Autopilot systems are typically composed of an "inner loop" providing stability and control, while an "outer loop" is responsible for mission-level objectives, e.g. way-point navigation. Autopilot systems for UAVs are predominately implemented using Proportional, Integral Derivative (PID) control systems, which have demonstrated exceptional performance in stable environments. However more sophisticated control is required to operate in unpredictable, and harsh environments. Intelligent flight control systems is an active area of research addressing limitations of PID control most recently through the use of reinforcement learning (RL) which has had success in other applications such as robotics. However previous work has focused primarily on using RL at the mission-level controller. In this work, we investigate the performance and accuracy of the inner control loop providing attitude control when using intelligent flight control systems trained with the state-of-theart RL algorithms, Deep Deterministic Gradient Policy (DDGP), Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO). To investigate these unknowns we first developed an open-source high-fidelity simulation environment to train a flight controller attitude control of a quadrotor through RL. We then use our environment to compare their performance to that of a PID controller to identify if using RL is appropriate in high-precision, time-critical flight control.

The purpose of the present research was to develop general guidelines to assist practitioners in setting up operational computerized adaptive testing (CAT) systems based on the graded response model. Simulated data were used to investigate the effects of systematic manipulation of various aspects of the CAT procedures for the model. The effects of three major variables were examined: item pool size, the stepsize used along the trait continuum until maximum likelihood estimation could be calculated, and the stopping rule employed. The findings suggest three guidelines for graded response CAT procedures: (1) item pools with as few as 30 items may be adequate for CAT; (2) the variable-stepsize method is more useful than the fixedstepsize methods; and (3) the minimum-standard-error stopping rule will yield fewer cases of nonconvergence, administer fewer items, and produce higher correlations of CAT &thetas; estimates with full-scale estimates and the known &thetas;s than the minimum-information stopping rule. The implications of these findings for psychological assessment are discussed. Index terms: computerized adaptive testing, graded response model, item response theory, polychotomous scoring.

No abstract

We introduce a Markov-model-based framework for Moving Target Defense (MTD) analysis. The framework allows modeling of broad range of MTD strategies, provides general theorems about how the probability of a successful adversary defeating an MTD strategy is related to the amount of time/cost spent by the adversary, and shows how a multi-level composition of MTD strategies can be analyzed by a straightforward combination of the analysis for each one of these strategies. Within the proposed framework we define the concept of security capacity which measures the strength or effectiveness of an MTD strategy: the security capacity depends on MTD specific parameters and more general system parameters. We apply our framework to two concrete MTD strategies.

Simulated datasets were used to research the effects of the systematic variation of three major variables on the performance of computerized adaptive testing (CAT) procedures for the partial credit model. The three variables studied were the stopping rule for terminating the CATs, item pool size, and the distribution of the difficulty of the items in the pool. Results indicated that the standard error stopping rule performed better across the variety of CAT conditions than the minimum information stopping rule. In addition it was found that item pools that consisted of as few as 30 items were adequate for CAT provided that the item pool was of medium difficulty. The implications of these findings for implementing CAT systems based on the partial credit model are discussed.