Corey Ippolito

Neural Adaptive Flight Control Testing on an Unmanned Experimental Aerial Vehicle

Unmanned Aerial Vehicles have demonstrated potential as being effective platforms for supporting scientific and exploratory missions. They are capable of performing long endurance flights, and reaching remote areas that may be too dangerous for humans. As their role and types of missions expand, challenges are presented which require onboard systems to have increasingly higher levels of intelligence and adaptability. Missions requiring radical reconfiguration to carry mission-specific payloads, or operations under uncertain or unknown flight conditions, will require intelligent flight controllers that are capable of being deployed with minimal prior testing. This paper describes the testing of a neural adaptive flight controller that was designed to provide consistent handling qualities across flight conditions and for different aircraft configurations. The controller was flight tested on an unmanned experimental aerial vehicle, without the benefit of extensive gain tuning or explicit knowledge of the aircraft’s aerodynamic characteristics. An overview of the neural adaptive flight controller is presented, along with a description of the experimental aerial vehicle test platform, and flight test results that demonstrate a dramatic improvement in handling qualities resulting from neural adaptation. I. Introduction HE Intelligent Flight Control (IFC) project at NASA Ames Research Center endeavors to investigate, maturate, and validate the next generation of intelligent flight controllers that exhibit higher levels of adaptability and autonomy than the current state of the art, reduce the costs associated with flight control law development, and can be applied to a wider-range of vehicle classes without significant development costs. The current IFC architecture is based on neural network augmentation, and is designed to enhance the handling qualities and response of a vehicle system subject to control surface failures or uncertainty in vehicle aerodynamic response resulting from structural damage, failures, or model inaccuracy. This technology has the promise to increase overall vehicle safety by adapting to changes in aircraft dynamics due to damage or failures, reduce cost associated with flight control law development by providing consistent handling qualities across flight regimes and variable aircraft configurations, and allow the application of generic control designs over a wide-range of vehicle classes, for example from commercial transports to high performance military aircraft and experimental concepts. The process of validating experimental control technologies typically progresses from analytical analysis through testing using increasing levels of simulation fidelity to full-scale vehicle testing. Simulation testing has taken on increased importance over the past few decades. The rapid increase in computational power and tool sophistication available to researchers has allowed for more comprehensive testing and validation to be performed in the lab environment while providing results in a much timelier fashion. Analysis tools such as Matlab and Simulink integrate analysis tools with simulation capability seamlessly, and provide mechanisms for converting these designs directly to source code that can be quickly integrated into embedded flight vehicle control systems. Despite the dramatic advances in computational technology, a crucial step in the maturation and validation of any research control technologies is real-world experimental flight testing on fully developed aircraft systems. The magnitude and severity of implementation-specific artifacts on a theoretical control construct may not be fully

A Trajectory Generation Approach for Payload Directed Flight

Presently, flight systems designed to perform payload-centric maneuvers require preconstructed procedures and special hand-tuned guidance modes. To enable intelligent maneuvering via strong coupling between the goals of payload-directed flight and the autopilot functions, there exists a need to rethink traditional autopilot design and function. Research into payload directed flight examines sensor and payload-centric autopilot modes, architectures, and algorithms that provide layers of intelligent guidance, navigation and control for flight vehicles to achieve mission goals related to the payload sensors, taking into account various constraints such as the performance limitations of the aircraft, target tracking and estimation, obstacle avoidance, and constraint satisfaction. Payload directed flight requires a methodology for accurate trajectory planning that lets the system anticipate expected return from a suite of onboard sensors. This paper presents an extension to the existing techniques used in the literature to quickly and accurately plan flight trajectories that predict and optimize the expected return of onboard payload sensors.

Applications of payload directed flight

Next generation aviation flight control concepts require autonomous and intelligent control system architectures that close control loops directly around payload sensors in manner more integrated and cohesive that in traditional autopilot designs. Research into payload and sensor directed flight control at NASA Ames Research Center is investigating new and novel architectures that can satisfy the requirements for next generation control and automation concepts for aviation. Tighter integration between sensor and machine require the definition of specific sensor directed control modes to tie the sensor data directly into a vehicle control structures throughout the entire control architecture, from low-level stability and control loops, to higher level mission planning and scheduling reasoning systems. Payload directed flight system provide guidance, navigation, and control for vehicle platforms hosting a suite of onboard payload sensors, performing missions that require observation of external partially observable systems or phenomena. This paper outlines related research into the field of payload directed flight, and outlines requirements and operating concepts for payload directed flight systems based on identified needs from the scientific literature.

Six-DOF Trajectory Tracking for Payload Directed Flight Using Trajectory Linearization Control

Payload Directed Flight (PDF) calls for agile and precise tracking control of an air vehicle that poses significant challenges to current flight control techniques. To support the goals of NASA’s Payload Directed Flight program, Trajectory Linearization Control (TLC) can provide robust, agile tracking of online-generated near-optimal trajectories for a wide variety of applications. In this paper we describe a 6DOF tracking controller design for a generic general aviation (GA) aircraft dynamics model using TLC. Initial design verification is presented via simulation results.

