计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (7): 1-9.doi: 10.11896/jsjkx.221200020

• 计算机软件 • 上一篇    下一篇

自主机器人的伴随观察模式及其软件实现框架

薛元洲1,2, 杨硕3, 毛新军1,2   

  1. 1 国防科技大学计算机学院 长沙 410073
    2 复杂系统软件工程湖南省重点实验室 长沙 410073
    3 国防科技大学系统工程学院 长沙 410073
  • 收稿日期:2022-12-04 修回日期:2023-03-27 出版日期:2023-07-15 发布日期:2023-07-05
  • 通讯作者: 杨硕(yangshuo11@nudt.edu.cn)
  • 作者简介:(yzxue@nudt.edu.cn)
  • 基金资助:
    国家自然科学基金(62172426)

Adjoint Observation Schemes and Software Implementation Framework for Autonomous Robots

XUE Yuanzhou1,2, YANG Shuo3, MAO Xinjun1,2   

  1. 1 College of Computer Science and Technology,National University of Defense Technology,Changsha 410073,China
    2 Key Laboratory of Software Engineering for Complex Systems,Changsha 410073,China
    3 College of Systems Engineering,National University of Defense Technology,Changsha 410073,China
  • Received:2022-12-04 Revised:2023-03-27 Online:2023-07-15 Published:2023-07-05
  • About author:XUE Yuanzhou,born in 1997,postgra-duate,is a student member of China Computer Federation.His main research interest is robot software engineering.YANG Shuo,born in 1992,Ph.D,lectu-rer,is a member of China Computer Fe-deration.His main research interests include intelligent robot software engineering,software engineering theory and methods and robot behavior mode-ling and task decision-making.
  • Supported by:
    National Natural Science Foundation of China(62172426).

PDF (PC)

2054

摘要： 自主机器人是一类运行于开放环境下、可自主决策和执行其自主行为的信息物理系统,它根据任务需求进行决策产生行为策略并调度执行。环境状态的动态变化性常常导致规划的行为策略不再适用于当前环境,使得行为执行的结果不符合预期,从而影响自主机器人的任务实现。上述问题对自主机器人软件的行为决策和软件构造均提出了更高的要求。一方面,自主机器人需在行为策略执行过程中加强对环境状态及其变化的观察,并基于观察的结果及时、灵活地调整行为决策,提升机器人的观察模式及行为决策算法的复杂度。另一方面,上述观察、决策、执行行为的复杂交互提升了软件构件抽象及数据交互的复杂性,如何抽象机器人的传感、决策、效应等软构件功能,并提供相适配的软件架构,成为自主机器人软件构造面临的重要挑战。针对上述挑战,首先提出自主机器人伴随行为的思想,显式定义观察与效应行为之间的伴随交互关系,根据行为执行不同阶段提出前提伴随观察模式和目标伴随观察模式,以提升自主机器人对环境变化的感知能力和决策调整能力。其次,开发了一款基于多智能体系统的自主机器人软件开发框架AutoRobot,该框架将机器人的传感器、效应器及规划器抽象为一组自主的软件智能体,智能体间通过自主决策和协同实现上述伴随观察模式。AutoRobot框架针对不同角色智能体设计和封装了一组可重用的软件组件,可有效支持自主机器人软件的复用和高效开发。最后,开展了仿真环境下的实验分析,通过与ROSPlan和DESPOT两种自主机器人任务规划和执行方法进行对比,验证了基于伴随观察模式的任务规划与执行的高效性和有效性。

关键词: 自主机器人, 开放环境, 伴随观察模式, 任务规划, 任务执行

Abstract: Autonomous robot is a kind of cyber-physical system which operates in an open environment and can make and execute its behavior autonomously.It generates and executes effective plans according to the task.The dynamic change of environment state often results in that the planned behavior strategy is no longer applicable to the current environment and the results of behavior execution are not in line with expectations,thus affecting the task achievement of autonomous robots.The above problems pose challenges to both the behavioral decision-making and the construction of autonomous robot software.On the one hand,autonomous robots need to strengthen the observation of environment states and their changes during the execution of its behavior strategy,and adjust the behavior strategy in a timely and flexible manner based on the observation results,which improves the complexity of the robot’s observation scheme and behavioral decision-making algorithm.On the other hand,the complex interactions of observation,decision-making and behavior execution enhances the complexity of software component abstraction and data interaction,and how to abstract the functions of software components such as sensing,decision-making and actuating of robots and provide suitable software architecture has become an important challenge for the software construction of autonomous robots.In view of the above challenges,the idea of adjoint behavior of autonomous robots is proposed,the adjoint interaction between observation and actuating behavior is clearly defined,and two adjoint observation schemes,conditional adjoint observation scheme and objective adjoint observation scheme,are proposed according to different stages of behavior execution,so as to improve the sensing of environmental changes and decision-making adjustment ability of autonomous robots.Secondly,AutoRobot,an autonomous robot software development framework based on multi-agent system,is developed,which abstracts the robot’s sensors,actuators and planners into a set of autonomous software agents,and the agents implement the above adjoint observation schemes through autonomous decision-making and collaboration.The AutoRobot framework designs and packages a set of reusable software components for different agent types,which can effectively support the reuse and efficient development of autonomous robot software.Finally,an experimental analysis is carried out in the simulation environment,and the efficiency and effectiveness of task planning and execution based on the adjoint observation schemes are verified by comparing it with ROSPlan and DESPOT,two autonomous robot task planning and execution methods.

