北京航空航天大学学报 ›› 2017, Vol. 43 ›› Issue (2): 277-284.doi: 10.13700/j.bh.1001-5965.2016.0572

• 论文 • 上一篇    下一篇

嫦娥三号“玉兔号”巡视器行为规划方法

高薇1,2, 蔡敦波3, 周建平1,4, 高宇辉2, 殷明浩5   

  1. 1. 北京航空航天大学 宇航学院, 北京 100083;
    2. 北京航天飞行控制中心, 北京 100094;
    3. 武汉工程大学 智能机器人湖北省重点实验室, 武汉 430205;
    4. 中国载人航天办公室, 北京 100720;
    5. 东北师范大学 计算机科学与信息技术学院, 长春 130017
  • 收稿日期:2016-07-05 出版日期:2017-02-20 发布日期:2016-11-16
  • 通讯作者: 蔡敦波,E-mail:dunbocai@163.com E-mail:dunbocai@163.com
  • 作者简介:高薇,女,博士研究生,工程师。主要研究方向:飞行器控制与通信;蔡敦波,男,博士,副教授。主要研究方向:智能规划与自动推理;周建平,男,博士,教授,博士生导师,中国工程院院士。主要研究方向:载人航天工程。
  • 基金资助:
    国家自然科学基金(61103136,61370156,61503074);新世纪优秀人才支持计划(NECT-13-0724);航天飞行动力学技术重点实验室开放基金(2014afdl002);湖北省教育厅科学技术研究计划中青年人才项目(Q20151516)

Activity planning method for Chang'E-3 “Jade Rabbit” rover

GAO Wei1,2, CAI Dunbo3, ZHOU Jianping1,4, GAO Yuhui2, YIN Minghao5   

  1. 1. School of Astronautics, Beijing University of Aeronautics and Astronautics, Beijing 100083, China;
    2. Beijing Aerospace Control Center, Beijing 100094, China;
    3. Hubei Provincial Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan 430205, China;
    4. China Manned Space Engineering Office, Beijing 100720, China;
    5. School of Computer Science and Information Technology, Northeast Normal University, Changchun 130017, China
  • Received:2016-07-05 Online:2017-02-20 Published:2016-11-16
  • Supported by:
    National Natural Science Foundation of China (61103136, 61370156, 61503074); Program for New Century Excellent Talents in University (NECT-13-0724); Open Research Foundation of Science and Technology on Aerospace Flight Dynamics Laboratory (2014afdl002); Scientific Research Program of Education Department of Hubei Province for Young Talents (Q20151516)

摘要: 为支持“玉兔号”巡视器完成对月面较大空间范围的科学探测,对动态任务进行快速规划,提出了一种基于人工智能领域智能规划技术的自动化任务规划方法。提出了行为持续时间和行为效果动态确定的时态规划模型(TPDD&DE),设计了描述TPDD&DE问题的规划领域定义语言PDDL——PDDLDD&DE,以及针对TPDD&DE问题的启发式规划算法,运用Landmark知识分析规划问题结构,从而设计了合理反映动作前提评估顺序的启发函数。在嫦娥三号任务中,本文方法支撑“玉兔号”巡视器圆满完成了预期的科学探测任务。

关键词: 月面巡视器, 行为规划, 自动规划, 任务建模, 启发式搜索

Abstract: To enable the "Jade Rabbit" rover to plan fast in a dynamic work environment on the lunar surface, an activity planning model called temporal planning with dynamic duration and dynamic effect (TPDD&DE) was developed based on the automated planning technology of artificial intelligence. This model extends temporal planning to incorporate external computing procedures and to support durations of actions to be determined dynamically. To describe tasks of TPDD&DE, an extension of the planning domain definition language(PDDL), called PDDLDD&DE, was designed. A planning system that is based on the heuristic state space search framework was developed to solve the planning problem. By utilizing the "proposition Landmarks analysis" technique, we designed a heuristic function that accounts for reasonable orderings of actions' preconditions and is capable of getting better goal distance estimates for states. With the successful completion of Chang'E-3 mission, the proposed method played a key role in supporting the "Jade Rabbit" rover to fulfill its exploration tasks on the moon.

Key words: lunar surface rover, activity planning, automated planning, task modeling, heuristic search

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发