检索结果-内蒙古大学图书馆

SS-ADA: A Semi-Supervised Active Domain Adaptation Framework for Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yan, Weihao Qian, Yeqiang Li, Yueyuan Li, Tao Wang, Chunxiang Yang, Ming Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

Semantic segmentation plays an important role in intelligent vehicles, providing pixel-level semantic information about the environment. However, the labeling budget is expensive and time-consuming when semantic segmentation model is applied to new driving scenarios. To reduce the costs, semi-supervised semantic segmentation methods have been proposed to leverage large quantities of unlabeled images. Despite this, their performance still falls short of the accuracy required for practical applications, which is typically achieved by supervised learning. A significant shortcoming is that they typically select unlabeled images for annotation randomly, neglecting the assessment of sample value for model training. In this paper, we propose a novel semi-supervised active domain adaptation (SS-ADA) framework for semantic segmentation that employs an image-level acquisition strategy. SS-ADA integrates active learning into semi-supervised semantic segmentation to achieve the accuracy of supervised learning with a limited amount of labeled data from the target domain. Additionally, we design an IoU-based class weighting strategy to alleviate the class imbalance problem using annotations from active learning. We conducted extensive experiments on synthetic-to-real and real-to-real domain adaptation settings. The results demonstrate the effectiveness of our method. SS-ADA can achieve or even surpass the accuracy of its supervised learning counterpart with only 25% of the target labeled data when using a real-time segmentation model. The code for SS-ADA is available at https://***/ywher/SS-ADA. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

Adaptive Optimal control of Nonlinear systems with Multiple Time-Scale Eligibility Traces

学校读者我要写书评

暂无评论

Adaptive Optimal Control of Nonlinear Systems with Multiple ...

IEEE Conference on Decision and control

作者： Jun Rao Jingcheng Wang Jiahui Xu Shunyu Wu Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China

Adaptive dynamic programming (ADP) is one of the main methods to solve the optimal control problem of nonlinear systems. Eligibility traces are utilized in recent years to reduce the computing burden of the value function, but the existing fixed eligibility trace is difficult to ensure stable convergence especially when facing environmental changes and complex neural network structures. To solve the above issues, a novel off-policy algorithm, $T$ -HDP $(\lambda)$ with Multiple Time-scale Eligibility Traces (MET), is proposed. By utilizing MET, the new algorithm can adaptively accumulate gradients and include more gradient information, which guides the control faster in the optimal direction. $T$ -step Truncated $\lambda$ -returns are utilized to solve the infinite-horizon optimal control problems, and a new importance sampling ratio is designed to correct the value function. Furthermore, the convergence and boundedness of the algorithm are proved. Based on the actor-critic network architecture, the optimal value function and policy are well approximated. Finally, compared with the original algorithm by a simulation example, the proposed algorithm has a faster convergence speed and lower variance.

关键词：

Stochastic Trajectory Optimization for Demonstration Imitation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ming, Chenlin Wang, Zitong Zhang, Boxuan Duan, Xiaoming He, Jianping The Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Germany

Humans often learn new skills by imitating the experts and gradually developing their proficiency. In this work, we introduce Stochastic Trajectory Optimization for Demonstration Imitation (STODI), a trajectory optimization framework for robots to imitate the shape of demonstration trajectories with improved dynamic performance. Consistent with the human learning process, demonstration imitation serves as an initial step, while trajectory optimization aims to enhance robot motion performance. By generating random noise and constructing proper cost functions, the STODI effectively explores and exploits generated noisy trajectories while preserving the demonstration shape characteristics. We employ three metrics to measure the similarity of trajectories in both the time and frequency domains to help with demonstration imitation. Theoretical analysis reveals relationships among these metrics, emphasizing the benefits of frequency-domain analysis for specific tasks. Experiments on a 7-DOF robotic arm in the PyBullet simulator validate the efficacy of the STODI framework, showcasing the improved optimization performance and stability compared to previous methods. The source code can be found at ming-bot/STODI. Copyright © 2024, The Authors. All rights reserved.

