检索结果-内蒙古大学图书馆

Experimental Validation of Functional Iterative Learning control on a One-Link Flexible Arm

学校读者我要写书评

暂无评论

Experimental Validation of Functional Iterative Learning Con...

IEEE International Conference on robotics and Automation (ICRA)

作者： Sjoerd Drost Pietro Pustina Franco Angelini Alessandro De Luca Gerwin Smit Cosimo Della Santina Department of Cognitive Robotics Delft University of Technology Delft Netherlands Department of Computer Control and Management Engineering Sapienza University of Rome Rome Italy Department of Information Engineering Research Center “Enrico Piaggio” University of Pisa Pisa Italy Institute of Robotics and Mechatronics German Aerospace Center (DLR) Oberpfaffenhofen Germany

Performing precise, repetitive motions is essential in many robotic and automation systems. Iterative learning control (ILC) allows determining the necessary control command by using a very rough system model to speed up the process. Functional iterative learning control is a novel technique that promises to solve several limitations of classic ILC. It operates by merging the input space into a large functional space, resulting in an over-determined control task in the iteration domain. In this way, it can deal with systems having more outputs than inputs and accelerate the learning process without resorting to model discretizations. However, the framework lacks so far a validation in experiments. This paper aims to provide such experimental validation in the context of robotics. To this end, we designed and built a one-link flexible arm that is actuated by a stepper motor, which makes the development of an accurate model more challenging and the validation closer to the industrial practice. We provide multiple experimental results across several conditions, proving the feasibility of the method in practice.

关键词：

iMTSP: Solving Min-Max Multiple Traveling Salesman Problem with Imperative Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Yifan Ren, Zhongqiang Wang, Chen The Flight Dynamics & Control/Hybrid Systems Lab Purdue University West LafayetteIN47907 United States Robotics Institute Carnegie Mellon University PittsburghPA15213 United States Lab Department of Computer Science and Engineering University at Buffalo NY14260 United States

This paper considers a Min-Max Multiple Traveling Salesman Problem (MTSP), where the goal is to find a set of tours, one for each agent, to collectively visit all the cities while minimizing the length of the longest tour. Though MTSP has been widely studied, obtaining near-optimal solutions for large-scale problems is still challenging due to its NP-hardness. Recent efforts in data-driven methods face challenges of the need for hard-to-obtain supervision and issues with high variance in gradient estimations, leading to slow convergence and highly sub-optimal solutions. We address these issues by reformulating MTSP as a bilevel optimization problem, using the concept of imperative learning (IL). This involves introducing an allocation network that decomposes the MTSP into multiple single-agent traveling salesman problems (TSPs). The longest tour from these TSP solutions is then used to self-supervise the allocation network, resulting in a new self-supervised, bilevel, end-to-end learning framework, which we refer to as imperative MTSP (iMTSP). Additionally, to tackle the high-variance gradient issues during the optimization, we introduce a control variate-based gradient estimation algorithm. Our experiments showed that these innovative designs enable our gradient estimator to converge 20× faster than the advanced reinforcement learning baseline, and find up to 80% shorter tour length compared with Google OR-Tools MTSP solver, especially in large-scale problems (e.g. 1000 cities and 15 agents). © 2024, CC BY.

关键词： Traveling salesman problem

DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Prior

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Mingrui Liu, Shuhong Deng, Tianchen Wang, Hongyu the Department of Computer Science Dalian University of Technology Dalian China the Department of Mechano-informatics Information Science and Technology The University of Tokyo Tokyo Japan Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education China

Gaussian SLAM systems excel in real-time rendering and fine-grained reconstruction compared to NeRF-based systems. However, their reliance on extensive keyframes is impractical for deployment in real-world robotic systems, which typically operate under sparse-view conditions that can result in substantial holes in the map. To address these challenges, we introduce DenseSplat, the first SLAM system that effectively combines the advantages of NeRF and 3DGS. DenseSplat utilizes sparse keyframes and NeRF priors for initializing primitives that densely populate maps and seamlessly fill gaps. It also implements geometry-aware primitive sampling and pruning strategies to manage granularity and enhance rendering efficiency. Moreover, DenseSplat integrates loop closure and bundle adjustment, significantly enhancing frame-to-frame tracking accuracy. Extensive experiments on multiple large-scale datasets demonstrate that DenseSplat achieves superior performance in tracking and mapping compared to current state-of-the-art methods. © 2025, CC BY.

