Autonomous helicopter flight is widely regarded to be a highly challenging control problem. Despite this fact, human experts can reliably fly helicopters through a wide range of maneuvers, including aerobatic maneuvers at the edge of the helicopterâs capabilities. We present apprenticeship learning algorithms, which leverage expert demonstrations to efficiently learn good controllers for tasks being demonstrated by an expert. These apprenticeship learning algorithms have enabled us to significantly extend the state of the art in autonomous helicopter aerobatics. Our experimental results include the first autonomous execution of a wide range of maneuvers, including but not limited to in-place flips, in-place rolls, loops and hurricanes, and even auto-rotation landings, chaos and tic-tocs, which only exceptional human pilots can perform. Our results also include complete airshows, which require autonomous transitions between many of these maneuvers. Our controllers perform as well as, and often even better than, our expert pilot.

/pdf/autonomous-helicopter-aerobatics-through-apprenticeship-275kvd1oi2.pdf

Autonomous Helicopter Aerobatics through Apprenticeship Learning

Autonomous helicopter flight is widely regarded to be a highly challenging control problem. This paper presents the first successful autonomous completion on a real RC helicopter of the following four aerobatic maneuvers: forward flip and sideways roll at low speed, tail-in funnel, and nose-in funnel. Our experimental results significantly extend the state of the art in autonomous helicopter flight. We used the following approach: First we had a pilot fly the helicopter to help us find a helicopter dynamics model and a reward (cost) function. Then we used a reinforcement learning (optimal control) algorithm to find a controller that is optimized for the resulting model and reward function. More specifically, we used differential dynamic programming (DDP), an extension of the linear quadratic regulator (LQR).

/pdf/an-application-of-reinforcement-learning-to-aerobatic-3shntu58t0.pdf

An Application of Reinforcement Learning to Aerobatic Helicopter Flight

Based on a detailed case study on change and customisation to existing products in the aerospace industry, this paper presents a comprehensive analysis of the problems and processes associated with product change. It looks at the potential causes and effects of changes, and analyses the formal and informal processes that are used to handle change. Change processes become problematic when change to one system propagates to other systems, because the tolerance margins of individual parameters are exceeded. The paper concludes with suggestions for handling change.

Change and customisation in complex engineering domains

Helicopters have highly stochastic, nonlinear, dynamics, and autonomous helicopter flight is widely regarded to be a challenging control problem. As helicopters are highly unstable at low speeds, it is particularly difficult to design controllers for low speed aerobatic maneuvers. In this paper, we describe a successful application of reinforcement learning to designing a controller for sustained inverted flight on an autonomous helicopter. Using data collected from the helicopter in flight, we began by learning a stochastic, nonlinear model of the helicopter’s dynamics. Then, a reinforcement learning algorithm was applied to automatically learn a controller for autonomous inverted hovering. Finally, the resulting controller was successfully tested on our autonomous helicopter platform.

/pdf/autonomous-inverted-helicopter-flight-via-reinforcement-3tscnr4r5w.pdf

Autonomous Inverted Helicopter Flight via Reinforcement Learning

Modeling and Backstepping-based Nonlinear Control Strategy for a 6 DOF Quadrotor Helicopter

Basic Helicopter Aerodynamics is widely appreciated as an easily accessible, rounded introduction to the first principles of the aerodynamics of helicopter flight. Simon Newman has brought this third edition completely up to date with a full new set of illustrations and imagery. An accompanying website www.wiley.com/go/seddon contains all the calculation files used in the book, problems, solutions, PPT slides and supporting MATLAB® code. Simon Newman addresses the unique considerations applicable to rotor UAVs and MAVs, and coverage of blade dynamics is expanded to include both flapping, lagging and ground resonance. New material is included on blade tip design, flow characteristics surrounding the rotor in forward flight, tail rotors, brown-out, blade sailing and shipborne operations. Concentrating on the well-known Sikorsky configuration of single main rotor with tail rotor, early chapters deal with the aerodynamics of the rotor in hover, vertical flight, forward flight and climb. Analysis of these motions is developed to the stage of obtaining the principal results for thrust, power and associated quantities. Later chapters turn to the characteristics of the overall helicopter, its performance, stability and control, and the important field of aerodynamic research is discussed, with some reference also to aerodynamic design practice. This introductory level treatment to the aerodynamics of helicopter flight will appeal to aircraft design engineers and undergraduate and graduate students in aircraft design, as well as practising engineers looking for an introduction to or refresher course on the subject.

Basic Helicopter Aerodynamics

Basic Helicopter Aerodynamics: Seddon/Basic Helicopter Aerodynamics

Basic helicopter aerodynamics. [Third edition]

This book gives an account from first principles of the aerodynamics of helicopter flight, concentrating on the well-known Sikorsky configuration of single main rotor with tail rotor.
Early chapters deal with the aerodynamics of the rotor in hover, vertical flight, forward flight and climb. Analysis of these motions is developed to the stage of obtaining the principal results for thrust, power and associated quantities but the lengthy mathematical treatment of some textbooks is avoided.
Later chapters turn to the characteristics of the overall helicopter, its performance, stability and control, and the important field of aerodynamic research is discussed, with some reference also to aerodynamic design practice.
The Second Edition has been revised to illustrate more fully the various features of rotor aerodynamics and helicopter design. The helicopter is unique in its linking of the aerodynamic and mechanical features and a full appreciation of these air vehicles can only be achieved by understanding these interactions. Many of the extra figures illustrate the diversity in the design and operation of a helicopter and these differences are highlighted in the text.
The book is aimed initially at the needs of undergraduates and postgraduates. However, because of its conciseness, it is likely to prove useful also to workers at any stage, as a background to short industrial courses or for anyone needing a refresher course in the basics of the subject.

Basic helicopter aerodynamics. Second edition

Introduction Rotor in vertical flight: momentum theory and wake analysis Rotor in vertical flight: blade element theory Rotor mechanisms for forward flight Rotor aerodynamics in forward flight Aerodynamic design Performance Trim, stability and control

John Seddon

Papers

Basic Helicopter Aerodynamics

Basic Helicopter Aerodynamics: Seddon/Basic Helicopter Aerodynamics

Basic helicopter aerodynamics. [Third edition]

Basic helicopter aerodynamics. Second edition

Basic helicopter aerodynamics : an account of first principles in the fluid mechanics and flight dynamics of the single rotor helicopter