关键词： Cost functions

Distributionally Robust Probabilistic Prediction for Stochastic Dynamical systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Tao He, Jianping The Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

Probabilistic prediction of stochastic dynamical systems (SDSs) aims to accurately predict the conditional probability distributions of future states. However, accurate probabilistic predictions tightly hinge on accurate distributional information from a nominal model, which is hardly available in practice. To address this issue, we propose a novel functional-maximin-based distributionally robust probabilistic prediction (DRPP) framework. In this framework, one can design probabilistic predictors that have worst-case performance guarantees over a pre-defined ambiguity set of SDSs. Nevertheless, DRPP requires optimizing over the function space of probability distributions, which is generally intractable. We develop a methodology that equivalently transforms the original maximin in function spaces into convex-nonconcave minimax in Euclidean spaces. Although it remains intractable to seek a global optimal solution, two suboptimal solutions are derived. By relaxing the inner constraints, we obtain a suboptimal predictor called Noise-DRPP. Relaxing the outer constraints yields another suboptimal predictor, Eig-DRPP. More importantly, we establish an explicit upper bound on the optimality gap between Eig-DRPP and the global optimal predictor. Utilizing the theoretical results obtained from solving the two suboptimal predictors, we synthesize practical rules to judge whether the pre-defined ambiguity set is too large or small. Finally, we conduct elaborate numerical simulations to compare the performance of different predictors under different SDSs. © 2024, CC BY-NC-ND.

关键词： Prediction models

Online distributed tracking of generalized Nash equilibrium on physical networks——Closing the Loop via Measurement Feedback

学校读者我要写书评

暂无评论

Autonomous Intelligent systems 2021年第1期1卷 69-80页

作者： Yifan Su Feng Liu Zhaojian Wang Shengwei Mei Qiang Lu The State Key Laboratory of Power System Department of Electrical EngineeringTsinghua UniversityBeijingChina The Key Laboratory of System Control and Information ProcessingMinistry of Education of ChinaDepartment of AutomationShanghai Jiao Tong UniversityShanghaiChina

In generalized Nash equilibrium(GNE)seeking problems over physical networks such as power grids,the enforcement of network constraints and time-varying environment may bring high computational *** online algorithms is recognized as a promising method to cope with this challenge,where the task of computing system states is replaced by directly using measured values from the physical *** this paper,we propose an online distributed algorithm via measurement feedback to track the GNE in a time-varying networked resource sharing *** that some system states are not measurable and measurement noise always exists,a dynamic state estimator is incorporated based on a Kalman filter,rendering a closed-loop dynamics of measurement-feedback driven online *** prove that,with a fixed step size,this online algorithm converges to a neighborhood of the GNE in *** simulations validate the theoretical results.

关键词： Generalized Nash equilibrium Distributed optimization Online optimization Feedback-based optimization State estimation Sharing market

Cross-Domain Buoy Placement for Underwater Target Tracking in Marine Wireless Networks

学校读者我要写书评

暂无评论

Cross-Domain Buoy Placement for Underwater Target Tracking i...

IEEE World Forum on Internet of Things (WF-IoT)

作者： Yichen Li Wenbin Yu Liangyu Jiang Buyiyi Wang Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350311617

ISBN: (纸本)9798350311624

Underwater target tracking can continuously provide position estimates of the interested target. It is the basis for marine applications. Usually, a proper deployment topology of the available devices could guarantee that the optimal tracking performance can be obtained. This paper investigates the optimal placement problem of buoys under a cross-domain tracking framework, where the buoys are deployed with unmanned aerial vehicles (UAVs) to perform coarse tracking and provide prior information for the subsequent arriving underwater vehicles. By taking advantage of the high-speed movement of UAVs, the disadvantage of underwater tracking (difficult to quickly form an effective tracking formation when the target is first found) is made up. Specifically, the placement is formulated as a convex optimization problem based on the idea of sensor selection, and the output makes the buoys and pre-deployed anchors form a combination that optimizes the tracking accuracy while guaranteeing the detection probability. Moreover, the target mobility and deployment convenience are also considered to favor practical uses. Through various simulation results, the advantages of the proposed method are illustrated.

