检索结果-内蒙古大学图书馆

Model-free design of stochastic lqr controller from reinforcement learning and primal-dual optimization perspective

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Man Qin, Jiahu Zheng, Wei Xing Wang, Yaonan Kang, Yu Department of Automation University of Science and Technology of China Hefei230027 China School of Computing Engineering and Mathematics Western Sydney University SydneyNSW2751 Australia College of Electrical and Information Engineering Hunan University Changsha410082 China National Engineering Laboratory for Robot Visual Perception and Control Technology Changsha410082 China

To further understand the underlying mechanism of various reinforcement learning (RL) algorithms and also to better use the optimization theory to make further progress in RL, many researchers begin to revisit the linear-quadratic regulator (LQR) problem, whose setting is simple and yet captures the characteristics of RL. Inspired by this, this work is concerned with the model-free design of stochastic LQR controller for linear systems subject to Gaussian noises, from the perspective of both RL and primal-dual optimization. From the RL perspective, we first develop a new model-free off-policy policy iteration (MF-OPPI) algorithm, in which the sampled data is repeatedly used for updating the policy to alleviate the data-hungry problem to some extent. We then provide a rigorous analysis for algorithm convergence by showing that the involved iterations are equivalent to the iterations in the classical policy iteration (PI) algorithm. From the perspective of optimization, we first reformulate the stochastic LQR problem at hand as a constrained non-convex optimization problem, which is shown to have strong duality. Then, to solve this non-convex optimization problem, we propose a model-based primal-dual (MBPD) algorithm based on the properties of the resulting Karush-Kuhn-Tucker (KKT) conditions. We also give a model-free implementation for the MB-PD algorithm by solving a transformed dual feasibility condition. More importantly, we show that the dual and primal update steps in the MB-PD algorithm can be interpreted as the policy evaluation and policy improvement steps in the PI algorithm, respectively. Finally, we provide one simulation example to show the performance of the proposed algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Stochastic systems

PL-VINS: Real-Time Monocular visual-Inertial SLAM with Point and Line Features

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Fu, Qiang Wang, Jialong Yu, Hongshan Ali, Islam Guo, Feng He, Yijia Zhang, Hong National Engineering Laboratory for Robot Visual Perception and Control Technology Hunan University China Department of Computing Science University of Alberta Canada Megvii Technology Beijing China

Leveraging line features to improve localization accuracy of point-based visual-inertial SLAM (VINS) is gaining interest as they provide additional constraints on scene structure. However, real-time performance when incorporating line features in VINS has not been addressed. This paper presents PL-VINS, a real-time and high-efficiency optimization-based monocular VINS method with point and line features, developed based on the state-of-the-art point-based VINS-Mono [1]. We observe that current works use the LSD [2] algorithm to extract line features;however, LSD is designed for scene shape representation instead of the pose estimation problem, which becomes the bottleneck for the real-time performance due to its high computational cost. In this paper, we modify the LSD algorithm by studying a hidden parameter tuning and length rejection strategy. The modified LSD algorithm can run at least three times as fast as LSD. Further, by representing space lines with the Plücker coordinates, the residual error in line estimation is modeled in terms of the point-to-line distance, which is then minimized by iteratively updating the minimum four-parameter orthonormal representation of the Plücker coordinates. Experiments in a public benchmark dataset show that the localization error of our method is 12-16% less than that of VINS-Mono at the same pose update frequency. The source code of our method is available at: https://***/cnqiangfu/PL-VINS. Copyright © 2020, The Authors. All rights reserved.

关键词： Iterative methods

Memory-augment convolutional Autoencoder for unsupervised pavement crack classification

学校读者我要写书评

暂无评论

Memory-augment convolutional Autoencoder for unsupervised pa...

Chinese Automation Congress (CAC)

作者： Tianyue Wu Hui Zhang Jiaxuan Liu Yurong Chen Junfei Yi Zouquan Zhang School of Electrical and Information Engineering Changsha University of Science and Technology Changsha China School of Robotics also with Visual Perception and Control Technology National Engineering Laboratory Hunan University Changsha China School of Electrical and Information Engineering Hunan University Changsha China

ISBN: (纸本)9781665426480

In urban construction, transportation system is an important part. However, the pavement cracks will occur because of using in long time and some external force collision, which has impacts on the safety and reliability of the whole transportation system. Therefore, it is necessary to detect the pavement cracks. The formation of pavement cracks is slow, and it is not concentrated on one place, so it is difficult to obtain enough images containing cracks to train. We propose a new pre-training method based on self-supervision study, which can obtain features closer to the target task from normal pavement images. In addition, we combine a memory-augment convolutional autoencoder and a hard-threshold module to improve the accuracy of the crack classification. Experiments conducted on the Mendeley Concrete crack dataset and Deep-Crack dataset demonstrate the good performance in pavement crack classification task.

