摘要
为降低任务规划的复杂度并提高机器人对动态环境的适应能力,提出一种基于人机协同的任务规划方法,将任务规划全过程划分为任务级和指令级.在任务级规划中,用户意图输入、任务描述和人形机器人的任务解析与智能推理相结合,为指令级规划提供依据.在指令级规划中,基于任务的三元分解模型建立模块化的规划结构,以直观的图形化方式组合任务分解出的三元素,构成各种不同的任务,实现对任意任务的实时规划,同时机器人系统通过指令解析和预判辅助规划过程,形成既能满足人的任务需求又符合规划合理性的指令序列.最后用实例验证所提方法的有效性与可行性.
In order to reduce the complexity of task planning and improve the adaptability of the robot to the dynamic environment,a method of task planning based on human-robot cooperation was proposed and the whole process was divided into task level and command level.In the task level planning,human′s intention and task description were combined with humanoid robot′s task analysis and intelligent reasoning to provide basis for command level planning.In the command level planning,modular planning structure was constructed based on three-element task decomposition model.Human chose and combined different elements that came from task decomposition model to achieve real-time task planning for any tasks.Meanwhile,in order to form commands sequence that conformed to rationality and task demands,humanoid robot analyzed and prejudged commands to assist human to plan tasks.Finally,a case was adopted to illustrate the effectiveness and feasibility of the proposed approach.
出处
《华中科技大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2017年第1期76-81,共6页
Journal of Huazhong University of Science and Technology(Natural Science Edition)
基金
国家自然科学基金资助项目(71301057)
上海航天科技创新基金资助项目(SAST201409)
关键词
任务规划
人形机器人
人机协同
实时
动态环境
task planning
humanoid robot
human-robot cooperation
real-time
dynamic environment