关键词： Performance evaluation Target tracking Wireless networks Simulation Design methodology Convex functions Underwater tracking

Two-Stage OD Flow Prediction for Emergency in Urban Rail Transit

学校读者我要写书评

暂无评论

IEEE Transactions on Intelligent Transportation systems 2024年第1期25卷 920-928页

作者： Zhu, Guangyu Ding, Jiacun Wei, Yun Yi, Yang Xu, Sendren Sheng-Dong Wu, Edmond Q. Beijing Jiaotong University Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport The Beijing Research Center of Urban Traffic Information Sensing and Service Technologies Beijing100044 China Beijing Mass Transit Railway Operation Corporation Ltd. Beijing100014 China Yangzhou University College of Information Engineering Yangzhou225127 China National Taiwan University of Science and Technology Automation and Control Center The Graduate Institute of Automation and Control Taipei106335 Taiwan Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China The Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai200240 China

Urban rail transit (URT) is vulnerable to natural disasters and social emergencies including fire, storm and epidemic (such as COVID-19), and real-time origin-destination (OD) flow prediction provides URT operators with important information to ensure the safety of URT system. However, hindered by the high dimensionality of OD flow and the lack of supportive information reflecting the real-time passenger flow changes, study in this area is at the beginning stage. A novel model consisting of two stages is proposed for OD flow prediction. The first stage predicts the inflows of all stations by Long Short-Term Memory (LSTM) in real time, where the dimension is reduced compared with predicting OD flows directly. In the second stage, the notion of separation rate, namely, the proportion of inbound passengers bounding for another station, is estimated. Finally, The OD flow is predicted by multiplying the inflow and separation rate. Experiments based on Hangzhou Metro dataset show the proposed model outperforms the contrast model in weighted mean average error (WMAE) and weighted mean square error (WMSE). Results also suggest that the proposed prediction model performs better on weekdays than on weekends, and with greater accuracy on larger OD flows. © 2000-2011 IEEE.

关键词： Forecasting

OIDM: An Observability-based Intelligent Distributed Edge Sensing Method for Industrial Cyber-Physical systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Shigeng Jin, Tiankai Ma, Yehan Chen, Cailian Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

Industrial cyber-physical systems (ICPS) integrate physical processes with computational and communication technologies in industrial settings. With the support of edge computing technology, it is feasible to schedule large-scale sensors for efficient distributed sensing. In the sensing process, observability is the key to obtaining complete system states, and stochastic scheduling is more suitable considering uncertain factors in wireless communication. However, existing works have limited research on observability in stochastic scheduling. Targeting this issue, we propose an observability-based intelligent distributed edge sensing method (OIDM). Deep reinforcement learning (DRL) methods are adopted to optimize sensing accuracy and power efficiency. Based on the system’s ability to achieve observability, we establish a bridge between observability and the number of successful sensor transmissions. Novel linear approximations of observability criteria are provided, and probabilistic bounds on observability are derived. Furthermore, these bounds guide the design of action space to achieve a probabilistic observability guarantee in stochastic scheduling. Finally, our proposed method is applied to the estimation of slab temperature in industrial hot rolling process, and simulation results validate its effectiveness. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

A semantic segmentation method for UAV image based on improved BiseNetv2 5

学校读者我要写书评

暂无评论

A semantic segmentation method for UAV image based on improv...

5th International Conference on Artificial Intelligence and Computer Science, AICS 2023

作者： Guo, Fengjuan Han, Sen Zhao, Jiahang Han, Jiale Xin, Jing Shaanxi Key Laboratory of Integrated and Intelligent Navigation The 20th Research Institute of China Electronics Technology Corporation Shaanxi Xi’an710068 China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of Technology Shaanxi Xi’an710048 China

ISBN: (纸本)9781510668621

Aiming at the problem of low semantic segmentation accuracy of tiny targets in UAV aerial images, a bilateral semantic segmentation network T-BiseNetv2 is proposed. The proposed segmentation network is based on BiseNetv2, and the Transformer structure is introduced into semantic branch, and the detail branch and feature fusion module are reconstructed, which improves the network’s capacity to capture both global context information and local semantic information. Several semantic segmentation experiments are conducted on the standard semantic segmentation dataset UAVID, experimental results show that the proposed semantic segmentation network T-BiseNetv2 has a MIoU of 69.52%, which is about 2.2% higher than the original BiseNetv2 network. Especially, for "Human", the IoU of TBiseNetv2 is about 4.3% higher than that of the popular UNetFormer. © 2023 SPIE.

关键词： Unmanned aerial vehicles (UAV)