC algorithm adopts a double-layer choice strategy driven by cell potential and motion pattern to generate the next waypoint. Furthermore, this algorithm contains two optimal strategies: avoiding collision and jumping out of the detected area. Compared with the pattern-based genetic algorithm, the results obtained by us show that the CPMPC algorithm could solve the multi-robot coverage path planning (MCPP) problem effectively with guarantee of complete coverage, and improved makespan. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

The Optimal Duty Cycle Model-Predictive control of PMSM Used for Satellite Payload 1

引用

17th Annual Conference of China Electrotechnical Society, CES 2022

作者： Li, Jialin Chen, Zhen Hu, Hengzai Liu, Xiangdong Bao, Liang School of Automatic Beijing Institute of Technology Beijing100081 China Key Laboratory of Drive and Control of Servo Motion System Ministry of Industry and Information Technology Beijing100081 China State Key Laboratory of Intelligent Control and Decision for Complex System Beijing100081 China Beijing Aerospace Automatic Control Institute Beijing100854 China

ISBN: (数字)9789819904082

ISBN: (纸本)9789819904075

Model-predictive control is emerging as an advanced control strategy for its feature that the state variables can be predicted according to the math model of the control system. In the PMSM drive application, conventional model-predictive control strategy induces current ripple due to the fact that the optimal voltage vector always acts on the system for the whole control period. In order to restrain the current ripple, the idea of duty cycle control is taken into MPC by inserting a zero vector into the optimal non-zero vector and regulating the duty cycle of non-zero vector. In this paper, the optimal duty cycle FSC-MPC strategy based on two different principles is investigated. Principle A is that the estimation is equal to the reference at the end of control cycle, and principle B is that the area under trace of the estimation is equal to that of reference. The calculation of duty based on the two different principles and the flow chart of the strategy are introduced in detail. Finally, the effectiveness of the optimal duty cycle FSC-MPC is firstly verified by the simulation, and then verified by the experimental results, which is implemented on the PMSM driver of the DQ-1 satellite payload. © 2023, Beijing Paike Culture Commu. Co., Ltd.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Vehicle Motion Prediction at Intersections Based on the Turning Intention and Prior Trajectories Model

引用

自动化学报（英文版） 2021年第10期8卷 1657-1666页

作者： Ting Zhang Wenjie Song Mengyin Fu Yi Yang Meiling Wang State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of TechnologyBeijing 100081 Nanjing University of Science and Technology Nanjing 210014China

Intersections are quite important and complex traffic scenarios, where the future motion of surrounding vehicles is an indispensable reference factor for the decision-making or path planning of autonomous vehicles. Considering that the motion trajectory of a vehicle at an intersection partly obeys the statistical law of historical data once its driving intention is determined, this paper proposes a long short-term memory based (LSTM-based) framework that combines intention prediction and trajectory prediction together. First, we build an intersection prior trajectories model (IPTM) by clustering and statistically analyzing a large number of prior traffic flow trajectories. The prior trajectories model with fitted probabilistic density is used to approximate the distribution of the predicted trajectory, and also serves as a reference for credibility evaluation. Second, we conduct the intention prediction through another LSTM model and regard it as a crucial cue for a trajectory forecast at the early stage. Furthermore, the predicted intention is also a key that is associated with the prior trajectories model. The proposed framework is validated on two publically released datasets, next generation simulation (NGSIM) and INTERACTION. Compared with other prediction methods, our framework is able to sample a trajectory from the estimated distribution, with its accuracy improved by about 20％. Finally, the credibility evaluation, which is based on the prior trajectories model, makes the framework more practical in the real-world applications.

关键词： Autonomous vehicle intersection motion prediction prior trajectories model turning intention

来源：评论

学校读者我要写书评

暂无评论

An Efficient Restart-Enhanced Genetic Algorithm for the Coalition Formation Problem 1

引用

13th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2018

作者： Guo, Miao Xin, Bin Chen, Jie Wang, Yipeng School of Automation State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing100081 China

ISBN: (数字)9789811328268

ISBN: (纸本)9789811328251

In multi-agent system (MAS), the coalition formation (CF) is an important problem focusing on allocating agents to different tasks. In this paper, the single-task single-coalition (STSC) formation problem is considered. The mathematical model of the STSC problem is built with the objective of minimizing the total cost with the ability constraint. Besides, an efficient restart-enhanced genetic algorithm (REGA) is designed to solve the STSC problem. Furthermore, this paper constructs a comparison experiment, employing a random sampling method, an estimation of distribution algorithm and a genetic algorithm without restart strategy as competitors. The results of statistical analysis by the Wilcoxon’s rank-sum test demonstrate that the designed REGA performs better than its competitors in solving the STSC cases of different scales. © 2018, Springer Nature Singapore Pte Ltd.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

An efficient decision and planning method for high speed autonomous driving in dynamic environment 28

An efficient decision and planning method for high speed aut...

