改进的分拣作业机械臂基于范例推理信念期望意图推理机制

doi:10.11772/j.issn.1001-9081.2016.03.746

计算机应用 ›› 2016, Vol. 36 ›› Issue (3): 746-750.DOI: 10.11772/j.issn.1001-9081.2016.03.746

改进的分拣作业机械臂基于范例推理信念期望意图推理机制

周昊天, 闵华松

武汉科技大学冶金自动化与检测技术教育部工程研究中心, 武汉 430081

收稿日期:2015-08-06 修回日期:2015-09-21 出版日期:2016-03-10 发布日期:2016-03-17
通讯作者: 周昊天
作者简介:周昊天(1991-),男,湖北黄石人,硕士研究生,主要研究方向:嵌入式系统;闵华松(1969-),男,湖北应城人,教授,博士,主要研究方向:嵌入式系统、智能机器人。
基金资助:
国家自然科学基金资助项目(61175094)。

Improved CBR-BDI reasoning mechanism for sorting operation mechanical arm

ZHOU Haotian, MIN Huasong

Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education, Wuhan University of Science and Technology, Wuhan Hubei 430081, China

Received:2015-08-06 Revised:2015-09-21 Online:2016-03-10 Published:2016-03-17
Supported by:
This work is partially supported by the National Natural Science Foundation of China(61175094).

摘要/Abstract

摘要： 针对以案例推理机制为推理核心的分拣作业机械臂系统不能用于物体信息较多的复杂场景的问题,提出一种改进的基于范例推理-信念期望意图(CBR-BDI)推理机制。首先,将输入的信息作为信念(Belief),通过分词与检索得到案例属性,将其作为期望(Desire);然后,加入地图匹配、期望分析和引导三个部分以完善期望;最后,完整的期望生成解决方案作为意图(Intention)。在多物体多信息的场景中,用户可通过对话指挥系统进行分拣作业。实验结果表明,与传统的案例推理(CBR)机制相比,改进的CBR-BDI推理机制具有分析和引导能力,能用于多物体复杂场景。

关键词: 推理机制, 案例推理, 推理算法, 智能机器人, 机械臂

Abstract: Focused on the issue that the sorting operation mechanical arm which used Case-Based Reasoning (CBR) mechanism could not be used for the complex scenario with a lot of object information, an improved Case-Based Reasoning-Belief, Desire, Intention (CBR-BDI) reasoning mechanism was proposed. Firstly, the input information was regarded as belief, and the case properties obtained through sentence segmentation and retrieval was regarded as desire. Secondly, map matching, desire analysis and guidance were added to perfect desire. Finally, complete desire generated solution which was regarded as intention. In the scenario of multiple object and information, users could command system for sorting operation through dialogue. The experimental results show that compared with the traditional CBR mechanism, the improved CBR-BDI reasoning mechanism possess the ability of analysis and guide, and can be used for the scenario of multiple object and information.

Key words: reasoning mechanism, Case-Based Reasoning (CBR), reasoning algorithm, intelligent robot, mechanical arm

中图分类号:

TP18

周昊天, 闵华松. 改进的分拣作业机械臂基于范例推理信念期望意图推理机制[J]. 计算机应用, 2016, 36(3): 746-750.

ZHOU Haotian, MIN Huasong. Improved CBR-BDI reasoning mechanism for sorting operation mechanical arm[J]. Journal of Computer Applications, 2016, 36(3): 746-750.

