检索结果-内蒙古大学图书馆

Real-Time Excavation Trajectory Modulation for Slip and Rollover Prevention

ieee ROBOTICS AND AUTOMATION LETTERS 2025年第4期10卷 3094-3101页

作者： Kim, Changu Son, Bukun Lee, Minhyeong Choi, Hyelim Hong, Seokhyun Kang, Minsung Moon, Jihyun Kim, Dongmok Lee, Dongjun Seoul Natl Univ Dept Mech Engn IAMD Seoul 08826 South Korea Seoul Natl Univ IOER Seoul 08826 South Korea HD Hyundai Xitesolut 477 Bundangsuseo Ro Seongnam 13553 Gyeonggi Do South Korea

We propose a novel real-time excavation trajectory modulation framework on a slope for an autonomous excavator with a low-level digital kinematic control as common for hydraulic industrial excavators. Excavation on a slope is challenging because of a higher risk of slips and rollovers. To deal with this, we propose a real-time excavation trajectory modulation framework based on slope tangential/normal force ratio mu and zero moment point xi. The slip and rollover prevention conditions are incorporated in a single linear inequality using the same fractional structure in mu and xi with the common denominator. However, due to the adoption of the low-level digital kinematic control, this prevention requires the prediction of the excavation force at the next timestamp, and, for this, we develop a data-driven excavation force difference prediction model utilizing a deep learning architecture, Transformer. The remaining error of this prediction is then addressed by using the technique of robust optimization with box uncertainty of the developed excavation force difference model. Our proposed framework is validated experimentally with our customized scaled-down excavator.

关键词： Excavation Force Trajectory Modulation Rollover Kinematics Real-time systems Prevention and mitigation Robots Predictive models Excavation trajectory modulation force difference prediction machine learning robust optimization rollover slip

来源：评论

学校读者我要写书评

暂无评论

Accelerated and Adaptive Power Scheduling for More Electric Aircraft Via Hybrid learning

引用

ieee TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2023年第1期70卷 833-845页

作者： Xu, Bowen Guo, Fanghong Xing, Lantao Wang, Yu Zhang, Wen-An Zhejiang Univ Technol Dept Automat Hangzhou 310023 Peoples R China Shandong Univ Sch Control Sci & Engn Jinan 250061 Peoples R China Imperial Coll London Dept Elect & Elect Engn London SW7 2AZ England

In recent studies, the power scheduling in more electric aircraft (MEA) has been formulated as a mixed-integer quadratic programming problem. Many model-driven methods, such as branch-and-bound algorithms, are advocated to solve it. However, these methods are often prone to considerably high complexities, which makes real-time processing a problem. In this article, a two-stage hybrid learning-based optimization approach is proposed to address this challenging issue. In the first stage, the task of optimizing integer variables is considered as a multilabel classification problem, which is solved by a data-driven method, i.e., ensemble deep neural networks (EDNNs). In the second stage, with the obtained integer solutions, the problem is transformed into a quadratic programming problem that can be quickly solved by model-driven numerical optimization methods. Compared to the state-of-the-art power scheduling algorithms, the model-driven and data-driven methods can compensate each other so that this two-stage hybrid learning-based approach can achieve orders of magnitude speedup in computational time, while guaranteeing the optimal scheduling performance. The structures of EDNNs are well designed so that the proposed approach can adapt to varying operating conditions in MEA. An offline simulation test and an online hardware-in-the-loop test validate the above advantages of the proposed approach.

关键词： Generators Optimization Job shop scheduling Optimal scheduling Real-time systems Aircraft Aerospace electronics Deep neural network (DNN) hybrid learning learning to optimize more electric aircraft (MEA) power scheduling

来源：评论

学校读者我要写书评

暂无评论

MPC of Uncertain Nonlinear systems with Meta-learning for Fast Adaptation of Neural Predictive Models 20

MPC of Uncertain Nonlinear Systems with Meta-Learning for Fa...

引用

ieee 20th International conference on Automation Science and Engineering (CASE)

作者： Yan, Jiaqi Chakrabarty, Ankush Rupenyan, Alisa Lygeros, John Swiss Fed Inst Technol Automat Control Lab Zurich Switzerland Mitsubishi Elect Res Labs Cambridge MA 02139 USA Zurich Univ Appl Sci ZHAW Ctr Artificial Intelligence Zurich Switzerland

