针对移动机器人在复杂场景中难以稳定跟随目标的问题,提出基于改进YOLOX的移动机器人目标跟随方法,主要包括目标检测、目标跟踪以及目标跟随三个部分.首先,以YOLOX网络为基础,在其框架下将主干网络采用轻量化网络MobileNetV2X,提高复杂...针对移动机器人在复杂场景中难以稳定跟随目标的问题,提出基于改进YOLOX的移动机器人目标跟随方法,主要包括目标检测、目标跟踪以及目标跟随三个部分.首先,以YOLOX网络为基础,在其框架下将主干网络采用轻量化网络MobileNetV2X,提高复杂场景中目标检测的实时性.然后,通过改进的卡尔曼滤波器获取目标跟踪状态并采用数据关联进行目标匹配,同时通过深度直方图判定目标发生遮挡后,采用深度概率信息约束及最大后验概率(Maximum a posteriori,MAP)进行匹配跟踪,确保机器人在遮挡情况下稳定跟踪目标.再采用基于视觉伺服控制的目标跟随算法,当跟踪目标丢失时,引入重识别特征主动搜寻目标实现目标跟随.最后,在公开数据集上与具有代表性的目标跟随方法进行了定性和定量实验,同时在真实场景中完成了移动机器人目标跟随实验,实验结果均验证了所提方法具有较好的鲁棒性和实时性.展开更多
In this paper, we investigate the nonlinear control problem for multi-agent formations with communication delays in noisy environments and in directed interconnection topologies. A stable theory of stochastic delay di...In this paper, we investigate the nonlinear control problem for multi-agent formations with communication delays in noisy environments and in directed interconnection topologies. A stable theory of stochastic delay differential equations is established and then some sufficient conditions are obtained based on this theory, which allow the required formations to be gained at exponentially converging speeds with probability one for time-invariant formations, time-varying formations, and time-varying formations for trajectory tracking under a special"multiple leaders" framework. Some numerical simulations are also given to illustrate the effectiveness of the theoretical results.展开更多
文摘针对移动机器人在复杂场景中难以稳定跟随目标的问题,提出基于改进YOLOX的移动机器人目标跟随方法,主要包括目标检测、目标跟踪以及目标跟随三个部分.首先,以YOLOX网络为基础,在其框架下将主干网络采用轻量化网络MobileNetV2X,提高复杂场景中目标检测的实时性.然后,通过改进的卡尔曼滤波器获取目标跟踪状态并采用数据关联进行目标匹配,同时通过深度直方图判定目标发生遮挡后,采用深度概率信息约束及最大后验概率(Maximum a posteriori,MAP)进行匹配跟踪,确保机器人在遮挡情况下稳定跟踪目标.再采用基于视觉伺服控制的目标跟随算法,当跟踪目标丢失时,引入重识别特征主动搜寻目标实现目标跟随.最后,在公开数据集上与具有代表性的目标跟随方法进行了定性和定量实验,同时在真实场景中完成了移动机器人目标跟随实验,实验结果均验证了所提方法具有较好的鲁棒性和实时性.
基金Supported by National Natural Science Foundation of China(61403133,61273215,61203148,61072121,61175075)International Postdoctoral Exchange Fellowship Program(20140034)+5 种基金Young Teachers Growth Plan of Hunan University(531107040651)China Postdoctoral Science Foundation(2013M540627)Hunan Provincial Postdoctoral Special Foundation(2013RS4042)Hunan Provincial Postdoctoral Daily Foundation(897202100)Natural Science Foundation of Hunan Province(14JJ3051)Doctoral Fund of Ministry of Education of China(20130161120016)
文摘In this paper, we investigate the nonlinear control problem for multi-agent formations with communication delays in noisy environments and in directed interconnection topologies. A stable theory of stochastic delay differential equations is established and then some sufficient conditions are obtained based on this theory, which allow the required formations to be gained at exponentially converging speeds with probability one for time-invariant formations, time-varying formations, and time-varying formations for trajectory tracking under a special"multiple leaders" framework. Some numerical simulations are also given to illustrate the effectiveness of the theoretical results.