Unmanned aerial vehicle path planning for traffic estimation and detection of non-recurrent congestion

Unmanned aerial vehicles (UAVs) provide a novel means of extracting road and traffic information via video data. Specifically, by analyzing objects in a video frame, UAVs can be used to detect traffic characteristics and road incidents. Under congested conditions, the UAVs can supply accurate incident information where it is otherwise difficult to infer the road state from traditional speed-density measurements. Leveraging the mobility and detection capabilities of UAVs, we investigate navigation algorithms that seek 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 an ensemble Kalman filter (EnKF). In the EnKF procedure, we incorporate nonlinear traffic observations through model diagnostic variables, and we present a parameter update procedure that maintains a monotonic relationship between states and measurements. We compare the traffic and incident state estimates resulting from the coupled 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.