检索结果-内蒙古大学图书馆

Diagnosing and Augmenting Feature Representations in Correctional Inverse Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lourenço, Inês Bobu, Andreea Rojas, Cristian R. Wahlberg, Bo The Division of Decision and Control Systems Kth Royal Institute of Technology Stockholm Sweden The Department of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA United States

Robots have been increasingly better at doing tasks for humans by learning from their feedback, but still often suffer from model misalignment due to missing or incorrectly learned features. When the features the robot needs to learn to perform its task are missing or do not generalize well to new settings, the robot will not be able to learn the task the human wants and, even worse, may learn a completely different and undesired behavior. Prior work shows how the robot can detect when its representation is missing some feature and can, thus, ask the human to be taught about the new feature;however, these works do not differentiate between features that are completely missing and those that exist but do not generalize to new environments. In the latter case, the robot would detect misalignment and simply learn a new feature, leading to an arbitrarily growing feature representation that can, in turn, lead to spurious correlations and incorrect learning down the line. In this work, we propose separating the two sources of misalignment: we propose a framework for determining whether a feature the robot needs is incorrectly learned and does not generalize to new environment setups vs. is entirely missing from the robot's representation. Once we detect the source of error, we show how the human can initiate the realignment process for the model: if the feature is missing, we follow prior work for learning new features;however, if the feature exists but does not generalize, we use data augmentation to expand its training and, thus, complete the correction. We demonstrate the proposed approach in experiments with a simulated 7DoF robot manipulator and physical human corrections. Copyright © 2023, The Authors. All rights reserved.

关键词： Manipulators

Scalable and low-cost remote lab platforms: Teaching industrial robotics using open-source tools and understanding its social implications

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kumar, Amit Jose, Jaison Jain, Archit Kulkarni, Siddharth Arya, Kavi Centre for Systems and Control Indian Institute of Technology Bombay Mumbai India Embedded Real-Time Systems / e-Yantra Lab. Indian Institute of Technology Bombay Mumbai India Computer Science and Engineering Department Indian Institute of Technology Bombay Mumbai India

With recent advancements in industrial robots, educating students in new technologies and preparing them for the future is imperative. However, access to industrial robots for teaching poses challenges, such as the high cost of acquiring these robots, the safety of the operator and the robot, and complicated training material. This paper proposes two low-cost platforms built using open-source tools like Robot Operating System (ROS) and its latest version ROS 2 to help students learn and test algorithms on remotely connected industrial robots. Universal Robotics (UR5) arm and a custom mobile rover were deployed in different life-size testbeds, a greenhouse, and a warehouse to create an Autonomous Agricultural Harvester System (AAHS) and an Autonomous Warehouse Management System (AWMS). These platforms were deployed for a period of 7 months and were tested for their efficacy with 1,433 and 1,312 students, respectively. The hardware used in AAHS and AWMS was controlled remotely for 160 and 355 hours, respectively, by students over a period of 3 months. © 2024, CC BY.

关键词： Costs

Differentially Private Dual Gradient Tracking for Distributed Resource Allocation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huo, Wei Chen, Xiaomeng Huang, Lingying Johansson, Karl Henrik Shi, Ling Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong School of Electrical and Electronic Engineering Nanyang Technology University Singapore639798 Singapore Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden

This paper investigates privacy issues in distributed resource allocation over directed networks, where each agent holds a private cost function and optimizes its decision subject to a global coupling constraint through local interaction with other agents. Conventional methods for resource allocation over directed networks require all agents to transmit their original data to neighbors, which poses the risk of disclosing sensitive and private information. To address this issue, we propose an algorithm called differentially private dual gradient tracking (DP-DGT) for distributed resource allocation, which obfuscates the exchanged messages using independent Laplacian noise. Our algorithm ensures that the agents’ decisions converge to a neighborhood of the optimal solution almost surely. Furthermore, without the assumption of bounded gradients, we prove that the cumulative differential privacy loss under the proposed algorithm is finite even when the number of iterations goes to infinity. To the best of our knowledge, we are the first to simultaneously achieve these two goals in distributed resource allocation problems over directed networks. Finally, numerical simulations on economic dispatch problems within the IEEE 14-bus system illustrate the effectiveness of our proposed algorithm. © 2024, CC BY.

