Search | Engineering

订阅投稿

首页工程期刊工程焦点工程成就工程前沿关于我们 English

资源类型

期刊论文 318

年份

2023 18

2022 21

2021 20

2020 21

2019 24

2018 14

2017 29

2016 19

2015 17

2014 9

2013 18

2012 18

2011 8

2010 9

2009 3

2008 16

2007 10

2006 9

2005 3

2004 4

展开︾

关键词

发展战略 7

技术预见 4

乡村规划 3

可持续发展 3

规划 3

运动补偿 3

三峡工程 2

人工智能 2

以人为本 2

任务调度 2

创新 2

城市规划 2

对策建议 2

规划设计 2

路径规划 2

2008年北京奥运 1

2035年 1

A^*算法 1

CAPP 1

展开︾

检索范围：

排序：展示方式：

A novel task-oriented framework for dual-arm robotic assembly task

《机械工程前沿（英文）》 2021年第16卷第3期页码 528-545 doi: 10.1007/s11465-021-0638-2

摘要： In industrial manufacturing, the deployment of dual-arm robots in assembly tasks has become a trend. However, making the dual-arm robots more intelligent in such applications is still an open, challenging issue. This paper proposes a novel framework that combines task-oriented motion planning with visual perception to facilitate robot deployment from perception to execution and finish assembly problems by using dual-arm robots. In this framework, visual perception is first employed to track the effects of the robot behaviors and observe states of the workpieces, where the performance of tasks can be abstracted as a high-level state for intelligent reasoning. The assembly task and manipulation sequences can be obtained by analyzing and reasoning the state transition trajectory of the environment as well as the workpieces. Next, the corresponding assembly manipulation can be generated and parameterized according to the differences between adjacent states by combining with the prebuilt knowledge of the scenarios. Experiments are set up with a dual-arm robotic system (ABB YuMi and an RGB-D camera) to validate the proposed framework. Experimental results demonstrate the effectiveness of the proposed framework and the promising value of its practical application.

关键词： dual-arm assembly AI reasoning intelligent system task-oriented motion planning visual perception

HTML PDF 收藏

基于融合任务信息图神经网络的多智能体系统协同规划 Research Article

戴汉奇1,2,芦维宁2,李祥隆3,杨君1,孟德山4,刘衍泽5,梁斌1

《信息与电子工程前沿（英文）》 2022年第23卷第7期页码 1069-1076 doi: 10.1631/FITEE.2100597

摘要：协同规划是多智能体系统博弈领域的关键问题之一。本文聚焦每个智能体只有一个局部观测范围和局部通信情况下的协作规划。提出一种新型协同规划框架，该框架将图神经网络与融合任务信息采样方法相结合。本文的两个主要贡献是基于与前期工作的比较：（1）使用图采样与聚合方法（GraphSAGE）实现动态近邻智能体信息融合，这是该方法首次用于处理协同规划问题；（2）提出一种面向任务的采样方法，从特定方向聚合知识，使所提模型获得高效、稳定的训练过程。实验结果证明了所提方法的有效性。

关键词：多智能体系统；协同规划；图采样与聚合（GraphSAGE）；融合任务信息

HTML PDF 收藏

基于面向任务的协同特征向量的联盟形成算法 Article

Hao FANG,Shao-lei LU,Jie CHEN,Wen-jie CHEN

《信息与电子工程前沿（英文）》 2017年第18卷第1期页码 139-148 doi: 10.1631/FITEE.1601608

摘要：联盟形成是多智能体系统中一个重要的协同问题，对智能体的协同能力进行适当的描述是处理这个问题的一个基本且必要的前提。这篇文章对智能体的协同能力进行了建模，该模型由五个影响因素构成。同时，对任务需求向量进行了描述。提了一种随机机制以减少联盟形成过程中的过度竞争。此外，为了减少任务需求和实际任务需求之间的差距，提出了一种人工智能方法，该方法可以提高多智能体对人类指令的认知。实验结果显示了该模型及分布式人工智能方法的有效性。

关键词：协同向量；任务分配；多智能体系统；联盟形成；人工智能

HTML PDF 收藏

Offline motion planning and simulation of two-robot welding coordination

Tie ZHANG, Fan OUYANG

《机械工程前沿（英文）》 2012年第7卷第1期页码 81-92 doi: 10.1007/s11465-012-0309-4

摘要：

This paper focuses on the two-robot welding coordination of complex curve seam which means one robot grasp the workpiece, the other hold the torch, the two robots work on the same workpiece simultaneously. This paper builds the dual-robot coordinate system at the beginning, and three point calibration method of two robots’ relative base coordinate system is presented. After that, the non master/slave scheme is chosen for the motion planning, the non master/slave scheme sets the poses versus time function of the point u on the workpiece, and calculates the two robot end effecter trajectories through the constrained relationship matrix automatically. Moreover, downhand welding is employed which can guarantee the torch and the seam keep in good contact condition all the time during the welding. Finally, a Solidworks-SimMechanics simulation platform is established, and a simulation of curved steel pipe welding is conducted. The results of the simulation illustrate the welding process can meet the requirements of downhand welding, the joint displacement curves are smooth and continuous and no joint velocities are out of working scope.

关键词： complex curve seam two robots coordinated welding motion planning

HTML PDF 收藏

High-efficiency inspecting method for mobile robots based on task planning for heat transfer tubes in

《机械工程前沿（英文）》 2023年第18卷第2期 doi: 10.1007/s11465-022-0741-z

摘要： Many heat transfer tubes are distributed on the tube plates of a steam generator that requires periodic inspection by robots. Existing inspection robots are usually involved in issues: Robots with manipulators need complicated installation due to their fixed base; tube mobile robots suffer from low running efficiency because of their structural restricts. Since there are thousands of tubes to be checked, task planning is essential to guarantee the precise, orderly, and efficient inspection process. Most in-service robots check the task tubes using row-by-row and column-by-column planning. This leads to unnecessary inspections, resulting in a long shutdown and affecting the regular operation of a nuclear power plant. Therefore, this paper introduces the structure and control system of a dexterous robot and proposes a task planning method. This method proceeds into three steps: task allocation, base position search, and sequence planning. To allocate the task regions, this method calculates the tool work matrix and proposes a criterion to evaluate a sub-region. And then all tasks contained in the sub-region are considered globally to search the base positions. Lastly, we apply an improved ant colony algorithm for base sequence planning and determine the inspection orders according to the planned path. We validated the optimized algorithm by conducting task planning experiments using our robot on a tube sheet. The results show that the proposed method can accomplish full task coverage with few repetitive or redundant inspections and it increases the efficiency by 33.31% compared to the traditional planning algorithms.

关键词： steam generator transfer tubes mobile robot dexterous structure task planning efficient inspection

HTML PDF 收藏

运动规划的高效配置空间构建与优化 Article

潘佳, Dinesh Manocha

《工程（英文）》 2015年第1卷第1期页码 46-57 doi: 10.15302/J-ENG-2015009

摘要：

配置空间是算法机器人学领域使用较为广泛的一种基本概念。机器人学、计算机辅助设计与相关领域的诸多应用都可归类为配置空间方面的计算问题。本文将对近期与配置空间相关的两项重大挑战的解决方案成果进行探讨：①如何高效计算高维配置空间的近似表达；②如何在高维配置空间内高效执行几何学接近度与运动规划查询。基于机器学习与几何学近似技术，笔者在此提出几种新型配置空间构建算法。上述算法对多个配置样本进行碰撞查询。得出的碰撞查询结果将用来计算配置空间的近似表达，可快速聚合至准确的配置空间；同时还提出了基于并行图形处理器（GPU）的算法，以便加速配置空间优化与搜索计算的性能情况。笔者特别设计出了基于GPU的并行k最近邻算法与并行碰撞检测算法，并使用这些算法来加快运动规划。

关键词：配置空间运动规划图形处理器（GPU）并行算法

HTML PDF 收藏

Strategy for robot motion and path planning in robot taping

Qilong YUAN,I-Ming CHEN,Teguh Santoso LEMBONO,Simon Nelson LANDÉN,Victor MALMGREN

《机械工程前沿（英文）》 2016年第11卷第2期页码 195-203 doi: 10.1007/s11465-016-0390-1

摘要：

Covering objects with masking tapes is a common process for surface protection in processes like spray painting, plasma spraying, shot peening, etc. Manual taping is tedious and takes a lot of effort of the workers. The taping process is a special process which requires correct surface covering strategy and proper attachment of the masking tape for an efficient surface protection. We have introduced an automatic robot taping system consisting of a robot manipulator, a rotating platform, a 3D scanner and specially designed taping end-effectors. This paper mainly talks about the surface covering strategies for different classes of geometries. The methods and corresponding taping tools are introduced for taping of following classes of surfaces: Cylindrical/extended surfaces, freeform surfaces with no grooves, surfaces with grooves, and rotational symmetrical surfaces. A collision avoidance algorithm is introduced for the robot taping manipulation. With further improvements on segmenting surfaces of taping parts and tape cutting mechanisms, such taping solution with the taping tool and the taping methodology can be combined as a very useful and practical taping package to assist humans in this tedious and time costly work.

关键词： robot taping path planning robot manipulation 3D scanning

HTML PDF 收藏

A robot fuzzy motion planning approach in unknown environments

FU Yi-li, JIN Bao, LI Han, WANG Shu-guo

《机械工程前沿（英文）》 2006年第1卷第3期页码 336-340 doi: 10.1007/s11465-006-0033-z

摘要： A fuzzy robot motion planning approach is proposed in unknown environments for three-degree industrial robots. The proposed planning system is composed of several separate fuzzy units, which control individually each manipulator joint. Each unit combines a repelling influence, which is related to the nearby obstacle, with the attracting influence produced by the final manipulator configuration, to generate actuating command for each link. Effectiveness of the proposed approach is verified through simulation.

关键词： manipulator repelling influence manipulator configuration three-degree industrial simulation

HTML PDF 收藏

机器人任务规划：基于PDDL和ASP的任务规划系统实验比较研究 Special Feature on Intelligent Robats

Yu-qian JIANG, Shi-qi ZHANG, Piyush KHANDELWAL, Peter STONE

《信息与电子工程前沿（英文）》 2019年第20卷第3期页码 363-373 doi: 10.1631/FITEE.1800514

摘要：本文比较了目前最先进的基于规划领域定义语言（planning domain description language, PDDL）和回答集程序（answer set programming, ASP）规划器的性能

关键词：任务规划；机器人；规划领域定义语言（PDDL）；回答集程序（ASP）

HTML PDF 收藏

面向任务信息的层次化存储DPM策略

黄少珉,戚隆宁,杨军,胡晨

《中国工程科学》 2010年第12卷第2期页码 83-89

摘要：在此基础上提出基于任务信息（task information based，TIB）的层次化存储DPM策略。

关键词：数据缓冲区任务信息 DPM 预读策略

HTML PDF 收藏

移动众包环境下基于友谊度的任务规划 Article

Yuan LIANG,Wei-feng LV,Wen-jun WU,Ke XU

《信息与电子工程前沿（英文）》 2017年第18卷第1期页码 107-121 doi: 10.1631/FITEE.1601860

摘要：最近，众包平台已吸引了大量的注册用户在线下执行特定的任务。然而，大部分现有方法仅考虑了工人和任务信息都已提前获知的情况（静态离线情景），而较少考虑到工人动态抵达的情况（动态在线情景）。因此，当工人动态抵达时，如何给工人安排适合的任务以获得其最大的满意度成为了一个具有挑战性的问题。为解决这一问题，本文提出了一种有用并且普遍的人工-任务模型，该模型不仅考虑在静态离线时给工人安排任务的情况，还同时考虑了在工人动态抵达时如何给工人安排合适的任务。在本文中，为解决静态离线情景下的任务分配问题，我们首先提出一个有效的贪心算法。由于贪心算法极易陷入局部最优，我们又加入了模拟退火法来提高贪心算法的性能。另外，为解决动态在线情景下的分配问题，我们提出了一种贪心算法。最后，在真实数据集和具有不同分布人造数据集上进行了大量实验，实验结果验证了算法的效果与性能。

关键词：移动众包；任务规划；贪心算法；模拟退火

HTML PDF 收藏

Motion planning and tracking control of a four-wheel independently driven steered mobile robot with multiple

Xiaolong ZHANG, Yu HUANG, Shuting WANG, Gen LI, Yuanlong XIE, Wei MENG

《机械工程前沿（英文）》 2021年第16卷第3期页码 504-527 doi: 10.1007/s11465-020-0626-y

摘要： Safe and effective autonomous navigation in dynamic environments is challenging for four-wheel independently driven steered mobile robots (FWIDSMRs) due to the flexible allocation of multiple maneuver modes. To address this problem, this study proposes a novel multiple mode-based navigation system, which can achieve efficient motion planning and accurate tracking control. To reduce the calculation burden and obtain a comprehensive optimized global path, a kinodynamic interior–exterior cell exploration planning method, which leverages the hybrid space of available modes with an incorporated exploration guiding algorithm, is designed. By utilizing the sampled subgoals and the constructed global path, local planning is then performed to avoid unexpected obstacles and potential collisions. With the desired profile curvature and preselected mode, a fuzzy adaptive receding horizon control is proposed such that the online updating of the predictive horizon is realized to enhance the trajectory-following precision. The tracking controller design is achieved using the quadratic programming (QP) technique, and the primal–dual neural network optimization technique is used to solve the QP problem. Experimental results on a real-time FWIDSMR validate that the proposed method shows superior features over some existing methods in terms of efficiency and accuracy.