引用

28th IEEE intelligent Vehicles Symposium, IV 2017

作者： Zhang, Kai Fu, Mengyin Yang, Yi Shang, Songtian Wang, Meiling State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institution of Technology Beijing 100081 China

ISBN: (纸本)9781509048052

This paper describes an improved decision and planning algorithm based on our previously proposed methods for unmanned ground vehicle (UGV). The new method can be applied to UGV driving both in structured environment and unstructured environment. In the improved method, the prospect of planning is extended from 40m to 100m for safe driving at high speed and some piecewise linear speed functions are designed for the new prospect. After this improvement our UGV now can drive at a maximum speed of 60km/h rather than 40km/h while avoiding obstacles safely. Besides, a velocity feedforward control is added to make the UGV overtake other cars driving at about 25km/h on the road. At last, the collision detection algorithm is improved to make the lane changing maneuver safer. The proposed decision and planning algorithm is implemented both on our old Polaris all terrain vehicle (ATV) and new FAW-H7 car, which exhibited good performance on Across Dangers & Obstacles 2016, Tahe, China and Future Challenge 2016, Changshu, China, respectively. © 2017 IEEE.

关键词： Planning Automobiles Laser radar Roads Feedforward neural networks Collision avoidance Cameras

来源：评论

学校读者我要写书评

暂无评论

Policy iteration based Q-learning for linear nonzero-sum quadratic differential games

引用

Science China(Information Sciences) 2019年第5期62卷 195-213页

作者： Xinxing LI Zhihong PENG Li LIANG Wenzhong ZHA School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex System Information Science Academy China Electronics Technology Group Corporation

In this paper, a policy iteration-based Q-learning algorithm is proposed to solve infinite horizon linear nonzero-sum quadratic differential games with completely unknown dynamics. The Q-learning algorithm, which employs off-policy reinforcement learning(RL), can learn the Nash equilibrium and the corresponding value functions online, using the data sets generated by behavior policies. First, we prove equivalence between the proposed off-policy Q-learning algorithm and an offline PI algorithm by selecting specific initially admissible polices that can be learned online. Then, the convergence of the off-policy Qlearning algorithm is proved under a mild rank condition that can be easily met by injecting appropriate probing noises into behavior policies. The generated data sets can be repeatedly used during the learning process, which is computationally effective. The simulation results demonstrate the effectiveness of the proposed Q-learning algorithm.

关键词： adaptive dynamic programming ADP Q-learning reinforcement learning RL linear nonzerosum quadratic differential games policy iteration PI off-policy

来源：评论

学校读者我要写书评

暂无评论

Modified gain-based lower bounds computation for the real structured singular value 7

Modified gain-based lower bounds computation for the real st...

引用

7th International Symposium on Computational Intelligence and Industrial Applications, ISCIIA 2016

作者： Gao, Linjie Song, Zhuoyue Zhang, Xuenan Key Laboratory of Complex System Intelligent Control and Decision Ministry of Education of China China Beijing Institute of Technology No.5 South Venue of ZhongGuan Village Beijing100081 China

ISBN: (纸本)9784990534349

In this paper, a modified gain-based algorithm (GBA) is presented to calculate the lower bound for the real structured singular Value (μ) problem. The basic idea of GBA is reformulating the real μ problem into a related worst-case disturbance-error performance problem, then the standard lower bound algorithm for worst-case performance assessment is used for calculation of maximizer uncertainty which maximizes the disturbance-error gain, and next this maximizer uncertainty can be used to obtain the lower bound for real μ. In the initial gain-based algorithm previously suggested by Pete Seiler etal, the way disturbance inserted and the error pulled off is from one channel to one channel. In this proposed modified algorithm, the error signal is still pulled off from one channel, however, the disturbance is inserted into from a linear combination (summation) of all channels, hence the effect of signals from all channels are reflected into the error signal. Several test problems indicate that the modified gain-based algorithm has a better performance for pure real μ problems. © 2016, Fuji Technology Press. All rights reserved.

关键词： Errors

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：