Cognitive Emotion Layer Architecture for Intelligent UAV Planning, Behavior and Control

Remote planetary exploration by autonomous vehicles in uncertain environments requires dynamic and highly adaptive decision making, behavior, and control mechanisms to maximize the chances of successful mission completion. We present in this paper an adaptive architecture for cognition, behavior and control of an autonomous unmanned aerial vehicle (UAV) Mars explorer called the Cognitive Emotion Layer (CEL) architecture that uses dynamical emotional response mechanisms to model explorers response to continuous stimuli and provides adaptive decision making and control capabilities for the exploration platform

Polymorphic Control Reconfiguration in an Autonomous UAV with UGV Collaboration

The emergence of distributed technologies as a reliable infrastructure for real-time control is enabling a new generation of distributed plug-and-play control architectures and methodologies; increasingly common are control systems that pass real-time data across traditional system boundaries to utilize distributed remote sensing, processing, and actuation. The polymorphic control systems (PCS) project formalizes constructs that permits topological reconfiguration of control systems that span multiple heterogeneous systems and multiple communication mediums, towards the goal of control coordination and strategy optimization in a multi-system environment, increased resilience to failure and uncertainty, increased overall and individual performance, and better utilization of available resources. This paper presents the concepts behind PCS, and presents results from a flight test experiment involving distributed reconfiguration of an autonomous landing controller in a collaborative multi-vehicle environment. These flight test experiments demonstrate one of the goals of polymorphic reconfiguration: providing emergency assistance and collaborative coordination between multiple systems to achieve safely the mission critical objectives, where a system failure would have resulted in the loss of the aircraft.

An Integrated Safety and Systems Engineering Methodology for Small Unmanned Aircraft Systems

This paper presents an integrated methodology for addressing safety concerns during the systems engineering of small Unmanned Aircraft Systems (sUAS). We describe both the systems and safety engineering activities performed, their interrelations, and how they complement range safety analysis. The broad goal of this work is to support the derivation of an airworthiness statement, and the subsequent application for a Certificate of Authorization (COA) to operate sUAS in the National Airspace System (NAS). We exemplify our methodology by presenting its application to the Swift UAS and its payload data system, both of which are under development at NASA Ames Research Center.

Topological Constructs for Automatic Reconfiguration of Polymorphic Control Systems

The emergence of distributed technologies as a reliable infrastructure for real-time control is enabling a new generation of distributed plug-and-play control architectures and methodologies; increasingly common are control system formulations configured across traditional system boundaries that utilize distributed remote sensing, processing, and actuation. The formalization of topological control constructs that permit autonomous reconfiguration in an unrestrained topology over distributed system architectures to enhance the level of resilience and adaptation demonstrated by composite systems has the promise of providing controllers that demonstrate increased resilience to failure and uncertainty, and increased performance by better utilization of available resources. This formalization enables the realization of control structures that give rise to polymorphic control systems: such systems can fundamentally restructure in a timely manner to optimize control system topologies that share resources across multiple heterogeneous systems with disparate individual system goals to take advantage of temporal topological possibilities, restructuring accordingly as the composite systems evolve over time and the availability of resources change. Autonomous reconfiguration would increase system resilience to component-failure, enable systems to exploit temporary configuration possibilities to decrease objective costs, and provide adaptability under the face of uncertainty. This paper introduces a topological formulation to model the domain of distributed plug-and-play control systems and demonstrates its application to an autonomous multi-vehicle control problem.

Concepts of Airspace Structures and System Analysis for UAS Traffic flows for Urban Areas

This paper addresses a system centric approach for design and analysis of airspace use in urban unmanned aerial vehicle (UAS) traffic flow control. The approach is based on numerical traffic simulations with a behavioral model of UASs for estimating characteristics of the future UAS air traffic in urban areas and performances of airspace structures. A concept on urban UAS traffic flow control is proposed with various airspace structural designs of different levels of freedom in flight, and a microscopic traffic model of UASs in one of the designs is developed. Fundamental diagrams of simple UAS traffic are obtained and performances of basic airspace structures are compared by using the traffic simulations.

Small Unmanned Aircraft System (sUAS) Trajectory Modeling in Support of UAS Traffic Management (UTM)

Small unmanned aircraft system (sUAS), as defined by the FAA, refers to a small unmanned aircraft weighing less than 55 pounds on takeoff, and its associated elements that are required for the safe and efficient operation of the small unmanned aircraft in the national airspace system. The unmanned aircraft system (UAS) traffic management (UTM) system is envisioned by NASA to enable civilian low-altitude airspace and UAS operations by providing services such as airspace design, corridors, dynamic geofencing, severe weather and wind avoidance, congestion management, terrain avoidance, route planning and rerouting, separation management, sequencing and spacing, and contingency management. Trajectory modeling and prediction methods are foundational capabilities in support of UTM to achieve its goals. This paper presents a framework for the development and validation of trajectory modeling and prediction methods for diverse types of sUASs under nominal environment and under a variety of realistic potential hazards, including adverse environmental conditions, and vehicle and system failures. Results from initial analysis of major components of the framework are also presented. Detailed results from the development and validation will be reported in subsequent papers as the research progresses.