关键词： Image segmentation Force Transportation Memory modules Safety Reliability Labeling

Online Parameter Estimation For Uncertain robot Manipulators With Fixed-time Convergence

学校读者我要写书评

暂无评论

Online Parameter Estimation For Uncertain Robot Manipulators...

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Chengzhi Zhu Yiming Jiang Chenguang Yang Key Laboratory of Autonomous Systems and Networked Control College of Automation Science and Engineering South China University of Technology Guangzhou China National Engineering Laboratory for Robot Visual Perception and Control Hunan University Changsha China Bristol Robotics Laboratory University of the West of England Bristol UK

ISBN: (数字)9781728151694

ISBN: (纸本)9781728151700

For traditional parameter estimation schemes of uncertain robot, most of them were proposed to identify unknown parameter with desired precision, but few of them focused on the convergence time. Recently finite-time estimation techniques have been proposed by scholars to achieve estimation in finite time. In this paper, we proposed a novel estimation scheme for uncertain robot systems with fixed time instead of finite time. In order to avoid using acceleration signals during the estimation, a kind of auxiliary filtering technique was employed. Besides, a continuous and recursive update law was employed for the parameter estimation such that the computational burdens of real-time inversion of square matrices could be avoided. Finally the effectiveness of the identification algorithm is verified based on a 2-DOF uncertain robot model.

关键词： Parameter estimation Filtering Heuristic algorithms Estimation Real-time systems Manipulator dynamics Convergence

Stiffness Estimation and Intention Detection for Human-robot Collaboration

学校读者我要写书评

暂无评论

Stiffness Estimation and Intention Detection for Human-Robot...

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Xiongjun Chen Yiming Jiang Chenguang Yang Key Laboratory of Autonomous Systems and Networked Control College of Automation Science and Engineering South China University of Technology Guangzhou China National Engineering Laboratory for Robot Visual Perception and Control Hunan University Changsha China Bristol Robotics Laboratory University of the West of England Bristol UK

ISBN: (数字)9781728151694

ISBN: (纸本)9781728151700

In this paper, we propose a stiffness estimation and intention detection method for human-robot collaboration. The human arm endpoint stiffness can be obtained according to the muscle activation levels of the upper arm and the human arm configurations. The estimated endpoint stiffness of human arm is matching to the robot arm joint stiffness through an appropriate mapping. The motion intention of human arm is detected based on the wrist configuration which is recognized by a Myo armband attached at the forearm of the operator. In order to reduce the time of feature engineering to ensure the performance of real-time collaboration, the wrist configuration recognition is realised based on the neural learning algorithm. The sEMG of the human forearm is directly fed into the neural network after processing by filters and sliding windows. The force sensor at the end of the robot arm is embedded in the feedback loop to make the robot arm better adapted to the operator's movement. The results of experiments performed on Baxter robot platform illustrate a good performance and verifies the proposed method.

关键词： Wrist Neural networks Collaboration Estimation robot sensing systems Manipulators robots

MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Jian Sun, Wei Yang, Hui Zheng, Jin Geng, Zichen Rahmani, Hossein Mian, Ajmal National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering China School of Robotics Hunan University Changsha410082 China Central South University Changsha410082 China Lancaster University LA1 4YW United Kingdom The University of Western Australia WA6009 Australia

Object pose estimation is a core means for robots to understand and interact with their environment. For this task, monocular category-level methods are attractive as they require only a single RGB camera. However, current methods rely on shape priors or CAD models of the intra-class known objects. We propose a diffusion-based monocular category-level 9D object pose generation method, MonoDiff9D. Our motivation is to leverage the probabilistic nature of diffusion models to alleviate the need for shape priors, CAD models, or depth sensors for intra-class unknown object pose estimation. We first estimate coarse depth via DINOv2 from the monocular image in a zero-shot manner and convert it into a point cloud. We then fuse the global features of the point cloud with the input image and use the fused features along with the encoded time step to condition MonoDiff9D. Finally, we design a transformer-based denoiser to recover the object pose from Gaussian noise. Extensive experiments on two popular benchmark datasets show that MonoDiff9D achieves state-of-the-art monocular category-level 9D object pose estimation accuracy without the need for shape priors or CAD models at any stage. Our code will be made public at https://***/CNJianLiu/MonoDiff9D. Copyright © 2025, The Authors. All rights reserved.

