检索结果-内蒙古大学图书馆

Signal Temporal Logic control Synthesis among Uncontrollable Dynamic Agents with Conformal Prediction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yu, Xinyi Zhao, Yiqi Yin, Xiang Lindemann, Lars Thomas Lord Department of Computer Science University of Southern California Los AngelesCA90089 United States Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai200240 China

The control of dynamical systems under temporal logic specifications among uncontrollable dynamic agents is challenging due to the agents’ a-priori unknown behavior. Existing works have considered the problem where either all agents are controllable, the agent models are deterministic and known, or no safety guarantees are provided. We propose a predictive control synthesis framework that guarantees, with high probability, the satisfaction of signal temporal logic (STL) tasks that are defined over a controllable system in the presence of uncontrollable stochastic agents. We use trajectory predictors and conformal prediction to construct probabilistic prediction regions for each uncontrollable agent that are valid over multiple future time steps. Specifically, we construct a normalized prediction region over all agents and time steps to reduce conservatism and increase data efficiency. We then formulate a worst-case bilevel mixed integer program (MIP) that accounts for all agent realizations within the prediction region to obtain an open-loop controller that provably guarantee task satisfaction with high probability. To efficiently solve this bilevel MIP, we propose an equivalent MIP program based on KKT conditions of the original bilevel formulation. Building upon this, we design a closed-loop controller, where both recursive feasibility and task satisfaction can be guaranteed with high probability. We illustrate our control synthesis framework on two case studies. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zeng, Runhao Zhou, Dingjie Liang, Qiwei Liu, Junlin Li, Hui Huang, Changxin Li, Jianqiang Hu, Xiping Sun, Fuchun Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Mechatronics and Control Engineering Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science and Technology Tsinghua University China

Learning behavior in legged robots presents a significant challenge due to its inherent instability and complex constraints. Recent research has proposed the use of a large language model (LLM) to generate reward functions in reinforcement learning, thereby replacing the need for manually designed rewards by experts. However, this approach, which relies on textual descriptions to define learning objectives, fails to achieve controllable and precise behavior learning with clear directionality. In this paper, we introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Specifically, we first process videos containing the target behaviors, converting the motion information of individuals in the videos into keypoint trajectories represented as coordinates through a video2text transforming module. These trajectories are then fed into an LLM to generate the reward function, which in turn is used to train the policy. To enhance the quality of the reward function, we develop a video-assisted iterative reward refinement scheme that visually assesses the learned behaviors and provides textual feedback to the LLM. This feedback guides the LLM to continually refine the reward function, ultimately facilitating more efficient behavior learning. Experimental results on tasks involving bipedal and quadrupedal robot motion control demonstrate that our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score. More importantly, by switching video inputs, we find our method can rapidly learn diverse motion behaviors such as walking and running. Copyright © 2024, The Authors. All rights reserved.

关键词： Robots

Efficient STL control Synthesis under Asynchronous Temporal Robustness Constraints

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yu, Xinyi Yin, Xiang Lindemann, Lars Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai200240 China Thomas Lord Department of Computer Science University of Southern California Los AngelesCA90089 United States

In time-critical systems, such as air traffic control systems, it is crucial to design control policies that are robust to timing uncertainty. Recently, the notion of Asynchronous Temporal Robustness (ATR) was proposed to capture the robustness of a system trajectory against individual time shifts in its sub-trajectories. In a multi-robot system, this may correspond to individual robots being delayed or early. control synthesis under ATR constraints is challenging and has not yet been addressed. In this paper, we propose an efficient control synthesis method under ATR constraints which are defined with respect to simple safety or complex signal temporal logic specifications. Given an ATR bound, we compute a sequence of control inputs so that the specification is satisfied by the system as long as each sub-trajectory is shifted not more than the ATR bound. We avoid combinatorially exploring all shifted sub-trajectories by first identifying redundancy between them. We capture this insight by the notion of instant-shift pair sets, and then propose an optimization program that enforces the specification only over the instant-shift pair sets. We show soundness and completeness of our method and analyze its computational complexity. Finally, we present various illustrative case studies. Copyright © 2023, The Authors. All rights reserved.