ISBN: (纸本)9798350358513;9798350358520

In this paper, we consider the problem of reference tracking in uncertain nonlinear systems. A neural State-Space Model (NSSM) is used to approximate the nonlinear system, where a deep encoder network learns the nonlinearity from data, and a state-space component captures the temporal relationship. This transforms the nonlinear system into a linear system in a latent space, enabling the application of model predictive control (MPC) to determine effective control actions. Our objective is to design the optimal controller using limited data from the target system (the system of interest). To this end, we employ an implicit model-agnostic meta-learning (iMAML) framework that leverages information from source systems (systems that share similarities with the target system) to expedite training in the target system and enhance its control performance. The framework consists of two phases: the (offine) meta-training phase learns an aggregated NSSM using data from source systems, and the (online) meta-inference phase quickly adapts this aggregated model to the target system using only a few data points and few online training iterations, based on local loss function gradients. The iMAML algorithm exploits the implicit function theorem to exactly compute the gradient during training, without relying on the entire optimization path. By focusing solely on the optimal solution, rather than the path, we can meta-train with less storage complexity and fewer approximations than other contemporary meta-learning algorithms. We demonstrate through numerical examples that our proposed method can yield accurate predictive models by adaptation, resulting in a downstream MPC that outperforms several baselines.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Safe data-driven Model Predictive control of systems With Complex Dynamics

引用

ieee TRANSACTIONS ON ROBOTICS 2023年第4期39卷 3242-3258页

作者： Mitsioni, Ioanna Tajvar, Pouria Kragic, Danica Tumova, Jana Pek, Christian KTH Royal Inst Technol Sch Elect Engn & Comp Sci Div Robot Percept & Learning S-11428 Stockholm Sweden

In this article, we address the task and safety performance of data-driven model predictive controllers (DD-MPC) for systems with complex dynamics, i.e., temporally or spatially varying dynamics that may also be discontinuous. The three challenges we focus on are the accuracy of learned models, the receding horizon-induced myopic predictions of DD-MPC, and the active encouragement of safety. To learn accurate models for DD-MPC, we cautiously, yet effectively, explore the dynamical system with rapidly exploring random trees (RRT) to collect a uniform distribution of samples in the state-input space and overcome the common distribution shift in model learning. The learned model is further used to construct an RRT tree that estimates how close the model's predictions are to the desired target. This information is used in the cost function of the DD-MPC to minimize the short-sighted effect of its receding horizon nature. To promote safety, we approximate sets of safe states using demonstrations of exclusively safe trajectories, i.e., without unsafe examples, and encourage the controller to generate trajectories close to the sets. As a running example, we use a broken version of an inverted pendulum where the friction abruptly changes in certain regions. Furthermore, we showcase the adaptation of our method to a real-world robotic application with complex dynamics: robotic food-cutting. Our results show that our proposed control framework effectively avoids unsafe states with higher success rates than baseline controllers that employ models from controlled demonstrations and even random actions.

关键词： Safety Task analysis Trajectory Planning Behavioral sciences Aerospace electronics Robots data-driven modelling dimensionality reduction formal specifications predictive control sampling methods

来源：评论

学校读者我要写书评

暂无评论

data driven learning of Aperiodic Nonlinear Dynamic systems Using Spike Based Reservoirs-in-Reservoir

Data Driven Learning of Aperiodic Nonlinear Dynamic Systems ...

引用

International Joint conference on Neural Networks (IJCNN)

作者： Paul, Ankita Kandasamy, Nagarajan Dandekar, Kapil Das, Anup Drexel Univ Dept Elect & Comp Engn Philadelphia PA 19104 USA

ISBN: (纸本)9798350359329;9798350359312

Mimicking an aperiodic nonlinear dynamic system is challenging as it is difficult to represent it using closed-form equations. A feedback-driven spike-based recurrent spiking neural network is a powerful computational model that can mimic such dynamical systems. We propose reservoirs-in-reservoir (R-iR), a novel architecture to mimic the frequent pattern changes in space and time of an aperiodic nonlinear dynamic system. Here, a large reservoir is built by connecting multiple small reservoirs to a common output. These small reservoirs are individually specialized to mimic a portion of the input dynamic. The internal recurrent connections of each reservoir and its readout are trained using a recursive least squares (RLS)-based full first-order and reduced control error (full-FORCE) algorithm. To make the entire R-i-R architecture adaptable to the change in periodicity of an input, we implement a new cost function that incorporates a unique forgetting factor to control the fading and wind-up of the covariance matrix of each reservoir during training. We evaluate R-i-R using seven aperiodic nonlinear dynamic systems. We show that R-i-R with rate encoding reduces the error rate by an average 59% with 1.8X reduction in network size compared to state-of-the-art. To improve energy efficiency, we implement a time-to-first-spike encoding and show an average reduction of 39. 5% in the number of spikes.

