检索结果-内蒙古大学图书馆

Direction and Trajectory Tracking control for Nonholonomic Spherical Robot by Combining Sliding Mode controller and Model Prediction controller

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Yifan Wang, Yixu Guan, Xiaoqing Hu, Tao Zhang, Ziang Jin, Song Wang, You Hao, Jie Li, Guang State Key Laboratory of Industrial Control Technology Institute of Cyber Systems and Control Zhejiang University Hangzhou310027 China Luoteng Hangzhou Techonlogy Co. Ltd. Hangzhou310027 China

Spherical robot is a nonlinear, nonholonomic and unstable system which increases the difficulty of the direction and trajectory tracking problem. In this study, we propose a new direction controller HTSMC, an instruction planning controller MPC, and a trajectory tracking framework MHH. The HTSMC is designed by integrating a fast terminal algorithm, a hierarchical method, the motion features of a spherical robot, and its dynamics. In addition, the new direction controller has an excellent control effect with a quick response speed and strong stability. MPC can obtain optimal commands that are then transmitted to the velocity and direction controller. Since the two torque controllers in MHH are all Lyapunov-based sliding mode controllers, the MHH framework may achieve optimal control performance while assuring stability. Finally, the two controllers eliminate the requirement for MPC's stability and dynamic constraints. Finally, hardware experiments demonstrate the efficacy of the HTSMC, MPC, and MHH. Copyright © 2022, The Authors. All rights reserved.

关键词： controllers

Adaptive Positional Encoding for Bundle-Adjusting Neural Radiance Fields

学校读者我要写书评

暂无评论

Adaptive Positional Encoding for Bundle-Adjusting Neural Rad...

International Conference on Computer Vision (ICCV)

作者： Zelin Gao Weichen Dai Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province and School of Computer Science Hangzhou Dianzi University Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province

Neural Radiance Fields have shown great potential to synthesize novel views with only a few discrete image observations of the world. However, the requirement of accurate camera parameters to learn scene representations limits its further application. In this paper, we present adaptive positional encoding (APE) for bundle-adjusting neural radiance fields to reconstruct the neural radiance fields from unknown camera poses (or even intrinsics). Inspired by Fourier series regression, we investigate its relationship with the positional encoding method and therefore propose APE where all frequency bands are trainable. Furthermore, we introduce period-activated multilayer perceptrons (PMLPs) to construct the implicit network for the high-order scene representations and fine-grained gradients during backpropagation. Experimental results on public datasets demonstrate that the proposed method with APE and PMLPs can outperform the state-of-the-art methods in accurate camera poses and high-fidelity view synthesis.

关键词：

A perspective on Attitude control Issues and Techniques

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Dandan Jin, Xin Su, Hongye The State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China The Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology Shanghai200237 China

This paper reviews the attitude control problems for rigid-body systems, starting from the attitude representation for rigid body kinematics. Highly redundant rotation matrix defines the attitude orientation globally and uniquely by 9 parameters, which is the most fundamental one, without any singularities;minimum 3-parameter Euler angles or (modified) Rodrigues parameters define the attitude orientation neither globally nor uniquely, but the former exhibits kinematical singularity and Gimbal lock, while the latter two exhibit geometrical singularity;once-redundant axis-angle or unit quaternion globally define the attitude rotation but not uniquely using 4 parameters, but the former is not appropriate to define very small or very large rotations, while the latter shows unwinding phenomenon despite of the reduced computation burden. In addition, we explore the relationships among those attitude representations, including the connections among Gimbal lock, unwinding phenomenon and a nowhere dense set of zero Lebesgue measure. Based on attitude representations, we analyze different attitude control laws, almost global control and global attitude control, nominal and general robustness, as well as the technique *** Codes 70E50 Copyright © 2022, The Authors. All rights reserved.

关键词： Attitude control

UGNA-VPR: A Novel Training Paradigm for Visual Place Recognition Based on Uncertainty-Guided NeRF Augmentation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Shen, Yehui Zhang, Lei Li, Qingqiu Zhao, Xiongwei Wang, Yue Lu, Huimin Chen, Xieyuanli College of Intelligence Science and Technology National University of Defense Technology China Faculty of Robot Science and Engineering Northeastern University China School of Electronic and Information Engineering Harbin Institute of Technology Shenzhen China State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University China SIASUN Robot& Automation Co. Ltd China School of Computer Science Fudan University China