Key words: Autonomous robots, Open environments, Adjoint observation schemes, Task planning, Task execution

中图分类号: 

  • TP311
[1]MAO X J.A Systematic Review on Software Engineering for Autonomous Robot[J].Chinese Journal of Computers,2021,44(8):1661-1678.
[2]THODUKA S,GALL J,PLÖGER P G.Using Visual Anomaly Detection for Task Execution Monitoring[C]//2021 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).2021:4604-4610.
[3]MIGIMATSU T,BOHG J.Object-Centric Task and MotionPlanning in Dynamic Environments[J].IEEE Robotics and Automation Letters,2020,5(2):844-851.
[4]CUI G,SHUAI W,CHEN X.Semantic Task Planning for Ser-vice Robots in OpenWorlds[J].Future Internet,2021,13(2):1-19.
[5]DONDRUP C,PAPAIOANNOU I,NOVIKOVA J,et al.Introducing a ROS based planning and execution framework for human-robot interaction[C]//Proceedings of the 1st ACM SIGCHI International Workshop on Investigating Social Interactions with Artificial Agents.New York,NY,USA,Association for Computing Machinery,2017:27-28.
[6]YANG S,MAO X,WANG S,et al.Towards Adjoint Sensing and Acting Schemes and Interleaving Task Planning for Robust Robot Plan[C]//2021 IEEEInternational Conference on Robo-tics and Automation(ICRA).2021:13791-13797.
[7]NOREILS F R,CHATILA R G.Plan execution monitoring and control architecture for mobile robots[J].IEEE Transactions on Robo-tics and Automation,1995,11(2):255-266.
[8]MUKHERJEE S,PAXTON C,MOUSAVIAN A,et al.Reactive Long Horizon Task Execution via Visual Skill and Precondition Models[C]//2021 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).2021:5717-5724.
[9]KASE K,PAXTON C,MAZHAR H,et al.Transferable Task Execution from Pixels through Deep Planning Domain Learning[C]//2020 IEEE International Conference on Robotics and Automation(ICRA).Paris,France,IEEE,2020:10459-10465.
[10]KAELBLING L P,LOZANO-PÉREZ T.Integrated task andmotion planning in belief space[J].International Journal of Robotics Research,2013,32(9/10):1194-1227.
[11]CASHMORE M,FOX M,LONG D,et al.Opportunistic plan-ning in autonomous underwater missions[J].IEEE Transactions on Automation Science and Engineering,2017,15(2):519-530.
[12]CORUHLU G,ERDEM E,PATOGLU V.Explainable Robotic Plan Execution Monitoring Under Partial Observability[J].IEEE Transactions on Robotics,2021:1-21.
[13]RAO D,HU G,JIANG Z.PRobPlan:A Framework of Integrating Probabilistic Planning Into ROS[J].IEEE Access,2020,8:106516-106530.
[14]SUAREZ R,BASANEZ L,ROSELL J.Using configuration and force sensing in assembly task planning and execution[C]//Pro-ceedings of IEEE International Symposium on Assembly and
Task Planning.1995:273-279.
[15]YE N,SOMANI A,HSU D,et al.DESPOT:Online POMDPPlanning with Regularization[J].Journal of Artificial Intelligence Research,2017,58:231-266.
[16]GRADY D K,MOLL M,KAVRAKI L E.Extending the Applicability of POMDP Solutions to Robotic Tasks[J].IEEE Tran-sactions on Robotics,2015,31(4):948-961.
[17]QUIGLEY M,CONLEY K,GERKEY B,et al.ROS:an open-source robot operating system[C]//ICRA Workshop on Open Source Software.2009.
[18]METTA G,FITZPATRICK P,NATALE L.YARP:Yet Ano-ther Robot Platform[J].International Journal of Advanced Robotic Systems,2006,3(1):43-48.
[19]HELLMUND A M,WIRGES S,TAŞ Ö Ş,et al.Robot opera-ting system:A modular software framework for automated dri-ving[C]//2016 IEEE 19th International Conference on Intelligent Transportation Systems(ITSC).2016:1564-1570.
[20]ROVIDA F,GROSSMANN B,KRÜGER V.Extended behavior trees for quick definition of flexible robotic tasks[C]//2017 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).2017:6793-6800.
[21]COLLEDANCHISE M,NATALE L.On the Implementation of Behavior Trees in Robotics[J].IEEE Robotics and Automation Letters,2021,6(3):5929-5936.
[22]SHPIEVA E,AWAAD I.Integrating task planning,executionand monitoring for a domestic service robot[J].Information Technology,2015,57(2):112-121.
[23]PAXTON C,RATLIFF N,EPPNER C,et al.Representing Robot Task Plans as Robust Logical-Dynamical Systems[C]//2019 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).Macau,China,IEEE,2019:5588-5595.
[24]POT E,MONCEAUX J,GELIN R,et al.Choregraphe:a gra-phical tool for humanoid robot programming[C]//The 18th IEEE International Symposium on Robot and Human Interactive Communication(ROMAN 2009).2009:46-51.
[25]CASHMORE M,FOX M,LONG D,et al.ROSPlan:Planning in the Robot Operating System[C]//Proceedings of the International Conference on Automated Planning and Scheduling.2015:333-341.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发