针对装甲车辆运动状态复杂性、战场态势不确定性、战术迷惑和欺骗性导致装甲车辆集群运动轨迹难以准确预测的问题,提出一种基于密度的空间聚类应用(Density-Based Spatial Clustering of Applications with Noise,DBSCAN)和长短时记忆(L...针对装甲车辆运动状态复杂性、战场态势不确定性、战术迷惑和欺骗性导致装甲车辆集群运动轨迹难以准确预测的问题,提出一种基于密度的空间聚类应用(Density-Based Spatial Clustering of Applications with Noise,DBSCAN)和长短时记忆(Long Short Term Memory,LSTM)神经网络的装甲车辆集群轨迹预测方法。根据装甲车辆的斜坡上行驶、转向和车-车交互行驶状态,建立运动学模型。选取机动特征、环境特征和车-车交互特征等轨迹特征信息,基于双层LSTM网络预测单个装甲车辆的轨迹。基于DBSCAN算法将多条单装预测轨迹进行分段、相似度计算和聚类,获得集群代表轨迹作为装甲车辆集群的预测轨迹。仿真结果表明,所提方法能够有效预测装甲车辆集群轨迹,实现料敌于先、谋敌于前。展开更多
随着地面无人平台(Unmanned Ground Vehicles,UGVs)在复杂作业环境中的潜在应用和战略价值日益凸显,确保其自主行为的安全性变得至关重要。提出一种结合系统理论过程分析(System-Theoretic Process Analysis,STPA)和Bow-Tie模型的地面...随着地面无人平台(Unmanned Ground Vehicles,UGVs)在复杂作业环境中的潜在应用和战略价值日益凸显,确保其自主行为的安全性变得至关重要。提出一种结合系统理论过程分析(System-Theoretic Process Analysis,STPA)和Bow-Tie模型的地面无人平台系统安全分析方法。围绕遥控操作地面无人平台系统安全,通过STPA方法识别UGV系统中的不安全控制行为及其潜在风险,并利用Bow-Tie模型分析从损失致因场景到可能事故后果的事件链,得到风险传播路径和风险扩散路径。最终,基于Bow-Tie分析结果确定主被动安全分级控制措施,并通过自主安全控制器实现了系统安全管理。展开更多
In this paper, a model order reduction strategy is adopted for the static and dynamic behaviour simulation of a high-speed tracked vehicle. The total number of degree of freedom of the structure is condensed through a...In this paper, a model order reduction strategy is adopted for the static and dynamic behaviour simulation of a high-speed tracked vehicle. The total number of degree of freedom of the structure is condensed through a selection of interface degrees of freedom and significant global mode shapes, for an approximated description of vehicle dynamic behaviour. The methodology is implemented in a customised open-source software to reduce the computational efforts. The modelled tracked vehicle includes the sprung mass, the unsprung masses, connected by means of torsional bars, and all the track assemblies, composing the track chain. The proposed research activity presents a comprehensive investigation of the influence of the track chain, combined with longitudinal vehicle speed, on statics and vehicle dynamics, focusing on vertical dynamics. The vehicle response has been investigated both in frequency and time domain. In this last case road-wheel displacements are assumed as inputs for the model, under different working conditions, hence considering several road profiles with different amplitudes and characteristic excitation frequencies. Simulation results have proven a high fidelity in model order reduction approach and a significant contribution of the track chain in the global dynamic behaviour of the tracked vehicle.展开更多
文摘针对装甲车辆运动状态复杂性、战场态势不确定性、战术迷惑和欺骗性导致装甲车辆集群运动轨迹难以准确预测的问题,提出一种基于密度的空间聚类应用(Density-Based Spatial Clustering of Applications with Noise,DBSCAN)和长短时记忆(Long Short Term Memory,LSTM)神经网络的装甲车辆集群轨迹预测方法。根据装甲车辆的斜坡上行驶、转向和车-车交互行驶状态,建立运动学模型。选取机动特征、环境特征和车-车交互特征等轨迹特征信息,基于双层LSTM网络预测单个装甲车辆的轨迹。基于DBSCAN算法将多条单装预测轨迹进行分段、相似度计算和聚类,获得集群代表轨迹作为装甲车辆集群的预测轨迹。仿真结果表明,所提方法能够有效预测装甲车辆集群轨迹,实现料敌于先、谋敌于前。
文摘随着地面无人平台(Unmanned Ground Vehicles,UGVs)在复杂作业环境中的潜在应用和战略价值日益凸显,确保其自主行为的安全性变得至关重要。提出一种结合系统理论过程分析(System-Theoretic Process Analysis,STPA)和Bow-Tie模型的地面无人平台系统安全分析方法。围绕遥控操作地面无人平台系统安全,通过STPA方法识别UGV系统中的不安全控制行为及其潜在风险,并利用Bow-Tie模型分析从损失致因场景到可能事故后果的事件链,得到风险传播路径和风险扩散路径。最终,基于Bow-Tie分析结果确定主被动安全分级控制措施,并通过自主安全控制器实现了系统安全管理。
文摘In this paper, a model order reduction strategy is adopted for the static and dynamic behaviour simulation of a high-speed tracked vehicle. The total number of degree of freedom of the structure is condensed through a selection of interface degrees of freedom and significant global mode shapes, for an approximated description of vehicle dynamic behaviour. The methodology is implemented in a customised open-source software to reduce the computational efforts. The modelled tracked vehicle includes the sprung mass, the unsprung masses, connected by means of torsional bars, and all the track assemblies, composing the track chain. The proposed research activity presents a comprehensive investigation of the influence of the track chain, combined with longitudinal vehicle speed, on statics and vehicle dynamics, focusing on vertical dynamics. The vehicle response has been investigated both in frequency and time domain. In this last case road-wheel displacements are assumed as inputs for the model, under different working conditions, hence considering several road profiles with different amplitudes and characteristic excitation frequencies. Simulation results have proven a high fidelity in model order reduction approach and a significant contribution of the track chain in the global dynamic behaviour of the tracked vehicle.