Visual place recognition (VPR) is crucial for robots to identify previously visited locations, playing an important role in autonomous navigation in both indoor and outdoor environments. However, most existing VPR datasets are limited to single-viewpoint scenarios, leading to reduced recognition accuracy, particularly in multi-directional driving or feature-sparse scenes. Moreover, obtaining additional data to mitigate these limitations is often expensive. This paper introduces a novel training paradigm to improve the performance of existing VPR networks by enhancing multi-view diversity within current datasets through uncertainty estimation and NeRF-based data augmentation. Specifically, we initially train NeRF using the existing VPR dataset. Then, our devised self-supervised uncertainty estimation network identifies places with high uncertainty. The poses of these uncertain places are input into NeRF to generate new synthetic observations for further training of VPR networks. Additionally, we propose an improved storage method for efficient organization of augmented and original training data. We conducted extensive experiments on three datasets and tested three different VPR backbone networks. The results demonstrate that our proposed training paradigm significantly improves VPR performance by fully utilizing existing data, outperforming other training approaches. We further validated the effectiveness of our approach on self-recorded indoor and outdoor datasets, consistently demonstrating superior results. Our dataset and code have been released at https://***/nubot-nudt/UGNA-VPR. Copyright © 2025, The Authors. All rights reserved.

关键词：

Surrogate Empowered Sim2Real Transfer of Deep Reinforcement Learning for ORC Superheat control

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lin, Runze Luo, Yangyang Wu, Xialai Chen, Junghui Huang, Biao Xie, Lei Su, Hongye State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China Department of Chemical and Materials Engineering University of Alberta EdmontonABT6G 2G6 Canada Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems School of Engineering Huzhou University Huzhou313000 China Department of Chemical Engineering Chung-Yuan Christian University Taoyuan32023 Taiwan

The Organic Rankine Cycle (ORC) is widely used in industrial waste heat recovery due to its simple structure and easy maintenance. However, in the context of smart manufacturing in the process industry, traditional model-based optimization control methods are unable to adapt to the varying operating conditions of the ORC system or sudden changes in operating modes. Deep reinforcement learning (DRL) has significant advantages in situations with uncertainty as it directly achieves control objectives by interacting with the environment without requiring an explicit model of the controlled plant. Nevertheless, direct application of DRL to physical ORC systems presents unacceptable safety risks, and its generalization performance under model-plant mismatch is insufficient to support ORC control requirements. Therefore, this paper proposes a Sim2Real transfer learning-based DRL control method for ORC superheat control, which aims to provide a new simple, feasible, and user-friendly solution for energy system optimization control. Experimental results show that the proposed method greatly improves the training speed of DRL in ORC control problems and solves the generalization performance issue of the agent under multiple operating conditions through Sim2Real transfer. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

Wavy Whiskers in Phocid Seals Exhibit High Signal-to-Noise in Sensing Hydrodynamic Flows

学校读者我要写书评

暂无评论

Wavy Whiskers in Phocid Seals Exhibit High Signal-to-Noise i...

IEEE International Conference on Cyborg and Bionic systems (CBS)

作者： Xingwen Zheng Amar M. Kamat Ming Cao Michael S. Triantafyllou Ajay G. P. Kottapalli Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen Groningen the Netherlands State Key Laboratory of Industrial Control and Technology Zhejiang University Hangzhou China Department of Control Science and Engineering Institute of Cyber-Systems and Control Zhejiang University Hangzhou China MIT Sea Grant College Program Massachusetts Institute of Technology (MIT) 77 Massachusetts Avenue Cambridge MA USA Department of Mechanical Engineering MIT Cambridge MA USA

ISBN: (数字)9798350388039

ISBN: (纸本)9798350388046

Phocid seals can detect fish from distances up to 180 meters solely using undulating whiskers. The unique undulating surfaces of these whiskers have been found to minimize vortex-induced vibrations (VIVs). In our previous work, we measured the ratios of undulation wavelength (λ) to mean diameter $\left(D_{m}\right),\left(\lambda / D_{m}\right)$ in both harbor and grey seals, yielding values of approximately 4.36 and 4.63, respectively. In this study, we delve into the significance of the $\lambda / D_{m}$ ratio to the vibration responses of seal whiskers in a fluid flow. We conducted comprehensive fluid-structure interaction studies using COMSOL Multiphysics®, wherein we studied vibration responses of harbor and grey seal whisker structures with diverse $\lambda / D_{m}$ values in the oncoming flow. Our results indicate that seal whiskers exhibited a trough in their VIV responses and a peak in wake-induced vibration (WIV) responses at $\lambda / D_{m}$ values around 4 to 5. Our findings could imply that the evolutionary optimization of the $\lambda / D_{m}$ value enables seal whiskers with resistance to VIV and sensitivity to WIV.

关键词： Vibrations Sensitivity Surface waves Biological system modeling Wavelength measurement Seals Fish Robot sensing systems Sensor systems Sensors

Detection methods of surface defects of sintering material based on machine vision

学校读者我要写书评

暂无评论

Detection methods of surface defects of sintering material b...

Fully Actuated System Theory and Applications (CFASTA), Conference on

作者： Wensi Liu Xiao-Yu Tang Yi Yang Liang Zhao Chunjie Yang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China School of Reliability and Systems Engineering Beihang University Beijing China School of Software Technology Dalian University of Technology Dalian China

The iron and steel industry is one of the pillar industries in the national economy. Blast furnace (BF) ironmaking is the core step in long-process ironmaking. Before BF production, to improve the ore quality, sintering is adopted to provide high-quality man-made ore from raw materials. In the sintering process, the material surface state is the main indicator for monitoring the ignition effect. During the actual production process, due to the influence of the ingredients and the ignition effect, there are defects on the sintering material surface, including yellow mud, mouse holes, and cracks. Detection of defect information on the material surface is conducive to ensuring the stable quality of the sinter and the stable operation of sintering production. This paper designs the corresponding detection methods for the three defects based on machine vision algorithms, 1) Yellow mud detection: separate the material surface area of the sintering trolley by semantic segmentation, and judge whether there is yellow mud according to the HSV histogram correlation combined with the shape judgment condition of yellow mud; 2) Mouse hole detection: use the target detection method of YOLOv5 without Mosaic detects mouse holes and improves the detection ability of small targets; 3) Crack detection: transfer learning and improved DeepLabv3+ network semantic segmentation are used for crack detection to improve the accuracy of crack detection. Finally, all methods are applied to the actual production line, and the detection accuracy and effectiveness of the above methods are verified through image testing and calculation of evaluation indicators, which can meet the needs of on-site use.

关键词：

PEBO-SLAM: Observer Design for Visual Inertial SLAM with Convergence Guarantees

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yi, Bowen Jin, Chi Wang, Lei Shi, Guodong Ila, Viorela Manchester, Ian R. The Australian Centre for Robotics School of Aerospace Mechanical and Mechatronic Engineering The University of Sydney SydneyNSW2006 Australia The TuSimple Inc. Liangmaqiao Road Beijing China State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China

This paper introduces a new linear parameterization to the problem of visual inertial simultaneous localization and mapping (VI-SLAM)—without any approximation—for the case only using information from a single monocular camera and an inertial measurement unit. In this problem set, the system state evolves on the nonlinear manifold SE(3)×3n, on which we design dynamic extensions carefully to generate invariant foliations, such that the problem can be reformulated into online constant parameter identification, then interestingly with linear regression models obtained. It demonstrates that VI-SLAM can be translated into a linear least squares problem, in the deterministic sense, globally and exactly. Based on this observation, we propose a novel SLAM observer, following the recently established parameter estimation-based observer (PEBO) methodology. A notable merit is that the proposed observer enjoys almost global asymptotic stability, requiring neither persistency of excitation nor uniform complete observability, which, however, are widely adopted in most existing works with provable stability but can hardly be assured in many practical scenarios. © 2023, CC BY.

关键词： Parameter estimation

Neural motion prediction for in-flight uneven object catching

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yu, Hongxiang Guo, Dashun Yin, Huan Chen, Anzhe Xu, Kechun Wang, Yue Xiong, Rong State Key Laboratory of Industrial Control and Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310058 China

In-flight objects capture is extremely challenging. The robot is required to complete trajectory prediction, interception position calculation and motion planning in sequence within tens of milliseconds. As in-flight uneven objects are affected by various kinds of forces, motion prediction is difficult for a time-varying acceleration. In order to compensate the system’s non-linearity, we introduce the Neural Acceleration Estimator (NAE) that estimates the varying acceleration by observing a small fragment of previous deflected trajectory. Moreover, end-to-end training with Differantiable Filter (NAE-DF) gives a supervision for measurement uncertainty and further improves the prediction accuracy. Experimental results show that motion prediction with NAE and NAE-DF is superior to other methods and has a good generalization performance on unseen objects. We test our methods on a robot, performing velocity control in real world and respectively achieve 83.3% and 86.7% success rate on a ploy urethane banana and a gourd. We also release an object in-flight dataset containing 1,500 trajectorys for uneven objects. © 2021, CC BY.

关键词： Motion estimation