本 文提 出 一种 支持 个性 化 协调 的服 务 机器 人 体系 结 构(individualized coordination architecture, ICA) . 主要动机是通过自然语言人机对话获取用户的个人特性和其他信息, 通过对这些信
息进行自动推理和规划, 实现利用个人特性的自动问题求解, 并满足家庭环境对服务机器人的应用要 求. 本文着重介绍 ICA 的主要部件的功能及其相互衔接方式, 描述任务规划的机制和实现手段, 并通过
一个实例说明在一个初步实现的原型系统中从自然语言到任务规划的完整过程.
Abstract
A service robot architecture supporting individualized coordination is proposed.In this approach, user features and other information will be acquired through human-robot dialogue in natural languages.The robot
reasons about and makes plans with the information, so that automatic, individualized problem-solving can be carried out under real-world environments.We present the main modules and their interfaces of the architecture, the
mechanism of task planning , and a case study which includes the entire working process from natural language processing( N LP)to task planning in an implemented prototype system, expected to work with humans in, say,
ordinary home environments.Standard NLP techniques such as syntactic parsing have been implemented in the prototype system, together with semantic analyzing developed by the authors.With these NLP techniques, the
user’ s commands and descriptions about the environment expressed in natural languages are transferred into logical forms in segmented discourse representation theory( SDRT)and finally in answer set programming( ASP), which are
ready for the task planning, through a 5 -steps procedure.In task planning module, ASP technique is employed, making it possible and feasible for the robot to conduct task planning and reasoning about the actions and changes in
a unifying way.With some good coding , according to the authors’ experiments with a real home robot, the task planning module can work for some typical tasks in real -time.This work provides a basis for investigations into
further challenges in individualized coordination.
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[ 1] Bill G .A Robot in every home.Scientific American, 2007, 296( 1): 58～ 65.
[ 2] Scerri P, Vincent R, Mailler R T . Coordination of large -scale multiagent systems.New York: Springer -Verlag Publishing , 2006, 1～ 347.
[ 3] Boutilier C. Sequential optimality and coordina- tion in multiagent systems.Dean T .Proceed- ings of the 16 th international Joint Conference on
Artificial intelligence (IJCAI -99). Morgan · 138 · 南京大学学报( 自然科学) 第 46 卷 Kaufmann Publishers, San Francisco, CA , 1999, 478～ 485.
[ 4] Dastani M , Arbab F , de Boer F.Coordination and composition in multi -agent systems.Pro- ceedings of the 4 th international Joint Conference
on Autonomous Agents and Multiagent Systems ( AAMAS-05).ACM , New York, NY, 2005, 439～ 446.
[ 5] Li L, Li B, Zhu J W .A semantic middleware for coordination of agents.Journal of Nanjing University(Natural Sciences), 2008, 44(5):
457～ 465. ( 亮, 李 斌, 朱俊武.一种用于agent 协同的语义中间件.南京大学学报( 自然科学), 2008, 44( 5) :457～ 465).
[ 6] Fischer G.User modeling in human -computer interaction.User Modeling and User-Adapted Interaction, 2001, 11( 1-2): 65～ 86.
[ 7] Heinath M , Dzaack J, Wiesner A , etal . Appli- cations for cognitive user modeling .Conati C, Mccoy K , Paliouras G.Proceedings of the 11 th
international Conference on User Modeling . Lecture Notes in Artificial Intelligence, Spring- er-Verlag , Berlin, Heidelberg, 2007, 4511: 127～ 136.
[ 8] Landauer T K, Prabhu P V .Handbook of hu- man-computer interaction. The 2 nd Edition. Elsevier Science Inc. , 1998, 1～ 1582.
[ 9] Jaimes A , Sebe N .Multimodal human-comput- er interaction:A survey.Computer Vision and Image Understanding, 2007, 108 (1-2): 116～ 134.
[ 10] Santhanam G, Ryi S I, Yu B M , et al.A high performance brain computer interface.Nature, 2006, 442: 195～ 198.
[ 11] Cohen P R, Levesque H J.Intention is choice with commitment.Artificial intelligence, 1990, 42( 2-3), 213～ 261.
[ 12] RoboCup2009.RoboCup @ Home:Rules & Regulations.http: // www. ai. rug. nl/ robocu- pathome/ documents/ rulebook2009 - DRAFT . pdf, 2009.
[ 13] Baral C.Knowledge representation, reasoning and declarative problem solving .Cambridge University Press, 2003, 1～ 548.
[ 14] Gelfond M .Answer set programming and the design of deliberative agents.Proceedings of 12 th International Conference on Logic Program-
ming ( ICLP’ 04) .Berlin, Heidelberg , Lecture Notes in Computer Science.Springer -Verlag, 2004, 3132:19～ 26.
[ 15] Eiter T , Faber W, Leone N , et al.The diagno- sis frontend of the dlvsystem.AI Communica- tions, 1999, 12( 1-2): 99～ 111.
[ 16] Nogueira M , Balduccini M , Gelfond M , et al. An A -Prolog decision support system for the space shuttle.Proceedings of the 3 rd Interna-
tional Symposium on Practical Aspects of De- clarative Languages. Lecture Notes in Computer Science. Springer -Verlag , 2001, 1990: 169～ 183
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家 863 计划( 2008AA01Z150) , 国家自然科学基金( 60745002)
{{custom_fund}}
PDF(300363 KB)