关键词： Dynamic systems reservoir computing spiking neural networks non-linear systems machine learning

来源：评论

学校读者我要写书评

暂无评论

Knowledge-data Fusion Based Source-Free Semi-Supervised Domain Adaptation for Seizure Subtype Classification

Knowledge-Data Fusion Based Source-Free Semi-Supervised Doma...

引用

2024 ieee International conference on systems, Man, and Cybernetics, SMC 2024

作者： Peng, Ruimin An, Jiayu Wu, Dongrui School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control Wuhan430074 China

ISBN: (纸本)9781665410205

Electroencephalogram (EEG)-based seizure sub-type classification enhances clinical diagnosis efficiency. Source-free semi-supervised domain adaptation (SF-SSDA), which transfers a pre-trained model to a new dataset with no source data and limited labeled target data, can be used for privacy-preserving seizure subtype classification. This paper considers two challenges in SF-SSDA for EEG-based seizure subtype classification: 1) How to effectively fuse both raw EEG data and expert knowledge in classifier design? 2) How to align the source and target domain distributions for SF-SSDA? We propose a Knowledge-data Fusion based SF-SSDA approach, KDF-MutuaISHOT, for EEG-based seizure subtype classification. In source model training, KDF uses Jensen-Shannon Diver-gence to facilitate mutual learning between a feature-driven Decision Tree-based model and a data-driven Transformer-based model. To adapt KDF to a new target dataset, an SF-SSDA algorithm, MutualSHOT, is developed, which features a consistency-based pseudo-label selection strategy. Experiments on the public TUSZ and CHSZ datasets demonstrated that KDF-MutualSHOT outperformed other supervised and source-free domain adaptation approaches in cross-subject seizure subtype classification. © 2024 ieee.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Dual Behavior Regularized Offline Deterministic Actor-Critic

引用

ieee TRANSACTIONS ON systems MAN CYBERNETICS-systems 2024年第8期54卷 4841-4852页

作者： Cao, Shuo Wang, Xuesong Cheng, Yuhu China Univ Min & Technol Engn Res Ctr Intelligent Control Underground Space Minist Educ Xuzhou 221116 Peoples R China China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Peoples R China

To mitigate the extrapolation error arising from offline reinforcement learning (RL) paradigm, existing methods typically make learned Q-functions over-conservative or enforce global policy constraints. In this article, we propose a dual behavior regularized offline deterministic Actor-Critic (DBRAC) by simultaneously performing behavior regularization on the coupling-iterative policy evaluation (PE) and policy improvement (PI) in the policy iteration process. In the PE phase, the difference between the Q-function and behavior value is first taken as the anti-exploration behavior value regularization term to drive the Q-function toward its true Q-value, which significantly reduces the conservatism of learned Q-function. In the PI phase, the estimated action variances of behavior policy in different states are then utilized for designing the weight and threshold of mild-local behavior cloning regularization term, which standardizes the local improvement potential of learned policy. Experiments on the well-known datasets for deep data-driven RL (D4RL) demonstrate that the DBRAC can quickly learn more competitive task-solving policies in various offline situations with different data qualities, significantly outperforming state-of-the-art offline RL baselines.

关键词： Anti-exploration behavior value dual behavior regularization (DBR) mild-local behavior cloning (BC) offline deterministic Actor-Critic reinforcement learning (RL)

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal data-driven and Machine learning based Applications for Transmission systems

Spatio-temporal Data-Driven and Machine Learning based Appli...

引用

ieee-Power-and-Energy-Society General Meeting (PESGM)

作者： Sevilla, F. R. Segundo Liu, Y. Barocio, E. Korbal, P. Zamora, A. Dotta, D. Bellizio, F. Chavez, H. Johannsson, H. Cepeda, J. Cremer, J. Zhao, J. Arrieta, M. Paolone, M. Ramirez, M. Papadopoulos, P. Susuki, Y. ZHAW Zurich Switzerland Tianjin Univ Tianjin Peoples R China Univ Guadalajara Guadalajara Jalisco Mexico UMICH Morelia Michoacan Mexico Univ Estadual Campinas Campinas SP Brazil EMPA Dubendorf Switzerland USACH Estn Cent Chile DTU Lyngby Denmark CENACE Quito Ecuador Delft Univ Technol Delft Netherlands Univ Connecticut Storrs CT USA Univ Nacl Autonoma Mexico Mexico City DF Mexico Ecole Polytech Fed Lausanne Lausanne Switzerland Univ Strathclyde Glasgow Lanark Scotland Kyoto Univ Kyoto Japan

ISBN: (纸本)9798350381849;9798350381832

This paper summarizes recent advancements on spatio-temporal data-driven and machine learning methods for static and dynamic security assessment, and their particular use cases. It is a collective effort of different research groups members of the ieee Working Group on Big data Analytics for Transmission systems, to provide transmission system operators (TSOs) with innovative tools and ideas for their potential implementation. The algorithms presented here are classified as non-training and training approaches, namely spatio-temporal and machine learning based, considering as input time series from time domain simulations, and or synchrophasor data from wide-area monitoring systems. The efficacy of these algorithms is then evaluated in different ieee benchmark models and using real system measurements from different countries.