关键词： Real time systems

Multi-Agent Distributed DQN and Transfer Learning for Energy-Efficient Power Management in Solar Energy-Harvested Small-Cell Networks

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2025年

作者： Cho, Hyebin Kim, Hyungsub Na, JeeHyeon Lim, Seung-Chan Lee, Howon Hankyong National University School of Electrical Electronic and Control Engineering Anseong17579 Korea Republic of Electronics and Telecommunications Research Institute Daejeon34141 Korea Republic of Hankyong National University School of ICT Robotics and Mechanical Engineering and IITC Anseong17579 Korea Republic of Ajou University Department of Electrical and Computer Engineering Suwon16499 Korea Republic of

The integration of solar energy harvesting into small-cell networks is a promising solution for achieving energy-efficient and sustainable wireless communications. However, the inherent variability and intermittency of solar energy, coupled with precise inter-cell interference management, significantly hinder efficient network operation. To resolve these challenges, we propose a multi-agent distributed deep Q-network (MA-DDQN) framework, where the distributed base stations learn the optimal transmit power control policies. To further enhance adaptability under varying solar conditions, we present a daily model transfer with a fine-tuning approach, enabling efficient deployment without extensive training overhead. Simulation results demonstrate that the proposed methods remarkably improve energy efficiency while maintaining robust adaptability under dynamic solar conditions, revealing their potential for sustainable small-cell network deployments. © 2014 IEEE.

关键词： Solar cell efficiency

Learning Goal-based Movement via Motivational-based Models in Cognitive Mobile Robots

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Berto, Letícia Costa, Paula Simões, Alexandre Gudwin, Ricardo Colombini, Esther Laboratory of Robotics and Cognitive Systems Institute of Computing University of Campinas Brazil Dept. of Computer Engineering and Industrial Automation School of Electrical and Computer Engineering University of Campinas Brazil Dept. of Control and Automation Engineering Institute of Science and Technology São Paulo State University Sorocaba Brazil University of Campinas Brazil

Humans have needs motivating their behavior according to intensity and context. However, we also create preferences associated with each action’s perceived pleasure, which is susceptible to changes over time. This makes decision-making more complex, requiring learning to balance needs and preferences according to the context. To understand how this process works and enable the development of robots with a motivational-based learning model, we computationally model a motivation theory proposed by Hull. In this model, the agent (an abstraction of a mobile robot) is motivated to keep itself in a state of homeostasis. We added hedonic dimensions to see how preferences affect decision-making, and we employed reinforcement learning to train our motivated-based agents. We run three agents with energy decay rates representing different metabolisms in two different environments to see the impact on their strategy, movement, and behavior. The results show that the agent learned better strategies in the environment that enables choices more adequate according to its metabolism. The use of pleasure in the motivational mechanism significantly impacted behavior learning, mainly for slow metabolism agents. When survival is at risk, the agent ignores pleasure and equilibrium, hinting at how to behave in harsh scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Metabolism

Fault Diagnostic Opportunities for Robot Servo Motors Using the Physics of Failure Analysis

学校读者我要写书评

暂无评论

Fault Diagnostic Opportunities for Robot Servo Motors Using ...

International Conference on Reliability, Maintainability and Safety,ICRMS

作者： Bo Zhang Shan Liang Kai Wang Key Laboratory of Networked Control Systems Shenyang Institute of Automation Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China College of Computer Science and Technology University of Chemical Technology Chinese Academy of Sciences Shenyang China

ISBN: (数字)9798350329988

ISBN: (纸本)9798350329995

Joint robots are widely used in various industries, such as aviation, aerospace, and automotive manufacturing. The performance degradation of servo motors can significantly affect the overall performance of the robots because of the core component of joint robots, and therefore, it is critical to detect and address servo motor failures promptly. In this study, we analyze some common causes and mechanisms of performance degradation in robot servo motors using the physics of failure analysis. We also discuss strategies for detecting and diagnosing faults using these mechanisms before the servo motors fail completely.

关键词： Degradation Industries Service robots Failure analysis Safety Manufacturing Reliability Servomotors Physics Automotive engineering

A Design for Improvement of Visual SLAM in Dynamic Environments Using Feature-Point Removal of Moving Persons

学校读者我要写书评

暂无评论

A Design for Improvement of Visual SLAM in Dynamic Environme...

International Automatic control Conference

作者： Kai-Tai Song Ching-Hao Meng Institute of Electrical and Control Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Graduate Degree Program of Robotics College of Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

This paper presents a design to improve the robustness of visual SLAM(vSLAM). A processing step of feature-removal is added to the tracking thread of the conventional ORB-SLAM2 algorithm to improve the localization accuracy of a mobile robot in an environment with moving persons. Instance segmentation and motion tracking are intergrated to identify motion state of people in an image. ORB feature points belonging to moving persons are removed for further processing of the vSLAM pipeline. The advantage of this method is that the vSLAM can remove feature points of moving people, while retain those belonging to static people in the environment, which improves the accuracy of robot pose estimation. The improved ORB-SLAM2 algorithm has been implemented in a NVIDIA Xavier embedded system, which is integrated to a mobile robot. In practical robot navigation experiments, the average positioning error of the proposed method is within 4cm for 22.4m travel distance. Compared with conventional ORB-SLAM2, the average accuracy of our vSLAM method improves 97% in a dynamic environment with moving people.

关键词：

HiER: Highlight Experience Replay for Boosting Off-Policy Reinforcement Learning Agents

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Horváth, Dániel Martín, Jesús Bujalance Erdos, Ferenc Gábor Istenes, Zoltán Moutarde, Fabien Center for Robotics MINES Paris PSL University Paris75272 France Centre of Excellence in Production Informatics and Control Institute for Computer Science and Control Hungarian Research Network Budapest1111 Hungary CoLocation Center for Academic and Industrial Cooperation Eötvös Loránd University Budapest1117 Hungary

Even though reinforcement-learning-based algorithms achieved superhuman performance in many domains, the field of robotics poses significant challenges as the state and action spaces are continuous, and the reward function is predominantly sparse. Furthermore, on many occasions, the agent is devoid of access to any form of demonstration. Inspired by human learning, in this work, we propose a method named highlight experience replay (HiER) that creates a secondary highlight replay buffer for the most relevant experiences. For the weights update, the transitions are sampled from both the standard and the highlight experience replay buffer. It can be applied with or without the techniques of hindsight experience replay (HER) and prioritized experience replay (PER). Our method significantly improves the performance of the state-of-the-art, validated on 8 tasks of three robotic benchmarks. Furthermore, to exploit the full potential of HiER, we propose HiER+ in which HiER is enhanced with an arbitrary data collection curriculum learning method. Our implementation, the qualitative results, and a video presentation are available on the project site: http://***/hier/. © 2023, CC BY-NC-ND.

关键词： Reinforcement learning

Fully Decentralized Design of Initialization-free Distributed Network Size Estimation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lee, Donggil Kim, Taekyoo Lee, Seungjoon Shim, Hyungbo Center for Intelligent and Interactive Robotics Korea Institute of Science and Technology Seoul02792 Korea Republic of The Train Control and Communication Team Korea Railroad Research Institute Uiwang16105 Korea Republic of NAVER Labs Seongnam13161 Korea Republic of ASRI Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of

In this paper, we propose a distributed scheme for estimating the network size, which refers to the total number of agents in a network. By leveraging a synchronization technique for multi-agent systems, we devise an agent dynamics that ensures convergence to an equilibrium point located near the network size regardless of its initial condition. Our approach is based on an assumption that each agent has a unique identifier, and an estimation algorithm for obtaining the largest identifier value. By adopting this approach, we successfully implement the agent dynamics in a fully decentralized manner, ensuring accurate network size estimation even when some agents join or leave the network. © 2024, CC BY-NC-ND.

关键词： Multi agent systems