关键词： mobile robot multiple maneuvering mode motion planning tracking control receding horizon control

HTML PDF 收藏

管理面向任务的虚拟助手软件系统的经验性研究 Research Article

李姝玥1,郭家琪1,高妍2,楼建光2,杨德建2,肖炎2,周亚东1,刘烃1

《信息与电子工程前沿（英文）》 2022年第23卷第5期页码 749-762 doi: 10.1631/FITEE.2100467

摘要：面向任务的虚拟助手是为用户提供自然语言接口以完成特定领域任务的软件系统。随着近年来自然语言处理和机器学习技术的发展，越来越多面向任务的虚拟助手产品开始涌现。由于自然语言理解这一问题的复杂性和困难性，管理一个面向任务的虚拟助手软件项目具有挑战性。同时，据我们所知，与虚拟助手开发相关的管理和经验在学术界和工业界都少有研究或分享。为填补这空白，本文分享了我们在微软开发一项虚拟助手产品过程中的管理经验和教训。相信我们的经验和教训能为研究人员和相关从业者提供宝贵参考。最后，设计了一个需求管理工具SpecSpace，对我们虚拟助手项目的管理有很大帮助。

关键词：经验报告；软件项目管理；虚拟助手；机器学习

HTML PDF 收藏

Motion capability analysis of a quadruped robot as a parallel manipulator

Jingjun YU,Dengfeng LU,Zhongxiang ZHANG,Xu PEI

《机械工程前沿（英文）》 2014年第9卷第4期页码 295-307 doi: 10.1007/s11465-014-0317-7

摘要：

This paper presents the forward and inverse displacement analysis of a quadruped robot MANA as a parallel manipulator in quadruple stance phase, which is used to obtain the workspace and control the motion of the body. The robot MANA designed on the basis of the structure of quadruped mammal is able to not only walk and turn in the uneven terrain, but also accomplish various manipulating tasks as a parallel manipulator in quadruple stance phase. The latter will be the focus of this paper, however. For this purpose, the leg kinematics is primarily analyzed, which lays the foundation on the gait planning in terms of locomotion and body kinematics analysis as a parallel manipulator. When all four feet of the robot contact on the ground, by assuming there is no slipping at the feet, each contacting point is treated as a passive spherical joint and the kinematic model of parallel manipulator is established. The method for choosing six non-redundant actuated joints for the parallel manipulator from all twelve optional joints is elaborated. The inverse and forward displacement analysis of the parallel manipulator is carried out using the method of coordinate transformation. Finally, based on the inverse and forward kinematic model, two issues on obtaining the reachable workspace of parallel manipulator and planning the motion of the body are implemented and verified by ADAMS simulation.

关键词： quadruped robot actuated joints selection kinematics analysis motion planning parallel manipulator

HTML PDF 收藏

Evolutionary Decision-Making and Planning for Autonomous Driving Based on Safe and Rational Exploration

Kang Yuan,Yanjun Huang,Shuo Yang,Zewei Zhou,Yulei Wang,Dongpu Cao,Hong Chen,

《工程（英文）》 doi: 10.1016/j.eng.2023.03.018

摘要： Decision-making and motion planning are extremely important in autonomous driving to ensure safe driving in a real-world environment. This study proposes an online evolutionary decision-making and motion planning framework for autonomous driving based on a hybrid data- and model-driven method. First, a data-driven decision-making module based on deep reinforcement learning (DRL) is developed to pursue a rational driving performance as much as possible. Then, model predictive control (MPC) is employed to execute both longitudinal and lateral motion planning tasks. Multiple constraints are defined according to the vehicle’s physical limit to meet the driving task requirements. Finally, two principles of safety and rationality for the self-evolution of autonomous driving are proposed. A motion envelope is established and embedded into a rational exploration and exploitation scheme, which filters out unreasonable experiences by masking unsafe actions so as to collect high-quality training data for the DRL agent. Experiments with a high-fidelity vehicle model and MATLAB/Simulink co-simulation environment are conducted, and the results show that the proposed online-evolution framework is able to generate safer, more rational, and more efficient driving action in a real-world environment.

关键词： Autonomous driving Decision-making Motion planning Deep reinforcement learning Model predictive control