检索结果-内蒙古大学图书馆

Automated loading of a hydraulic excavator using nonlinear model predictive control with preference-based calibration

引用

SICE JOURNAL OF CONTROL MEASUREMENT AND SYSTEM INTEGRATION 2023年第1期16卷 247-256页

作者： Ishihara, Shinji Ohtsuka, Toshiyuki Hitachi Ltd Omika cho Hitachi Ibaraki Japan Kyoto Univ Kyoto Japan

This study deals with the control methods for automating the operation of a hydraulic excavator loading soil onto the bed of a dump truck. The loading operation requires moving the bucket to a target position without contacting the dump truck. In addition, there is a demand to minimize soil spillage during the loading process. We applied Model Predictive Control (MPC) using constraints of the hydraulic excavator and objective functions corresponding to the requirements of the loading problem. To achieve the desired behaviour using MPC, the weights of the objective function need to be tuned appropriately. Tuning these weights is not an easy task, even for control engineers. To solve this problem, we utilize a weight tuning method based on preference learning. Using this tuning method, the weights can be tuned by repeating the process of selecting the result that the user finds preferable from pairwise tuning results. To confirm the effectiveness of the proposed method, weight tuning experiments were conducted in a simulation environment with multiple users with different levels of skill and knowledge. Through these experiments, we confirmed that each user was able to tune the weights to achieve a desired loading behaviour that appropriately reflected their preferences, independent of their levels of skill and knowledge.

关键词： Model predictive control automated excavator preference-based optimization

来源：评论

学校读者我要写书评

暂无评论

Optimizing the maintenance schedule for a vehicle fleet: a simulation-based case study

引用

ENGINEERING optimization 2022年第7期54卷 1258-1271页

作者： Wang, Yali Limmer, Steffen Van Nguyen, Duc Olhofer, Markus Back, Thomas Emmerich, Michael Leiden Univ Leiden Inst Adv Comp Sci Leiden Netherlands Honda Res Inst Europe GmbH Offenbach Germany

Vehicle fleets support a diverse array of functions and are increasing rapidly in the world of today. For a vehicle fleet, maintenance plays a critical role. In this article, an evolutionary algorithm is proposed to optimize the vehicle fleet maintenance schedule based on the predicted remaining useful lifetime (RUL) of vehicle components to reduce the costs of repairs, decrease maintenance downtime and make them safer for drivers. The multi-objective evolutionary algorithm (MOEA) is then enhanced to focus precisely on the preferred solutions. Moreover, stability is involved as another objective in the dynamic MOEA for handling the problem under changes in the environment. To implement the complete maintenance process, a simulator is developed that can define vehicles, predict the RUL of components and optimize the maintenance schedule in a rolling-horizon fashion. The results of the proposed MOEAs under different scenarios are reported and compared.

关键词： Multi-objective evolutionary optimization preference-based optimization dynamic optimization prognostic-based maintenance scheduling

来源：评论

学校读者我要写书评

暂无评论

Optimal physical human-robot collaborative controller with user-centric tuning

引用

CONTROL ENGINEERING PRACTICE 2023年第1期139卷

作者： Roveda, Loris Mantovani, Lorenzo Maccarini, Marco Braghin, Francesco Piga, Dario Univ Svizzera Italiana USI Scuola Univ Profess Svizzera Italiana SUPSI Ist Dalle Molle Intelligenza Artificiale IDSI IDSIA SUPSI CH-6928 Manno Switzerland Politecn Milan Dept Mech Engn Milan Italy

Collaborative robots are increasingly used in different fields of application to physically interact with the human (e.g., manufacturing, rehabilitation, etc.) In order to improve the physical collaboration performance, the interaction between the user and the robot must be safe, smooth, and intuitive. Indeed, this paper proposes a controller which is composed of three nested loops. A Passive Velocity Field Control (PVFC) defines the lowest control layer, ensuring the passivity of the system. The intermediate control layer is defined by a Cartesian impedance controller, managing the interaction between the user and the robot and sending to the PVFC a reference position. The outer layer is defined by a Linear Quadratic Regulator (LQR), detecting the intention of motion of the user and deforming accordingly the Cartesian impedance setpoint to follow such a motion. In addition, to enhance the collaboration performance for each user, a preference-based optimization approach is employed to tune the control parameters, implementing a human-centric tuning procedure. In such a way, the controller is customized for the specific user to establish the proper interaction with the robot. The proposed controller has been evaluated by making use of a Franka EMIKA panda robot as a test platform, comparing the achieved performance with a controller previously developed by some of the authors in a free-motion collaborative task along the z vertical direction. Achieved results show the improved performance obtained by the proposed controller. In addition, an assembly task has also been optimized to show the potential of the proposed control framework in complex and realistic situations.

