Mariam Faied

Vehicle Routing Problem Instances: Application to Multi-UAV Mission Planning

variants have been studied and found applications in the real world. This paper briey surveys VRP instances with applications to multi-objective Unmanned Aerial Vehicle (UAV) operations. Focusing on multi-objective multi-UAV mission planning problems, we try to take advantage of the literature in the VRP and its variants. We show that each military multi-UAV mission has its corresponding VRP variant. We present a novel algorithm that relies on an enhanced tree search algorithm to solve complex multi-UAV mission planning problems with complex constraints. In simulation, we introduce examples for practical problem sizes in military UAV applications.

UAVs Dynamic Mission Management in Adversarial Environments

We address a dynamic configuration strategy for teams of Unmanned Air Vehicles (UAVs). A team is a collection of UAVs which may evolve through different organizations, called configurations. The team configuration may change with time to adapt to environmental changes, uncertainty, and adversarial actions. Uncertainty comes from the stochastic nature of the environment and from incomplete knowledge of adversary behaviors. To each configuration, there corresponds a set of different properties for the UAVs in the team. The design for the configuration control problem involves a distributed hierarchical control architecture where the properties of the system can be formally analyzed. We do this in the framework of dynamic networks of hybrid automata. We present results from simulation to demonstrate different scenarios for adversarial response.

Formation control with collision avoidance

We present a formation flight control strategy featuring a collision avoidance scheme. The control algorithm is based on a Sliding Mode controller. The controller sliding surfaces account for aircraft maneuvering limitations, restricting the required velocities to a feasible set. Further, the relative position between vehicles affects the sliding surfaces shape, enabling collision avoidance. The control method derivation is based on an extended unicycle model, resulting in a controller adequate for fixed wing aircraft.

Dynamic optimal control of Multiple Depot Vehicle Routing Problem with Metric Temporal Logic

This paper discusses a class of mission planning problems that generalizes the standard Multiple Depot Vehicle Routing Problem with Time Windows (MDVRPTW) to incorporate complicated technical constraints. These constraints are specified via Metric Temporal Logic (MTL). A tree search algorithm is provided to solve that novel MDVRPTW with MTL specifications (MDVRPMTL) to optimality. In this work, we use tree search algorithm to seek the optimal flyable trajectories for teams of UAVs starting from different depots to complete missions with complicated time and technical requirements. Then a Stochastic Dynamic Programming (SDP) based algorithm is proposed to dynamically tune the UAV teams in order to secure them against adversarial actions. Examples for practical mission planning problems, in which MTL is used as a high level language to specify complex mission tasks, are presented and discussed in the paper.

Mixed-initiative nested classification by optimal thresholding

The purpose of this paper is to demonstrate that having two classifiers, a trichotomous classifier (true, false, or unknown) with workload-independent performance that turns over the data classified as unknown to a binary classifier (true or false) with workload-dependent performance, gives superior classification performance (lower probability of misclassification) compared to a single dichotomous classifier. We relate the classifiers performance to the inherent difficulty of the classification task at hand (classifiability), and compare the performance of different classifiers.

Specification and Planning of Interactive UAV Missions in Adversarial Environments

In this paper, specification and planning of UAV missions, in which interaction with the operators, adversaries, and the environment plays a crucial role, are studied. A novel specification method is introduced to model interactive tasks in UAV missions and process algebra framework is used to model complex interactive tasks from relatively simple ones. An anytime state-space search algorithm is proposed. The algorithm effectively searches for a feasible solution and improves on such solution over time, eventually terminating with an optimal solution.

Path planning for optimal classification

As stated in the Office of the Secretary of Defenses Unmanned Aircraft Systems Roadmap 2005-2030, reconnaissance is the number one priority mission for Unmanned Air Vehicles (UAVs) of all sizes. During reconnaissance missions, classification of objects of interest (e.g, as friend or foe) is key to mission performance. Classification is based on information collection, and it has generally been assumed that the more information collected, the better the classification decision. Although this is a correct general trend, a recent study has shown it does not hold in all cases. This paper focuses on presenting methods to plan paths for unmanned vehicles that optimize classification decisions (as opposed to the amount of information collected). We consider an unmanned vehicle (agent) classifying an object of interest in a given area. The agent plans its path to collect the information most relevant to optimizing its classification performance, based on the maximum likelihood ratio. In addition, a classification performance measure for multiple measurements is analytically derived.

Modeling and optimizing military air operations

Dynamic programming has recently received significant attention as a possible technology for formulating control commands for decision makers in an extended complex enterprise that involves adversarial behavior. Enterprises of this type are typically modeled by a nonlinear discrete time dynamic system. The state is controlled by two decision makers, each with a different objective function and different hierarchy of decision making structure. To illustrate this enterprise, we derive a state space dynamic model of an extended complex military operation that involves two opposing forces engaged in a battle. The model assumes a number of fixed targets that one force is attacking and the other is defending. Due to the number of control commands, options for each force, and the steps during which the two forces could be engaged, the optimal solution for such a complicated dynamic game over all stages is computationally extremely difficult, if not impossible, to propose. As an alternative, we propose an expeditious suboptimal solution for this type of adversarial engagement. We discuss a solution approach where the decisions are decomposed hierarchically and the task allocation is separate from cooperation decisions. This decoupled solution, although suboptimal in the global sense, is useful in taking into account how fast the decisions should be in the presence of adversaries. An example scenario illustrating this military model and our solution approach is presented.

Autonomous Sensors Collaboration for Moving Object Classification

Wireless Sensor Networks (WSN) perform collaborative distributed sensing of a moving object in an environment for the purpose of classification. This requires collecting measurements from as many sensors as possible to classify the object. However, there is a tradeoff between the value of information contained in a distributed set of measurements and the energy cost of acquiring these measurements, fusing them into a belief and transmitting the updated belief. To manage this tradeoff, sensor selection schemes are used. In this paper, the sensor selection scheme proceeds as a sequence of rounds as follows. The network chooses an active set of sensors at each round based on physical proximity to the object. From this set, one sensor is selected by bidding to take a measurement. This measurement is transmitted to the sensor selected at the next round. The main contribution is to dynamically optimize the classification performance for a given cost of sensing, communication and computation. The method is illustrated by an example.

Communication-constrained distributed task assignment

This paper considers the problem of distributed assignment of tasks to agents in the presence of task constraints, where the agents use a known, but arbitrary communication topology. The task assignment problem considered here requires that all agents that perform tasks related by a task constraint be able to communicate directly. The problem is motivated by complex military missions where tasks are assigned to various vehicles and tasks must be scheduled to meet constraints between them. This requires communication between vehicles responsible for tasks that are related by constraints. The physically distributed and dynamic nature of such missions combined with unreliable communication motivates algorithms that can perform the required distributed planning. Toward this goal, we introduce a method that assigns tasks under the restrictions imposed by these mission constraints. The new method presented here is a distributed search designed to solve a nonlinear, distributed constrained assignment problem for which a proof of correctness is presented. The method is illustrated on an example involving two unmanned air vehicles and two unmanned ground vehicles.