论文部分内容阅读
针对现有的任务规划方法在响应深空动态不确定因素的扰动情况时存在的不确定因素识别度低、响应策略单一等问题,文章提出了一种考虑动态不确定因素的深空探测器任务规划算法。首先,对不确定扰动按从轻到重四个等级进行划分,并采用模糊神经网络评估不确定扰动属于哪种扰动级别,根据评估结果选择对应的扰动响应策略;然后,采用基于分层任务网络规划(Hierarchical Task Network,HTN)的局部任务修复方法,对受到扰动的子系统对应的复合任务重新进行任务分解,完成对初始规划方案的调整修复。仿真结果表明所提出的算法可以有效地对深空动态不确定因素进行评估和响应,从而提高了任务规划的可靠性和灵活性。
Aiming at the problems of low recognition rate and single response strategy of existing mission planning methods in response to the disturbances of dynamic uncertainties in deep space, this paper proposes a deep space probe mission that takes into account dynamic uncertainties Planning algorithm. First of all, the uncertain disturbance is divided into four levels according to lightness to heavyness, and the fuzzy neural network is used to evaluate the disturbance level to which the uncertain disturbance belongs. According to the assessment result, the perturbation response strategy is selected. Then, based on the hierarchical task network (HNT) local task remediation method, re-decompose the complex task corresponding to the perturbed subsystem, and finish the adjustment and restoration of the initial plan. Simulation results show that the proposed algorithm can effectively evaluate and respond to the dynamic uncertainties in deep space, and improve the reliability and flexibility of task planning.