摘要
轨迹预测在打乒乓球机器人击球的过程中具有十分重要的作用,轨迹预测的准确性关系到击球的成败.因击球时,非光滑的接触面对乒乓球产生摩擦力,使乒乓球产生了旋转并对乒乓球的飞行轨迹产生了一定影响,造成轨迹预测的不准确.在对旋转球进行受力分析的基础上,详细讨论了不同旋转模式下Magnus力对乒乓球飞行轨迹的影响,并设计了两个模糊神经网络分类器,分别对左右旋和上下旋的飞行轨迹进行分类.发球机实验验证了分类器的有效性.
Trajectory prediction plays a very important role in the process of playing table tennis for robot. Its accuracy determines whether the striking action will succeed or not. Since the surfaces of the racket and the table are not absolutely smooth, friction force exists during the contact process of table tennis ball and racket/table, which make the bali＇s spin. The existence of spinning influences the trajectory of the spinning ball. On the basis of force analysis, how the Magnus force influences the flying trajectory under different spinning patterns is discussed firstly, and then two fuzzy neural network classifiers are designed to estimate the spinning patterns. The experiments with serve machine show the effectiveness of the classifiers.
出处
《控制与决策》
EI
CSCD
北大核心
2014年第2期263-269,共7页
Control and Decision
基金
国家自然科学基金项目(61075035
61273337)
