49 research outputs found
Implementation of CAPIO for Composite Adaptive Control of Cross-Coupled Unstable Aircraft
Get PDFPeer Reviewedhttp://deepblue.lib.umich.edu/bitstream/2027.42/90647/1/AIAA-2011-1460-295.pd
A Control Allocation Technique to Recover From Pilot-Induced Oscillations (CAPIO) Due to Actuator Rate Limiting
Get PDFThis paper proposes a control allocation technique that can help pilots recover from pilot induced oscillations (PIO). When actuators are rate-saturated due to aggressive pilot commands, high gain flight control systems or some anomaly in the system, the effective delay in the control loop may increase depending on the nature of the cause. This effective delay increase manifests itself as a phase shift between the commanded and actual system signals and can instigate PIOs. The proposed control allocator reduces the effective time delay by minimizing the phase shift between the commanded and the actual attitude accelerations. Simulation results are reported, which demonstrate phase shift minimization and recovery from PIOs. Conversion of the objective function to be minimized and constraints to a form that is suitable for implementation is given
Adaptive control of time delay systems and applications to automotive control problems
Get PDFThesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Mechanical Engineering, 2009.Includes bibliographical references (p. 107-114).This thesis is about the adaptive control of time delay systems with applications to automotive control problems. The stabilization of systems involving time delays is a difficult problem since the existence of a delay may induce instability or poor performance for the closed loop system. A unique approach for controlling systems with known time delay was originated by Otto Smith in the 1950s by compensating for the delayed output using input values stored over a time window of [t - [tau], t] and estimating the plant output using a model of the plant. Later, this idea was extended to include unstable plants as well, using finite-time integrals of the delayed input values thereby avoiding unstable pole-zero cancellations that may occur in Smith's controller. Adaptive versions of these delay compensating controllers were also developed with rather complicated adaptive rules which might not be practical to use in real applications. In this thesis, a simpler adaptive version of delay compensating controllers is developed, which has adaptive rules that are easily implementable and thus suitable for real life implementations. The developed controller is tested in two important automotive control problems that are idle speed control (ISC) and fuel-to-air ratio (FAR) control. These two applications, ISC and FAR control, constitute the experimental part of this research. In ISC, the objective is to regulate the engine speed to a prescribed set-point in the presence of accessory load torque disturbances such as due to air conditioning and power steering. The adaptive controller, integrated with the existing proportional spark controller, is used to drive the electronic throttle actuator. Both simulation and experimental results demonstrating the performance improvement by employing the adaptive controller are presented. Modifications and improvements to the controller structure, which were developed during the course of experimentation to solve specific problems, are also presented. In addition, the potential for the reduction in calibration time and effort which can be achieved with our approach is discussed.(cont.) The objective in FAR control is to maintain the in-cylinder FAR at a prescribed set point, determined primarily by the state of the Three-Way Catalyst (TWC), so that the pollutants in the exhaust are removed with the highest efficiency. The FAR controller must also reject disturbances due to canister vapor purge and inaccuracies in air charge estimation and wall-wetting (WW) compensation. Two adaptive controller designs are considered. The first design is based on feedforward adaptation while the second design is based on both feedback and feedforward adaptation. Both simulation and experimental results demonstrating the performance improvement by employing the APC are presented. In addition, modifications and improvements to the APC structure, which were developed during the course of the experiments, to solve specific implementation problems are presented.by Yildiray Yildiz.Ph.D
Developing Driving Strategies Efficiently: A Skill-Based Hierarchical Reinforcement Learning Approach
Full text linkDriving in dense traffic with human and autonomous drivers is a challenging
task that requires high-level planning and reasoning. Human drivers can achieve
this task comfortably, and there has been many efforts to model human driver
strategies. These strategies can be used as inspirations for developing
autonomous driving algorithms or to create high-fidelity simulators.
Reinforcement learning is a common tool to model driver policies, but
conventional training of these models can be computationally expensive and
time-consuming. To address this issue, in this paper, we propose ``skill-based"
hierarchical driving strategies, where motion primitives, i.e. skills, are
designed and used as high-level actions. This reduces the training time for
applications that require multiple models with varying behavior. Simulation
results in a merging scenario demonstrate that the proposed approach yields
driver models that achieve higher performance with less training compared to
baseline reinforcement learning methods.Comment: This work has been submitted to the IEEE for possible publication.
Copyright may be transferred without notice, after which this version may no
longer be accessibl
Predicting Pilot Behavior in Medium Scale Scenarios Using Game Theory and Reinforcement Learning
Get PDFEffective automation is critical in achieving the capacity and safety goals of the Next Generation Air Traffic System. Unfortunately creating integration and validation tools for such automation is difficult as the interactions between automation and their human counterparts is complex and unpredictable. This validation becomes even more difficult as we integrate wide-reaching technologies that affect the behavior of different decision makers in the system such as pilots, controllers and airlines. While overt short-term behavior changes can be explicitly modeled with traditional agent modeling systems, subtle behavior changes caused by the integration of new technologies may snowball into larger problems and be very hard to detect. To overcome these obstacles, we show how integration of new technologies can be validated by learning behavior models based on goals. In this framework, human participants are not modeled explicitly. Instead, their goals are modeled and through reinforcement learning their actions are predicted. The main advantage to this approach is that modeling is done within the context of the entire system allowing for accurate modeling of all participants as they interact as a whole. In addition such an approach allows for efficient trade studies and feasibility testing on a wide range of automation scenarios. The goal of this paper is to test that such an approach is feasible. To do this we implement this approach using a simple discrete-state learning system on a scenario where 50 aircraft need to self-navigate using Automatic Dependent Surveillance-Broadcast (ADS-B) information. In this scenario, we show how the approach can be used to predict the ability of pilots to adequately balance aircraft separation and fly efficient paths. We present results with several levels of complexity and airspace congestion