关键词： Human-robot collaboration Optimal control Passive velocity field control Impedance control Intelligent control preference-based optimization

来源：评论

学校读者我要写书评

暂无评论

Targeting solutions in Bayesian multi-objective optimization: sequential and batch versions

引用

ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE 2020年第1-3期88卷 187-212页

作者： Gaudrie, David Le Riche, Rodolphe Picheny, Victor Enaux, Benoit Herbert, Vincent Grp PSA Velizy Villacoublay France Ecole Natl Super Mines CNRS LIMOS St Etienne France Prowler Io Cambridge England

Multi-objective optimization aims at finding trade-off solutions to conflicting objectives. These constitute the Pareto optimal set. In the context of expensive-to-evaluate functions, it is impossible and often non-informative to look for the entire set. As an end-user would typically prefer a certain part of the objective space, we modify the Bayesian multi-objective optimization algorithm which uses Gaussian Processes and works by maximizing the Expected Hypervolume Improvement, to focus the search in the preferred region. The cumulated effects of the Gaussian Processes and the targeting strategy lead to a particularly efficient convergence to the desired part of the Pareto set. To take advantage of parallel computing, a multi-point extension of the targeting criterion is proposed and analyzed.

关键词： Gaussian processes Bayesian optimization Computer experiments preference-based optimization Parallel optimization 65Kxx

来源：评论

学校读者我要写书评

暂无评论

Targeting Well-Balanced Solutions in Multi-Objective Bayesian optimization Under a Restricted Budget 12th

Targeting Well-Balanced Solutions in Multi-Objective Bayesia...

引用

12th International Conference on Learning and Intelligent optimization (LION)

作者： Gaudrie, D. Le Riche, R. Picheny, V Enaux, B. Herbert, V Grp PSA Velizy Villacoublay France Ecole Natl Super Mines CNRS LIMOS St Etienne France MIAT Inst Natl Rech Agron Toulouse France

ISBN: (纸本)9783030053482;9783030053475

Multi-objective optimization aims at finding trade-off solutions to conflicting objectives. These constitute the Pareto optimal set. In the context of expensive-to-evaluate functions, it is impossible and often non-informative to look for the entire set. As an end-user would typically prefer solutions with equilibrated trade-offs between the objectives, we define a Pareto front center. We then modify the Bayesian multi-objective optimization algorithm which uses Gaussian Processes to maximize the expected hypervolume improvement, to restrict the search to the Pareto front center. The cumulated effects of the Gaussian Processes and the center targeting strategy lead to a particularly efficient convergence to a critical part of the Pareto set.

关键词： Gaussian processes Parsimonious optimization Computer experiments preference-based optimization

来源：评论

学校读者我要写书评

暂无评论

preference-guided evolutionary algorithms for many-objective optimization

引用

INFORMATION SCIENCES 2016年 329卷 236-255页

作者： Goulart, Fillipe Campelo, Felipe Univ Fed Minas Gerais Grad Program Elect Engn BR-31270901 Belo Horizonte MG Brazil Univ Fed Minas Gerais Dept Elect Engn BR-31270901 Belo Horizonte MG Brazil

This paper presents a technique that incorporates preference information within the framework of multi-objective evolutionary algorithms for the solution of many-objective optimization problems. The proposed approach employs a single reference point to express the preferences of a decision maker, and adaptively biases the search procedure toward the region of the Pareto-optimal front that best matches its expectations. Experimental results suggest that incorporating preferences within these algorithms leads to improvements in several quality criteria, and that the proposed approach is capable of yielding competitive results when compared against existing algorithms. (C) 2015 Elsevier Inc. All rights reserved.

关键词： Multi-objective optimization Many-objective optimization preference-based optimization Evolutionary algorithms Decision making Reference point

来源：评论

学校读者我要写书评

暂无评论

Skyline computation on commercial data 8

Skyline computation on commercial data

引用

8th International Conference on Agents and Artificial Intelligence, ICAART 2016

作者： Galli, Michael Schniirle, Stefan Arnold, Ruedi Pouly, Marc Lucerne University of Applied Sciences and Arts Horw Switzerland

ISBN: (纸本)9789897581724

Many different skyline algorithms for preference-based search have been proposed and compared in the literature, but most of these evaluations were based on synthetic data. In this paper, we present a case study of skyline computation on commercial data that we consider representative for many e-commerce platforms. The results of our measurements differ significantly from the results reported on synthetic data. Copyright © 2016 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved.

关键词： Industrial application preference-based optimization Skyline computation

来源：评论

学校读者我要写书评

暂无评论

Preferred design of recurrent neural network architecture using a multiobjective evolutionary algorithm with un-supervised information recruitment: a paradigm for modeling shape memory alloy actuators

引用

MECCANICA 2014年第6期49卷 1297-1326页

作者： Mozaffari, Ahmad Fathi, Alireza Azad, Nasser Lashgarian Univ Waterloo Dept Syst Design Engn Waterloo ON N2L 3G1 Canada Babol Univ Technol Dept Mech Engn Babol Sar Iran

Shape memory alloys (SMAs) are able to compensate any undergoing plastic deformations and return to their memorized shape. Such a behavior persuades industrialists to use them for different engineering applications, as smart actuators and sensors. Because of their vast applications, it is crucial to engineers to develop effective identification tools capable of simulating the behavior of SMAs. However, SMA actuators have complex and hysteric behavior that in turn obstructs the modeling process. The motivation behind the current study emanates in the pursuit of developing efficient prediction tools for effective modeling of SMA actuators. Actually, after several experiments and software simulations, the authors develop a hybrid intelligent tool which takes advantage of the self-organizing Pareto based evolutionary algorithm (SOPEA) and simultaneous recurrent neural network (SRNN), as a black-box model, to automatically identify the behavior of SMA. SOPEA is a multiobjective evolutionary algorithm which is based on the concepts of survival of the fittest, non-dominated sorting and information recruitment. The information recruitment is guaranteed by applying an un-supervised neuro computing technique, i.e. adaptive self organizing map (ASOM) with conscience mechanism. ASOM is an un-supervised network that assists SOPEA to recognize the non-dominated patterns and produce further non-dominated solutions. Together with the structure of SOPEA, the authors follow a comprehensive preference-based strategy to exploit the desired regions in the Pareto front. This occurs through introducing deliberate reference points. The outcome method is applied to the design of SRNN for modeling the SMA actuator. It is demonstrated that the designed optimization tool can show acceptable performance for the present case study within the imposed computational budget. Besides, through a rigorous experimental procedure, it is indicated that by applying an efficient artificial system, the behav

关键词： Shape memory alloy (SMA) Self-organizing Pareto based evolutionary algorithm (SOPEA) Simultaneous recurrent neural network (SRNN) preference-based optimization

来源：评论

学校读者我要写书评

暂无评论

A preference-based Multi-objective Evolutionary Algorithm for Redundancy Allocation Problem 4

A Preference-based Multi-objective Evolutionary Algorithm fo...

引用

International Conference on IT Convergence and Security (ICITCS)

作者： Sudeng, Sufian Wattanapongsakorn, Naruemon King Mongkuts Univ Technol Thonburi Dept Comp Engn 126 Pracha Uthit Rd Bangkok 10140 Thailand

ISBN: (纸本)9781479965410

Allowing the decision maker (DM) incorporates his/her preferences in Multiobjective Evolutionary Algorithm (MOEA) is likely yield better approximation of optimal trade-off solutions for multi-objective optimization problem (MOP). In this paper, we propose a preference-based MOEA to help the DM choosing the final best solution(s) based on his/her preferred objective(s). Our algorithm is called ASA-NSGA-II. The approach is accomplished by replacing the crowding estimator technique in NSGA-II algorithm by applying an extended angle-based dominance technique. We consider Redundancy Allocation Problem (RAP) to observe the usefulness of our algorithm in practical context. The system composes of multiple subsystems connected in series. The designed objective is to select multiple components for a subsystem. The objective functions are to maximize system reliability (R), minimize system cost (C), and minimize system weight (W), simultaneously. We demonstrate seven cases of preferences with interesting results.

关键词： multi-objective optimization preference-based optimization evolutionary algorithm pareto-optimal solutions

来源：评论

学校读者我要写书评

暂无评论

Multiobjective optimization of Temporal Processes

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 2010年第3期40卷 845-856页

作者： Song, Zhe Kusiak, Andrew Univ Iowa Dept Mech & Ind Engn Iowa City IA 52242 USA

This paper presents a dynamic predictive-optimization framework of a nonlinear temporal process. Data-mining (DM) and evolutionary strategy algorithms are integrated in the framework for solving the optimization model. DM algorithms learn dynamic equations from the process data. An evolutionary strategy algorithm is then applied to solve the optimization problem guided by the knowledge extracted by the DM algorithm. The concept presented in this paper is illustrated with the data from a power plant, where the goal is to maximize the boiler efficiency and minimize the limestone consumption. This multiobjective optimization problem can be either transformed into a single-objective optimization problem through preference aggregation approaches or into a Pareto-optimal optimization problem. The computational results have shown the effectiveness of the proposed optimization framework.

关键词： Data mining (DM) dynamic modeling evolutionary algorithms (EAs) multiobjective optimization nonlinear temporal process power plant predictive control preference-based optimization

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：