关键词： Image coding

Towards to robust and generalized medical image segmentation framework

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Yurong Zhang, Hui Wang, Yaonan Liu, Lizhu Wu, Q.M. Jonathan Yang, Yimin National Engineering Laboratory of Robot Visual Perception and Control Technology School of Robotics Hunan University Hunan Changsha410082 China Department of Electrical and Computer Engineering University of Windsor WindsorONN9B3P4 Canada Department of Computer Science Lakehead University Vector Institute TorontoM5G 1M1 Canada

—To mitigate the radiologist’s workload, computer-aided diagnosis with the capability to review and analyze medical images is gradually deployed. Deep learning-based region of interest segmentation is among the most exciting use cases. However, this paradigm is restricted in real-world clinical applications due to the poor robustness and generalization. The issue is more sinister with a lack of training data. In this paper, we address the challenge from the representation learning point of view. We investigate that the collapsed representations, as one of the main reasons which caused poor robustness and generalization, could be avoided through transfer learning. Therefore, we propose a novel two-stage framework for robust generalized segmentation. In particular, an unsupervised Tile-wise AutoEncoder (T-AE) pretraining architecture is coined to learn meaningful representation. Furthermore, this learned prior knowledge is transferred to the segmentation benchmark. Coupled with an image reconstruction network, the representation keeps to be decoded, encouraging the model to capture more semantic features. Experiments of lung segmentation on multi chest X-ray datasets are conducted. Empirically, the comprehensive results demonstrate the superior generalization capability of the proposed framework on unseen domains in terms of high performance and robustness to corruption, especially under the scenario of the limited training data. © 2021, CC BY.

关键词： Computer aided diagnosis

Dynamic Update Siamese Networks with Deeper Features

学校读者我要写书评

暂无评论

Dynamic Update Siamese Networks with Deeper Features

作者： Jianhao Tan Shanshan Tan Wang Yin Liming Liu Siyuan Zhang Yaonan Wang College of Electrical and Information Engineering Hunan University National Engineering Laboratory for Robot Visual Perception and Control Technology

visual object tracking has been a concern topic these years,and many trackers have achieved good results in various *** researches and breakthroughs have made many improvements to solve problems such as drift,lighting,deformation and *** this paper,we improve the structure of the AlexNet[1] network by designing the three important influencing factors of the receptive field size,total network step size,and feature filling of the twin *** from this,we add a smoothing matrices and a background suppression matrices to effectively learn the features of the first few frames as much as *** multilayer feature elements can learn online about target appearance changes and background suppression,and we train them by using continuous video sequences.

关键词： Target tracking Siamese network Residual network Dynamic update

Cleaning robot Operation Decision Based on Causal Reasoning and Attribute Learning*

学校读者我要写书评

暂无评论

Cleaning Robot Operation Decision Based on Causal Reasoning ...

2020 IEEE/RSJ International Conference on Intelligent robots and Systems (IROS)

作者： Yapeng Li Dongbo Zhang Feng Yin Ying Zhang Institute of Automation and Electronic Information Xiangtan University Xiangtan China Institute of National Engineering Laboratory of Robot Vision Perception and Control Technology Xiangtan University Xiangtan China

ISBN: (数字)9781728162126

ISBN: (纸本)9781728162133

In order to improve the operation ability of cleaning robots, this paper proposes a decision method for cleaning robot's operation mode. Firstly, we use the hierarchical expression ability of deep network to obtain the attributes of garbage such as state, shape, distribution, size and so on. Then the causal relationship between the attributes and the operation modes can be built by using joint learning of association attributes with depth network model and causal inference. Based on this, a fuzzy inference decision network is designed. With the help of causal analysis, the structure of the decision model is greatly simplified. Compared with conventional fuzzy neural networks, the total parameters of the model are reduced by 2 / 3. The method proposed in this paper imitates the way that human dispose of different types of garbage and has good interpretability. The experimental results verify the effectiveness of the proposed method.

关键词： Training Shape Semantics Fuzzy neural networks Cleaning Cognition robots