关键词： Trajectories

Language-Queried Target Sound Extraction Without Parallel Training Data

学校读者我要写书评

暂无评论

Language-Queried Target Sound Extraction Without Parallel Tr...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Hao Ma Zhiyuan Peng Xu Li Yukai Li Mingjie Shao Qiuqiang Kong Ju Liu School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University North Carolina USA ARC Lab Tencent PCG Key Laboratory of System and Control AMSS Chinese Academy of Sciences Beijing China The Chinese University of Hong Kong China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are labor-intensive. We introduce a parallel-data-free training scheme, requiring only unlabelled audio clips for TSE model training by utilizing the contrastive language-audio pre-trained model (CLAP). In a vanilla parallel-data-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding, while during testing, user language queries are encoded by CLAP text encoder as the condition embedding. This vanilla approach assumes perfect alignment between text and audio embeddings, which is unrealistic. Two major challenges arise from training-testing mismatch: the persistent modality gap between text and audio and the risk of overfitting due to the exposure of rich acoustic details in target audio embedding during training. To address this, we propose a retrieval-augmented strategy. Specifically, we create an embedding cache using audio captions generated by a large language model (LLM). During training, target audio embeddings retrieve text embeddings from this cache to use as condition embeddings, ensuring consistent modalities between training and testing and eliminating information leakage. Extensive experiment results show that our retrieval-augmented approach achieves consistent and notable performance improvements over existing state-of-the-art with better generalizability.

关键词： Training Large language models Training data Signal processing Information leakage Acoustics Data models Data mining Speech processing Overfitting

Strike a Balance in Continual Panoptic Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Jinpeng Cong, Runmin Luo, Yuxuan Ip, Horace Ho Shing Kwong, Sam Department of Computer Science City University of Hong Kong Hong Kong School of Control Science and Engineering Shandong University Shandong Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Shandong Jinan China Centre for Innovative Applications of Internet and Multimedia Technologies City University of Hong Kong Hong Kong Lingnan University Hong Kong

This study explores the emerging area of continual panoptic segmentation, highlighting three key balances. First, we introduce past-class backtrace distillation to balance the stability of existing knowledge with the adaptability to new information. This technique retraces the features associated with past classes based on the final label assignment results, performing knowledge distillation targeting these specific features from the previous model while allowing other features to flexibly adapt to new information. Additionally, we introduce a class-proportional memory strategy, which aligns the class distribution in the replay sample set with that of the historical training data. This strategy maintains a balanced class representation during replay, enhancing the utility of the limited-capacity replay sample set in recalling prior classes. Moreover, recognizing that replay samples are annotated only for the classes of their original step, we devise balanced anti-misguidance losses, which combat the impact of incomplete annotations without incurring classification bias. Building upon these innovations, we present a new method named Balanced Continual Panoptic Segmentation (BalConpas). Our evaluation on the challenging ADE20K dataset demonstrates its superior performance compared to existing state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

A Performance-Based Model Recovery Anti-Windup Design for Linear systems Subject to Actuator Saturation

学校读者我要写书评

暂无评论

A Performance-Based Model Recovery Anti-Windup Design for Li...

American control Conference (ACC)

作者： Wenxin Lai Yuanlong Li Zongli Lin Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China Charles L. Brown Department of Electrical and Computer Engineering University of Virginia Char-lottesville VA U.S.A.

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

In this paper, we investigate the problem of reference tracking for a class of linear systems subject to actuator saturation and propose a performance-based model recovery anti-windup strategy. We adopt the classic model recovery anti-windup framework and regard the states or one of the outputs of the anti-windup compensator as the tracking error, by which the difference between the unconstrained system and the saturated system is quantified. Then, instead of employing the commonly used $\mathcal{L}_{2}$ gain, we present the prescribed performance functions (PPFs) to characterize the real-time tracking error such that the system performance can be captured more specifically. In particular, to avoid singular issues arising from the occurrence of saturation, we modify the existing PPFs with an auxiliary system when saturation occurs. Based on these modified performance functions, we follow a modified prescribed performance control approach and design the remaining output of the anti-windup compensator. Such a design procedure is constructive, making it more promising for extension to nonlinear systems. Theoretical results establish the boundedness of all signals in the closed-loop system. Simulation results verify the effectiveness of our design strategy.

关键词： Linear systems Actuators Simulation system performance Stability analysis Real-time systems Trajectory

Prototype Guided Personalized Federated Intrusion Detection system

学校读者我要写书评

暂无评论

Prototype Guided Personalized Federated Intrusion Detection ...

