Unmanned aerial vehicles (UAVs) provide a novel means of extracting road and traffic information from video data. In particular, by analyzing objects in a video frame, UAVs can detect traffic characteristics and road incidents. Leveraging the mobility and detection capabilities of UAVs, we investigate a navigation algorithm that seeks to maximize information on the road/traffic state under non-recurrent congestion. We propose an active exploration framework that (1) assimilates UAV observations with speed-density sensor data, (2) quantifies uncertainty on the road/traffic state, and (3) adaptively navigates the UAV to minimize this uncertainty. The navigation algorithm uses the A-optimal information measure (mean uncertainty), and it depends on covariance matrices generated by a dual state ensemble Kalman filter (EnKF). In the EnKF procedure, since observations are a nonlinear function of the incident state variables, we use diagnostic variables that represent model predicted measurements. We also present a state update procedure that maintains a monotonic relationship between incident parameters and measurements. We compare the traffic/incident state estimates resulting from the UAV navigation-estimation procedure against corresponding estimates that do not use targeted UAV observations. Our results indicate that UAVs aid in detection of incidents under congested conditions where speed-density data are not informative.

翻译：无人驾驶航空飞行器(无人驾驶飞行器)提供了一种从视频数据中提取道路和交通信息的新手段。特别是,通过在视频框架中分析物体,无人驾驶飞行器能够检测交通特征和道路事故。利用无人驾驶飞行器的移动和检测能力,我们调查了一种导航算法,该算法力求在非经常性交通堵塞下最大限度地增加道路/交通状态信息。我们提议了一个积极的勘探框架,该框架(1) 将无人驾驶飞行器观测与快速密度传感器数据相提并论,(2) 量化道路/交通状态的不确定性,(3) 以适应性方式导航无人驾驶飞行器,以尽量减少这种不确定性。导航算法使用A最佳信息计量(程度不确定性),并取决于由双重州整体卡尔曼过滤器生成的共变矩阵。在EnKF程序中,由于观测是事件状态变量的非线性功能,我们使用诊断变量作为模型的预测测量。我们还提出了一个州更新程序,在事故参数和测量之间保持单一的关联性关系。我们比较了从UAV导航测算结果中得出的交通/状态估计结果,而不是根据AV测算中的数据速度。