Flying an unmanned helicopter with an iPhone:
Unmanned Aerial Vehicles (UAVs), such as the military's Predator drone, currently require sophisticated and intensive training to operate. For example, an Air Force Predator UAV requires two full-time operators, both certified pilots who have attended a 10-week training course. Advances in UAV design have led to personal, micro aerial vehicles (MAVs) which can range in size from a fly to a basketball. MAVs are even more difficult to fly than their larger cousins due to a lack of conventional control surfaces like rudders and flaps. These MAVs are intended for use by soldiers or other highly trained first-responder personnel for real-time scouting and exploration. It is therefore impractical to demand the additional specialized training required to operate such a complex craft with a traditional joystick or remote control.
David Pitman's Master's thesis, Collaborative Micro Aerial Vehicle Exploration of Outdoor Environments, created and analyzed a controller, MAV-VUE, for flying these MAVs which uses an iPhone. MAV-VUE allows users to control a MAV via high-level waypoint commands, or through fine-grained nudge controls. This innovation, which can work on any hand-held device, can be extended to operate any type of robot such as a bomb disposal robot.
New Use for Your iPhone: Controlling Drones by Wired.com
Research sponsored by ONR and The Boeing Company
Deciding if and what objects should be engaged in a Ballistic Missile Defense System (BMDS) scenario involves a number of complex issues. The system is large and the timelines may be on the order of a few minutes, which drives designers to highly automate these systems. On the other hand, the critical nature of BMD engagement decisions suggests exploring a human-in-the-loop (HIL) approach to allow for judgment and knowledge-based decisions, which provide for potential automated system override decisions. This BMDS problem is reflective of the role allocation conundrum faced in many supervisory control systems, which is how to determine which functions should be mutually exclusive and which should be collaborative.
Jason Rathje's Master's thesis, Human-Automation Collaboration in Occluded Trajectory Smoothing, described two experiments that quantitatively investigated human/automation tradeoffs in the specific domain of tracking problems. Human participants in both experiments were tested in their ability to smooth trajectories in different scenarios. In the first experiment, they clearly demonstrated an ability to assist the algorithm in more difficult, shorter timeline scenarios. The second experiment combined the strengths of both human and automation in those scenarios in order to produce a human-augmented system. Comparison of the augmented system to the algorithm showed that adjusting the criterion for having human participation could significantly alter the solution. The appropriate criterion would be specific to each application of this augmented system.
Research sponsored by Lincoln Lab
For the future vision of a single human operator controlling multiple heterogeneous unmanned vehicles (UVs), operators will conduct high level goal-based control, in contrast to more low-level vehicle-based control. To achieve this type of control, operators will be assisted by automated planners, which are generally faster and more accurate than humans at path planning and task allocation in a multivariate, dynamic, time-pressured environment. Human management of the automated planner is crucial, however, as automated planners do not always generate accurate solutions, especially in the presence of uncertain or incomplete information.
Research areas include: