检索结果-内蒙古大学图书馆

第41届中国控制会议

作者： Junjie Fu Jian Sun Gang Wang Key Lab of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Deep neural networks(DNNs) have achieved remarkable success in diverse ***,it has been demonstrated that DNNs are very vulnerable to adversarial examples even in black-box settings.A large number of black-box attack methods have been proposed to in the ***,those methods usually suffer from low success rates and large query counts,which cannot fully satisfy practical *** this paper,we propose a hybrid attack method which trains meta adversarial perturbations(MAPs) on surrogate models and performs black-box attacks by estimating gradients of the *** method uses the meta adversarial perturbation as an initialization and subsequently trains any black-box attack method for several ***,the MAPs enjoy favorable transferability and universality,in the sense that they can be employed to boost performance of other black-box adversarial attack *** experiments demonstrate that our method can not only improve the attack success rates,but also reduces the number of queries compared to other methods.

关键词： Deep neural networks adversarial examples black-box attack meta adversarial perturbation transferability

来源：评论

学校读者我要写书评

暂无评论

Target tracking trajectory generation for quadrotors in static complex environments 4

Target tracking trajectory generation for quadrotors in stat...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Ji, Yang School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex System Beijing100081 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

This paper mainly focuses on the problem of target tracking trajectory generation for quadrotors in static complex environments. In this paper, a trajectory planning framework is proposed that can be used to address the occlusion problem caused by obstacles in target tracking situations. The main innovations are: First, a visibility function is introduced that is constructed based on a signed Euclidean distance field (ESDF) map. Based on this function, the favorable view direction is derived to track the target distinctly. Second, the distance between the target and chaser is optimized as one of the cost functions, resulting in a smooth and comfortable distance between them. Finally, the effectiveness of the algorithm is verified on the Rviz platform. © 2022 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Small-scale intersection scan model for UGV in urban environment

Small-scale intersection scan model for UGV in urban environ...

引用

2017 American control Conference, ACC 2017

作者： Yang, Yi Hao, Li Zhu, Hao Ningyi, Lyu Wenjie, Song School of Automation State Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9781509059928

Intersection detection is a critical capacity for an Unmanned Ground Vehicle (UGV) to drive safely in structured urban environment. Large-scale intersections stamped on maps have plenty of features for detection while some unmapped small-scale urban intersections are hard to be identified. In this paper, we propose a novel intersection detection method conducted on the basis of Hidden Markov Model (HMM). This method is based on the intersection scan model to obtain the traversable directions to classify the intersection. The scan model is effective in dealing with both LIDAR and visual data. Combination of the scan model and the HMM can accurately estimate the traversable directions in consideration of both real-time and historic data. Results from simulations and real-world experiments have shown the functionality of the presented approach. © 2017 American Automatic control Council (AACC).

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

UAV-aided Large-scale Map Building and Road Extraction for UGV 7

UAV-aided Large-scale Map Building and Road Extraction for U...

引用

7th IEEE Annual International Conference on CYBER Technology in Automation, control, and intelligent systems, CYBER 2017

作者： Meiling, Wang Huachao, Yu Guoqiang, Feng Yi, Yang Yafeng, Li Tong, Liu School of Automation Beijing Institute of Technology State Key Laboratory of Complex System Intelligent Control and Decision Beijing100081 China

ISBN: (纸本)9781538604892

Due to the limited visual field of UGV, it is difficult to detect the accessible zone in a wide range of area in real time. This paper proposes a UAV-aided autonomous road network construction method where roads are previously unknown for UGV navigation. First, SIFT and RANSAC algorithms are applied to obtain the homography of UAV sequential images, through which these images are stitched to a large-scale map. Next, least square fitting algorithm and RDP algorithm are applied to extract initial road area and then obtain road network suitable for UGV navigation by topological processing and skeleton extraction. The experiments show that this UAV-aided method is effective in generating a large-scale road network map for UGV driving through unknown environment without human intervention. © 2017 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

A Dual-Motor Joint Model for Humanoid Robots

A Dual-Motor Joint Model for Humanoid Robots

引用

第25届中国控制与决策会议

作者： Jingtao Xue Xiaopeng Chen Ye Tian Zhangguo Yu Fei Meng Qiang Huang IRI School of Mechatronic Engineering Beijing Institute of Technology Key Laboratory of Biomimetic Robots and Systems Ministry of Education Key Laboratory of Intelligent Control and Decision of Complex System

ISBN: (纸本)9781467355339

To make humanoid robots walking fast, it's important to improve driving force of their leg joints. Usually, each joint of humanoid robots is driven by a single motor. Dual-motor joint, on the other hand, is one of the candidate solutions to meet the power requirement needed for fast walking. This paper proposed a new dual-motor control model. In the model, two motors are treated as a single control plant instead of two parallel control plants. With the usage of current distributor, the control model can pump different current to each motor freely so as to eliminate the unbalance of the load imposed on each motor. Simulation and experiment show that the proposed model works well under high joint load and it can be used on a fast walking humanoid robot.

关键词： Humanoid robot, dual motor, control model

来源：评论

学校读者我要写书评

暂无评论

Sliding angle reconstruction and robust lateral control of autonomous vehicles in presence of lateral disturbance

Sliding angle reconstruction and robust lateral control of a...

引用

2009 IEEE/RSJ International Conference on intelligent Robots and systems, IROS 2009

作者： Hao, Fang Lihua, Dou Jie, Chen Education Ministry Key Laboratory of Complex System Intelligent Control and Decision School of Automation Beijing Institute of Technology 100081 Beijing China

ISBN: (纸本)9781424438044

In this paper the problem of path following control of autonomous vehicles subject to sliding is addressed. First a kinematic model is built which takes sliding effects into account by introducing two additional tire sliding angles. Since the tire sliding angles cannot be directly measured by sensors, an adaptive robust Luenberger observer is designed. With this observer, the tire cornering stiffness instead of the sliding angles is identified in presence of time-varying lateral disturbance. The Lyapunov stability theory guarantees that the estimated cornering stiffness would converge to a neighborhood of the real value when control inputs excitated the system persistently. But due to the existence of the lateral disturbance which causes loss of accuracy of the sliding angle reconstruction, the previously designed anti-sliding controller whose effectiveness completely depends on the estimation of the sliding angles cannot yield satisfactory results. To overcome this problem a tire-oriented kinematic model is built in which the inaccuracy of the sliding angle reconstruction is modeled in form of additive disturbances to the kinematic model. By transforming the tire-oriented kinematic model into a perturbed chained system, a sliding mode controller, which is robust to both the sliding effects and the negative effects of the lateral disturbance is designed with the help of the natural algebraic structure of the chained systems. Simulation results show that the proposed methods can provide accurate estimation of the sliding angles and guarantee high anti-sliding control accuracy even in presence of time-varying lateral disturbance. © 2009 IEEE.

关键词： Tires

来源：评论

学校读者我要写书评

暂无评论

Short-term PV generation system direct power prediction model on wavelet neural network and weather type clustering

Short-term PV generation system direct power prediction mode...

引用

2013 5th International Conference on intelligent Human-Machine systems and Cybernetics, IHMSC 2013

作者： Yang, Ying Dong, Lei School of Automation Beijing Institute of Technology China Key Laboratory of Complex System Intelligent Control and Decision Ministry of Education Beijing China

ISBN: (纸本)9780769550114

With the increase of the capacity of PV generated systems, how to eliminate the problem caused by the randomness of power output for photovoltaic system becomes more significant. Most of the existing photovoltaic prediction is Based on the solar radiation. However, it's difficult to implement in China due to insufficient solar radiation station available and poor forecasting performance. In addition, indirect forecasting cannot consider the factors related with PV system. A novel power forecasting model using historical power is proposed to solve the problems. Furthermore, in order to adapt sudden weather changes, the future weather type was recognized by using self-organizing feature map(SOM). Then, PV power generation in each weather type could be forecasted from its corresponding forecast network and the over fitting issue of single network model could be addressed. Wavelet neural network is combined with wavelet analysis and neural network. It is compatible with the good time-frequency property and good fault tolerant ability of neural network. Wavelet neural network can optimize the forecasting model. The experimental results indicate that the prediction has high precision and can be applied in stable operation of photovoltaic generation system. © 2013 IEEE.