关键词： Differential privacy

Improving finite-difference time-domain memory bandwidth by using block floating-point arithmetic

学校读者我要写书评

暂无评论

Improving finite-difference time-domain memory bandwidth by ...

Telecommunications Forum (TELFOR)

作者： Stefan Pijetlovic Ivan Kastelan Milos Subotic Nebojsa Pjevalica RT-RK Institute for computer based systems Novi Sad Serbia Department of Computing and control engineering (Faculty of Technical Sciences) University of Novi Sad Novi Sad Serbia

Finite-difference time-domain is a numerical method used for modelling of computational electrodynamics. The method is resource intensive, especially regarding memory usage since multiple memory accesses are required per single computation. In other words, memory, or more precisely its speed, is a limiting factor for the overall performance. Existing solutions focus either on structures with great parallelism such as graphical processing units or custom designs. The former have issues with underutilized resources, while the latter require significant time and effort to achieve similar or slightly better performances. The approach taken during this research was to target the memory itself and find a way to improve the efficiency of memory usage across multiple platforms. The main contribution of the paper is using block floating-point in a novel way regarding the finite-difference time-domain method. The presented solution is a verification of earlier research, proving that the performance of this algorithm can indeed be improved using the suggested methods.

关键词：

On modal observers for beyond rigid body H∞ control in high-precision mechatronics*

学校读者我要写书评

暂无评论

On modal observers for beyond rigid body H∞ control in high...

IEEE Conference on Decision and control

作者： Yorick Broens Hans Butler Roland Tóth Department of Electrical Engineering Eindhoven University of Technology Eindhoven The Netherlands ASML Veldhoven The Netherlands Systems and Control Laboratory Institute for Computer Science and Control Hungary

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

The ever increasing need for performance results in increasingly rigorous demands on throughput and positioning accuracy of high-precision motion systems, which often suffer from position dependent effects that originate from relative actuation and sensing of the moving-body. Due to the highly stiff mechanical design, such systems are typically controlled using rigid body control design approaches. Nonetheless, the presence of position dependent flexible dynamics severely limits attainable position tracking performance. This paper presents two extensions of the conventional rigid body control framework towards active control of position dependent flexible dynamics. Additionally, a novel control design approach is presented, which allows for shaping of the full closed-loop system by means of structured H ∞ co-design. The effectiveness of the approach is validated through simulation using a high-fidelity model of a state-of-the-art moving-magnet planar actuator.

关键词： Linear systems Mechatronics Costs control design Tracking Dynamics Observers

Adaptive Sampling of Algal Blooms Using Autonomous Underwater Vehicle and Satellite Imagery: Experimental Validation in the Baltic Sea

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Fonseca, Joana Bhat, Sriharsha Lock, Matthew Stenius, Ivan Johansson, Karl H. The Division of Decision and Control Systems School of Electrical Engineering and Computer Science and Digital Futures Sweden The Department of Aeronautical and Vehicle Engineering School of Engineering Sciences Kth Royal Institute of Technology StockholmSE-100 44 Sweden

This paper investigates using satellite data to improve adaptive sampling missions, particularly for front tracking scenarios such as with algal blooms. Our proposed solution to find and track algal bloom fronts uses an Autonomous Underwater Vehicle (AUV) equipped with a sensor that measures the concentration of chlorophyll a and satellite data. The proposed method learns the kernel parameters for a Gaussian process (GP) model using satellite images of chlorophyll a from the previous days. Then, using the data collected by the AUV, it models chlorophyll a concentration online. We take the gradient of this model to obtain the direction of the algal bloom front and feed it to our control algorithm. The performance of this method is evaluated through realistic simulations for an algal bloom front in the Baltic sea, using the models of the AUV and the chlorophyll a sensor. We compare the performance of different estimation methods, from GP to curve interpolation using least squares. Sensitivity analysis is performed to evaluate the impact of sensor noise on the methods' performance. We implement our method on an AUV and run experiments in the Stockholm archipelago in the summer of 2022. Copyright © 2023, The Authors. All rights reserved.

