Boyles and Claudel Receive NSF Grant to Study UAVs
On today’s roadways, traffic conditions are currently monitored by using either fixed, static sensors or crowdsourced data. Using a combination of traffic sensor measurement data and past information about typical traffic patterns, these observations provide a sparse and often inaccurate traffic map that cannot reflect real-time conditions. On a normal day, these maps are typically accurate enough for the average commuter’s use. However, when a disruption to usual traffic patterns occur, traffic maps need to become more responsive and alert travelers to current traffic conditions. An inexpensive option for improving current traffic monitoring systems is to deploy mobile sensors—such as a swarm of unmanned aerial vehicles (UAVs), which can obtain additional data on disruptions and their impacts as needed.
To lay the foundations for such a system, the NSF recently awarded CTR’s Christian Claudel and Stephen Boyles $397,933 to pioneer the use of mobile wireless sensor networks in UAVs (NSF grant number 1636154). The project kicks off on January 1, 2017, with an estimated end date of December 2019.
The optimal sensor placement problem solved by this research will allow the system to automatically compute the best path that each UAV should take to sense the traffic conditions, enabling quick updates on the traffic situation. The optimal sensor placement problem solved by this research will allow the network system to automatically compute the best path that each UAV should take to sense the traffic conditions, enabling quick updates on the traffic situation. This research could provide the means to sense traffic in real time, as well as open new horizons for mobile sensing systems.
To achieve this goal, Claudel and Boyles plan to develop an efficient simulation framework for networks by modeling traffic flow. The team will model a way to optimally route a set of UAVs over a transportation network to decrease the uncertainty of traffic estimation and identify the current state of traffic. The team will also investigate the problem of optimal routing of ground vehicles with partial traffic sensor information.