关键词： Solar radiation

来源：评论

学校读者我要写书评

暂无评论

A Positioning Algorithm of Autonomous Car Based on Map-matching and Environmental Perception 33

A Positioning Algorithm of Autonomous Car Based on Map-match...

引用

第三十三届中国控制会议

作者： XU Qian WANG Meiling DU Zhifang ZHANG Yi School of Automation Beijing Institute of Technology Key Laboratory of Intelligent Control and Decision of Complex System Chongqing Jialing Huaguang Photoelectric Technology Co.Ltd.

ISBN: (纸本)9789881563842

Autonomous car is an important tool for transportation and military in the future,and its precise positioning is the basis of autonomous *** positioning algorithms based on map-matching for autonomous car make little use of environmental perception *** solve this problem,a positioning algorithm is proposed in this paper,which is based on map-matching and environmental perception for autonomous *** algorithm includes macroscopic road matching and microscopic precise *** for macroscopic road matching,the algorithm makes use of computational geometry to match the position of autonomous car to the corresponding road,based on GPS point and map information of the road *** for microscopic precise positioning,the algorithm makes use of the environmental perception,which is detected by the autonomous car to make precise *** road matching provides matching road to microscopic precise positioning,and microscopic precise positioning eliminates gross error produced in macroscopic road *** real car tests,the algorithm can match map quickly,improving the positioning precision with strong real-time.

关键词： Autonomous car,Map-matching,Environmental perception,Computational geometry

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of the Knowledge Base for Battlefield Task Management system 33

Design and Implementation of the Knowledge Base for Battlefi...

引用

第三十三届中国控制会议

作者： Zhang Jia Wang Xiang School of Automation Beijing Institute of Technology Key Laboratory of Complex System Intelligent Control and Decision (Beijing Institute of Technology) Ministry of Education

ISBN: (纸本)9781479947249

In order to reduce the operators on the battlefield, and obtain adequate knowledge and improve reaction speed to enhance combat efficiency, the paper builds a knowledge base of battlefield mission management system to manage a variety of required knowledge on the battlefield and supervise each mission profile. Knowledge is presented by production method and is reasoned by forward reasoning method. According to different levels of battlefield tasks, task links are used to organize knowledge. Take combat preparation mission profile as an example, we design every data sheet of the knowledge base. The knowledge base of the battlefield management system could enhance the reusability, sharing and timeliness of knowledge on the battlefield.

关键词： Battlefield Task Management Knowledge Base Task Links Mission Profile

来源：评论

学校读者我要写书评

暂无评论

Stabilization of Perturbed Continuous-Time systems Using Event-Triggered Model Predictive control

引用

IEEE Transactions on Cybernetics 2022年第5期52卷 4039-4051页

作者： Wang, Mengzhi Sun, Jian Chen, Jie Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China Beijing Institute of Technology Key Laboratory of Intelligent Control and Decision of Complex System Beijing100081 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China

In this article, event-triggered model predictive control (EMPC) of continuous-time nonlinear systems with bounded disturbances is studied. Two novel event-triggered control schemes are proposed. In the first strategy, an event-triggering condition, designed based on the state error between the actual system state and the optimal one, with an absolute threshold is considered. In the second strategy, an event-triggering condition with a mixed threshold is designed to further save the computational resources. The minimal interevent times of both event-triggered control schemes are obtained to avoid the Zeno behavior. Sufficient conditions of recursive feasibility for these two triggering strategies, which refer to the prediction horizon, the triggering level, and the disturbance bound, are obtained, respectively. Input-to-state practical stability (ISpS) of both event-triggered control systems is established without requiring the system state entering the terminal set in finite time, respectively. Finally, the numerical simulation shows the effectiveness of the proposed methods. © 2013 IEEE.

关键词： Model predictive control

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：