关键词： Autonomous underwater vehicles

Probabilistic Tube-based control Synthesis of Stochastic Multi-Agent systems under Signal Temporal Logic

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Vlahakis, Eleftherios E. Lindemann, Lars Sopasakis, Pantelis Dimarogonas, Dimos V. Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden Thomas Lord Department of Computer Science Viterbi School of Engineering University of Southern California Los AngelesCA90089 United States School of Electronics Electrical Engineering and Computer Science Queen’s University Northern Ireland Belfast United Kingdom

We consider the control design of stochastic discrete-time linear multi-agent systems (MASs) under a global signal temporal logic (STL) specification to be satisfied at a predefined probability. By decomposing the dynamics into deterministic and error components, we construct a probabilistic reachable tube (PRT) as the Cartesian product of reachable sets of the individual error systems driven by disturbances lying in confidence regions (CRs) with a fixed probability. By bounding the PRT probability with the specification probability, we tighten all state constraints induced by the STL specification by solving tractable optimization problems over segments of the PRT, and relax the underlying stochastic problem with a deterministic one. This approach reduces conservatism compared to tightening guided by the STL structure. Additionally, we propose a recursively feasible algorithm to attack the resulting problem by decomposing it into agent-level subproblems, which are solved iteratively according to a scheduling policy. We demonstrate our method on a ten-agent system, where existing approaches are impractical. © 2024, CC BY.

关键词： Stochastic systems

Biological Influence of Low-Frequency Electromagnetic Field Exposition Based on Selected Cell Death Markers

学校读者我要写书评

暂无评论

Biological Influence of Low-Frequency Electromagnetic Field ...

ELEKTRO

作者： Robert Cichorowski Olga Kocikowska Marek Bajtoš Roman Radil Ladislav Janoušek Daria Gendosz De Carrillo Sebastian Student Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology liwice Poland Department of Engineering and Systems Biology Faculty of Automatic Control Electronics and Computer Science Gliwice Poland Department of Physiology Faculty of Medical Sciences Silesian University of Medicine Katowice Poland Department of Electromagnetic and Biomedical Engineering Faculty of Electrical Engineering and Informational Technology Žilina Slovakia Department of Histology Faculty of Medical Sciences in Zabrze Silesian University of Medicine Zabrze Poland Biotechnology Center Silesian University of Technology Gliwice Poland

ISBN: (数字)9798350372359

ISBN: (纸本)9798350372366

This work presents the results of the examination of the HeLa cell line exposure on the ELF-EMF (extremely low-frequency electromagnetic field). In particular, the relationship between ELF-EMF exposition time and cell death. The examination of cell death hallmarks were examined by estimation levels of selected proteins - FACL4 (a protein that is a part of the ferroptosis pathway) and CK18 (Cytokeratin related to necrosis and apoptosis pathways) in the proposed model of workers exposed to ELF-EMF week.

关键词： Proteins Biological system modeling Estimation Electromagnetic fields

LPV sequential loop closing for high-precision motion systems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Broens, Yorick Butler, Hans Tóth, Roland The Department of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands ASML Veldhoven Netherlands The Systems and Control Laboratory Institute for Computer Science and Control Hungary

Increasingly stringent throughput requirements in the industry necessitate the need for lightweight design of high-precision motion systems to allow for high accelerations, while still achieving accurate positioning of the moving-body. The presence of position dependent dynamics in such motion systems severely limits achievable position tracking performance using conventional sequential loop closing (SLC) control design strategies. This paper presents a novel extension of the conventional SLC design framework towards linear-parameter-varying systems, which allows to circumvent limitations that are introduced by position dependent effects in high-precision motion systems. Advantages of the proposed control design approach are demonstrated in simulation using a high-fidelity model of a moving-magnet planar actuator system, which exhibits position dependency in both actuation and *** Codes 93-06 © 2022, CC BY.

关键词： Linear systems