关键词： data-driven machine learning static and dynamic security assessment transient stability event detection preventive control coherency modal analysis parameter identification

来源：评论

学校读者我要写书评

暂无评论

Supervise-Assisted Self-Supervised Deep-learning Method for Hyperspectral Image Restoration

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND learning systems 2025年第4期36卷 7331-7344页

作者： Li, Miaoyu Fu, Ying Zhang, Tao Wen, Guanghui Beijing Inst Technol Sch Comp Sci & Technol Beijing Key Lab Intelligent Informat Technol Beijing 100081 Peoples R China Beijing Inst Technol Beijing Key Lab Intelligent Informat Technol MIIT Key Lab Complex Field Intelligent Explorat Beijing 100081 Peoples R China Beijing Inst Technol Sch Comp Sci & Technol Beijing 100081 Peoples R China Hangzhou Dianzi Univ Sch Commun Engn Hangzhou 310018 Peoples R China Southeast Univ Dept Math Nanjing 210096 Peoples R China

Hyperspectral image (HSI) restoration is a challenging research area, covering a variety of inverse problems. Previous works have shown the great success of deep learning in HSI restoration. However, facing the problem of distribution gaps between training HSIs and target HSI, those data-driven methods falter in delivering satisfactory outcomes for the target HSIs. In addition, the degradation process of HSIs is usually disturbed by noise, which is not well taken into account in existing restoration methods. The existence of noise further exacerbates the dissimilarities within the data, rendering it challenging to attain desirable results without an appropriate learning approach. To track these issues, in this article, we propose a supervise-assisted self-supervised deep-learning method to restore noisy degraded HSIs. Initially, we facilitate the restoration network to acquire a generalized prior through supervised learning from extensive training datasets. Then, the self-supervised learning stage is employed and utilizes the specific prior of the target HSI. Particularly, to restore clean HSIs during the self-supervised learning stage from noisy degraded HSIs, we introduce a noise-adaptive loss function that leverages inner statistics of noisy degraded HSIs for restoration. The proposed noise-adaptive loss consists of Stein's unbiased risk estimator (SURE) and total variation (TV) regularizer and fine-tunes the network with the presence of noise. We demonstrate through experiments on different HSI tasks, including denoising, compressive sensing, super-resolution, and inpainting, that our method outperforms state-of-the-art methods on benchmarks under quantitative metrics and visual quality. The code is available at https://***/ying-fu/SSDL-HSI.

关键词： Convolutional neural network (CNN) deep learning hyperspectral image (HSI) image restoration self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

CARL: Congestion-Aware Reinforcement learning for Imitation-Based Perturbations in Mixed Traffic control 14

CARL: Congestion-Aware Reinforcement Learning for Imitation-...

引用

14th ieee International conference on Cyber Technology in Automation, control, and Intelligent systems, CYBER 2024

作者： Poudel, Bibek Li, Weizi Li, Shuai University of Tennessee Min H. Kao Department of Electrical Engineering and Computer Science KnoxvilleTN United States University of Tennessee Department of Civil and Environmental Engineering KnoxvilleTN United States

ISBN: (纸本)9798331506056

Human-driven vehicles (HVs) exhibit complex and diverse behaviors. Accurately modeling such behavior is crucial for validating Robot Vehicles (RVs) in simulation and realizing the potential of mixed traffic control. However, existing approaches like parameterized models and data-driven techniques struggle to capture the full complexity and diversity. To address this, in this work, we introduce CARL, a hybrid approach that combines imitation learning for close proximity car-following and probabilistic sampling for larger headways. We also propose two classes of RL-based RVs: a safety RV focused on maximizing safety and an efficiency RV focused on maximizing efficiency. Our experiments show that the safety RV increases Time-to-Collision above the critical 4 second threshold and reduces Deceleration Rate to Avoid a Crash by up to 80%, while the efficiency RV achieves improvements in throughput of up to 49%. These results demonstrate the effectiveness of CARL in enhancing both safety and efficiency in mixed traffic. © 2024 ieee.

关键词： Reinforcement learning

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：