UAV SWARM Health Management Project Information
We are investigating techniques that will enable the execution of continuous (24-7) mission operations using multiple autonomous vehicles (i.e., vehicle SWARMS) in a dynamic environment. We believe that a massively-distributed, intelligent airborne capability with little human supervision has the potential to provide many performance benefits in long-term mission operations. However, these benefits will not be easily achieved without a fully-integrated health management system.
As part of this study, we are developing and testing systems which include, but are not limited to, the following:
- Vehicle and mission health monitoring systems which coordinate mission task execution with maintenance
- Real-time task management systems for multiple vehicle operations
- Operator interfaces to support around-the-clock mission activities
We have constructed a unique indoor multi-vehicle testbed to study long duration missions in a controlled environment. This testbed provides an ideal platform for demonstrating algorithms that embed the fleet and vehicle health state into the mission and UAV planning by enabling researchers to examine questions such as how best to account for the impact of vehicle failures on mission success, and what are the best strategies for performing routine refueling and maintenance using real hardware.
The testbed is comprised of both aerial and ground vehicles, allowing researchers to conduct tests for a wide variety of mission scenarios. A multi-vehicle flight test from January 2006 using the testbed is shown in the figures below. Between January to mid-July 2006, we have flown over 300 multi-vehicle flight demonstrations, including over 60 flight demonstrations we completed in a two-day time span in mid-May.
Figure 1. Indoor Multi-Vehicle Flight Test using the Testbed
Figure 2. Close-up of an Indoor Multi-Vehicle Flight
The testbed is designed to emulate the full functionality of an operational UAV system. There are two major components to this testbed - the hardware architecture and the software architecture.
Figure 3. Simplified Hardware Architecture Block Diagram
We have developed a low-cost, indoor testing environment that can be used over extended periods of time to test and demonstrate the real-time capabilities of these health management algorithms in a realistic real-time environment. The hardware architecture of the system has the following components:
- Unmanned Aerial Vehicles
- Unmanned Ground Vehicles
- Positioning System and Computers
- Mission Tasking and Guidance Computers
Each system component communicates through ethernet connections and provide updates to one another in real-time according the architecture and system-level requirements. With this platform we have demonstrated single and multi-vehicle operation capabilities (in both uncoordinated and coordinated missions) with multiple air and ground vehicles. We have developed videos for a number of our vehicle tests.
In addition to the hardware components of this system, this platform has an integrated mission system architecture designed to develop and rapidly prototype hardware and software algorithms for multiple unmanned vehicle missions.
This architecture is designed to test and accommodate both mission and vehicle level planning algorithms. In the past, our research group has tested these algorithms in other systems. In the DARPA-sponsored Software Enable Control Capstone demonstration , we successfully developed and tested a system that allowed a pilot to create tasks for a single UAV to perform in real-time. This UAV was equipped with a trajectory generation algorithm that created waypoint lists for the vehicle to follow in real-time. This technology has been expanded to include multiple vehicles and has been demonstrated in , , . In addition, in , , we have successfully developed and tested mission tasking systems which will decide how vehicles are allocated to perform tasks based on environmental information in real-time. Therefore, these algorithms and capabilities have been tested on other systems in the past and are being incorporated into this testbed.
In addition, health information for each system component is accessible by all mission level processing steps. In the past, the term "health management" was used to define systems which actively monitored and managed vehicle sub-systems (e.g., flight controls, fuel management, avionics) in the event of component failures. In the context of multiple vehicle operations, we extend this definition to autonomous multi-agent teams. In this case, teams involved in a mission serve as a vehicle system. Then, each multi-agent team involved in the mission is a sub-system to the larger mission team. The health management information about each component in the mission systems enables the strategic and tactical level planners to make informed decisions about the best way to allocate resources given the impact of likely failures. Note that all levels of the architecture are implemented in parallel in real-time, and communication between each system is performed over ethernet using a pre-defined interface protocol.
If you have any questions or would like to hear more about this research effort, please email our team at
This research has been generously supported by the Boeing Company.
 M. Alighanbari and J. P. How. Cooperative Task Assignment of Unmanned Aerial Vehicles in Adversarial Environments. In Proceedings of the American Control Conference, June 2005.
 M. Alighanbari and J. P. How. Decentralized Task Assignment for Unmanned Aerial Vehicles. In Proceedings of the IEEE Conference on Decision and Control, December 2005.
 J. P. How, E. King, and Y. Kuwata. Flight Demonstrations of Cooperative Control for UAV Teams. In AIAA 3rd Unmanned Unlimited Technical Conference, Workshop and Exhibit, Chicago, IL, September 2004.
 Y. Kuwata, A. Richards, T. Schouwenaars, and J. P. How. Robust Receding Horizon Control for Multi-Vehicle Guidance. In Proceedings of the 2004 American Control Conference, June 2006.
 T. Schouwenaars, J. How, and E. Feron. Decentralized Cooperative Trajectory Planning of Multiple Aircraft with Hard Safety Guarantees. In Proceedings of the AIAA Guidance, Navigation, and Control Conference and Exhibit, Providence, RI, August 2004.
 M. Valenti, T. Schouwenaars, Y. Kuwata, E. Feron, J. How, and J. Paunicka. Implementation of a Manned Vehicle-UAV Mission System. In Proceedings of the AIAA Guidance, Navigation, and Control Conference and Exhibit, Providence, RI, August 2004.