Smart World Congress (SWC), IEEE

作者： Long Cheng Huiru Yan Hanlin Zhou Ying Wang Haichuan Tang Fang Fang State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering North China Electric Power University Beijing China Chinese Academy of Sciences Institute of Computing Technology Beijing China AI Lab of CRRC Academy Beijing China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

Preventing network attacks and protecting user privacy are consistently hot research topics in the Internet of Things (IoT) and edge computing fields. Recent advancements in Federated Learning (FL) have shown promise in addressing these challenges. FL allows various clients to collaboratively build an intrusion detection system (IDS) without sharing their private data. However, most existing methods train a single intrusion detection model for all clients and assume that the training and test data distribution are identical, leading to unsatisfactory detection accuracy and generalization abilities in practice. To overcome these challenges, this paper introduces a prototype-guided personalized FL approach named PG-FedIDS. We propose two novel mechanisms within this method. Firstly, we utilize class prototypes as auxiliary information carriers to generate personalized models for each client, rather than generating a single global model as in previous works. Secondly, we propose a prototype-guided ensemble learning strategy, which can leverage the global knowledge in prototypes to enhance detection accuracy and generalization abilities for each client. We conduct extensive experiments on two benchmark datasets with different evaluation test settings. The results demonstrate that our PG-FedIDS achieves promising detection accuracy and consistently outperforms other FL baselines.

关键词： Training Privacy Accuracy Federated learning Image edge detection Prototypes Intrusion detection Data models Ensemble learning Internet of Things

RBP-Former: Joint Prediction of RNA-protein Binding Sites on Full-length RNA Transcripts for Multiple RBPs

学校读者我要写书评

暂无评论

RBP-Former: Joint Prediction of RNA-protein Binding Sites on...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yichong Li Xiaojian Liu Fan Cheng Xiaoyong Pan Yang Yang Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

RNA-binding proteins (RBPs) are essential for gene expression, and the complex RNA-protein interaction mechanisms require analysis of global RNA information. Therefore, accurate prediction of RBP binding sites on full-length RNA transcripts is crucial for understanding these mechanisms and their roles in diseases. While machine learning methods can predict RBP binding to RNA fragments, extending this to full-length transcripts presents challenges due to sequence length and data imbalance. In this paper, we introduce RBP-Former, a binding site joint prediction model designed specifically for full-length RNA transcripts that can be used for multiple RBPs. This model processes information at both coarse and fine-grained levels to fully exploit sequence data and its interactions with multiple RBPs. We develop multi-level imbalance learning strategies, achieving favorable results on imbalanced data. Our method outperforms existing methods in predicting binding sites on full-length RNA transcripts for multiple RBPs, demonstrating its effectiveness in handling imbalanced label and sample distributions.

关键词： Proteins Protein engineering Accuracy RNA Machine learning Predictive models Data models Gene expression Bioinformatics Diseases

TIME PERIODIC SOLUTIONS TO THE EVOLUTIONARY OSEEN MODEL FOR A GENERALIZED NEWTONIAN INCOMPRESSIBLE FLUID

学校读者我要写书评

暂无评论

Acta Mathematica Scientia 2023年第4期43卷 1645-1667页

作者：岑金夏 Stanislaw MIGóRSKI Emilio VILCHES 曾生达 School of Mathematical Sciences Zhejiang Normal UniversityJinhua 321004China Jagiellonian University in Krakow Chair of Optimization and Controlul.Lojasiewicza 630348 KrakowPoland Instituto de Ciencias de la Ingenier´ıa Universidad de O’HigginsAv.Libertador Bernardo OHiggins 6112841959 RancaguaChile Guangxi Colleges and Universities Key Laboratory of Complex System Optimization and Big Data Processing Yulin Normal UniversityYulin 537000China Department of Mathematics Nanjing University Nanjing 210093China Jagiellonian University in Krakow Faculty of Mathematics and Computer Scienceul.Lojasiewicza 630348 KrakowPoland

In this paper we study a nonstationary Oseen model for a generalized Newtonian incompressible fluid with a time periodic condition and a multivalued,nonmonotone friction ***,a variational formulation of the model is obtained;that is a nonlinear boundary hemivariational inequality of parabolic type for the velocity ***,an abstract first-order evolutionary hemivariational inequality in the framework of an evolution triple of spaces is *** mild assumptions,the nonemptiness and weak compactness of the set of periodic solutions to the abstract inequality are ***,a uniqueness theorem for the abstract inequality is established by using a monotonicity ***,we employ the theoretical results to examine the nonstationary Oseen model.

关键词： nonstationary Oseen model Newtonian incompressible fluid hemivariational inequality periodic solution generalized subgradient