参考文献

[1] 李洋,李星,吴秋云,等.基于CBR+RBR的快速应急预案生成方法[J].兵工自动化,2013(5):31-35.(LI Y, LI X, WU Q Y, et al. Emergency plan generating method based on CBR and RBR[J]. Ordnance Industry Automation, 2013(5):31-35.)
[2] 闵华松,甘勋.一种实时的智能机器人推理机制[J].计算机工程,2012,38(22):141-145.(MIN H S, GAN X. A real-time reasoning mechanism of intelligent robot [J]. Computer Engineering, 2012,38(22):141-145.)
[3] PEULA J M, URDIALES C, HERRERO I, et al. Implicit robot coordination using case-based reasoning behaviors [C]//Proceedings of the 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, NJ: IEEE, 2013:5929-5934.
[4] ALTAF M M, ELBAGOURY B M, ALRADDADY F, et al. Extended case-based behavior control for multi-humanoid robots [EB/OL]. [2015-04-05]. http://www.worldscientific.com/doi/abs/10.1142/S0219843615500358?src=recsys.
[5] 韩敏,沈力华.基于FCM与神经网络的案例推理方法[J].控制与决策,2012,27(9):1421-1424.(HAN M, SHEN L H. Case-based reasoning based on FCM and neural network [J]. Control and Decision, 2012,27(9):1421-1424.)
[6] 刘强,马家辰,谢玮,等.混合粒子群优化算法和案例推理方法的多机器人学习[J].电子科技大学学报,2014,43(1):137-143.(LIU Q, MA J C, XIE W, et al. Multi-robot learning using PSO combined with CBR algorithm [J]. Journal of University of Electronic Science and Technology of China, 2014,43(1):137-143.)
[7] 张林,史豪斌,吴佳斌.基于改进 CBR 的机器人足球对抗决策技术研究[J]. 西北工业大学学报,2013,31(6):991-996.(ZHANG L, SHI H B, WU J B. Applying intelligent confrontation decision-making system to robot soccer based on improved CBR [J]. Journal of Northwestern Polytechnical University, 2013,31(6):991-996.)
[8] de PAZ J F, BAJO J, BORRAJO M L, et al. A multi-Agent system for Web-based risk management in small and medium business [J]. Expert Systems with Applications, 2012,39(8): 6921-6931.
[9] DALAL S, TANWAR G, ALHAWAT N. Designing CBR-BDI Agent for implementing supply chain system [J]. International Journal of Engineering Research and Applications, 2013,3(1):1288-1292.
[10] FRAILE J A, PAZ Y, BAJO J, et al. Context-aware multi-Agent system: planning home care tasks [J]. Knowledge and Information Systems, 2014,40(1):171-203.
[11] 甘勋.基于Multi-Agent智能机器人推理机制研究[D].武汉:武汉科技大学,2012.(GAN X. Research of reasoning mechanism for intelligent robot based on multi-Agent architecture [D]. Wuhan: Wuhan University of Science and Technology, 2012.)
[12] CHENG Z, MIN H, SHEN X. Case-based reasoning with improved vector space model of indoor mobile robot [C]//Proceedings of the 2014 11th World Congress on Intelligent Control and Automation. Piscataway, NJ: IEEE, 2014:2239-2246.
[13] 程志强,闵华松.一种基于向量词序的句子相似度算法研究[J].计算机仿真,2014,31(7):419-424.(CHENG Z Q, MIN H S. A sentences similarity algorithm based on word order of vectors distance [J]. Computer Simulation, 2014,31(7):419-424.)
[14] 陈飞宏.基于向量空间模型的中文文本相似度算法研究[D].成都:电子科技大学,2011.(CHEN F H. Research of Chinese text similarity algorithm based on vector space model [D]. Chengdu: University of Electronic Science and Technology of China, 2011.)

改进的分拣作业机械臂基于范例推理信念期望意图推理机制

Improved CBR-BDI reasoning mechanism for sorting operation mechanical arm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

[1]	王建平, 王刚, 毛晓彬, 马恩琪. 基于深度强化学习的二连杆机械臂运动控制方法[J]. 计算机应用, 2021, 41(6): 1799-1804.
[2]	严爱军, 魏志远. 案例推理分类器的权重分配及案例库维护方法[J]. 计算机应用, 2021, 41(4): 1071-1077.
[3]	李克讷, 张增, 王温鑫. 基于伪逆的导轨机械臂关节速度纠偏运动规划方案[J]. 计算机应用, 2020, 40(12): 3695-3700.
[4]	袁蒙恩, 陈立家, 冯子凯. 基于单目视觉的多种群粒子群机械臂路径规划算法[J]. 计算机应用, 2020, 40(10): 2863-2871.
[5]	周锋, 林楠, 陈小平. 基于六维线性插值的六自由度机械臂逆运动学方程求解方法[J]. 计算机应用, 2018, 38(2): 563-567.
[6]	邹思凡, 吴国庆, 茅靖峰, 朱维南, 王玉荣, 王健. 改进非线性干扰观测器的机械臂自适应反演滑模控制[J]. 计算机应用, 2018, 38(10): 2827-2832.
[7]	张万绪张向兰李莹. 基于改进粒子群算法的智能机器人路径规划[J]. 计算机应用, 2014, 34(2): 510-513.
[8]	黄浙京汪斌强张建辉贺磊. 案例推理变权值引擎模型及权值计算方法[J]. 计算机应用, 2011, 31(07): 1776-1780.
[9]	刘双印. 电子商务智能推荐系统中基于领域本体的案例检索算法[J]. 计算机应用, 2010, 30(05): 1304-1308.
[10]	刘晓文胡克瑾胡克瑾. 一种基于本体和CBR的电子政务项目审批决策支持系统[J]. 计算机应用, 2009, 29(3): 896-899.
[11]	姚全珠孟丽崔杜武. 基于CBR和XML的软构件检索方法[J]. 计算机应用, 2007, 27(7): 1711-1714.
[12]	杨振刚邓飞其. CFW的CBR与ART-KNN集成智能预测[J]. 计算机应用, 2007, 27(5): 1177-1179.
[13]	李培峰朱巧明钱培德. 一个多文种语言Ontology框架的构建方法[J]. 计算机应用, 2007, 27(3): 646-649.