Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Unmanned aerial vehicles (UAVs) are mainly used by military and government organizations, but with low-cost sensors, electronics, and airframes there is significant interest in using low-cost UAVs among aircraft hobbyists, academic researchers, and industries. Applications such as mapping, search and rescue, patrol, and surveillance require the UAV to autonomously follow a predefined path at a prescribed height. The most commonly used paths are straight lines and circular orbits. Path-following algorithms ensure that the UAV will follow a predefined path in three or two dimensions at constant height. A basic requirement for these path-following algorithms is that they must be accurate and robust to wind disturbances.

Unmanned Aerial Vehicle Path Following: A Survey and Analysis of Algorithms for Fixed-Wing Unmanned Aerial Vehicless

In this paper, an adaptive neural fault-tolerant control scheme is proposed for the three degrees of freedom model helicopter, subject to system uncertainties, unknown external disturbances, and actuator faults. To tackle system uncertainty and nonlinear actuator faults, a neural network disturbance observer is developed based on the radial basis function neural network. The unknown external disturbance and the unknown neural network approximation errors are treated as a compound disturbance that is estimated by another nonlinear disturbance observer. A disturbance observer-based adaptive neural fault-tolerant control scheme is then developed to track the desired system output in the presence of system uncertainty, external disturbance, and actuator faults. The stability of the whole closed-loop system is analyzed using the Lyapunov method, which guarantees the convergence of all closed-loop signals. Finally, the simulation results are presented to illustrate the effectiveness of the new control design techniques.

/pdf/adaptive-neural-fault-tolerant-control-of-a-3-dof-model-l1tfjbx8o1.pdf

Adaptive Neural Fault-Tolerant Control of a 3-DOF Model Helicopter System

A fundamental problem that the bearing rigidity theory studies is to determine when a framework can be uniquely determined up to a translation and a scaling factor by its inter-neighbor bearings While many previous works focused on the bearing rigidity of two-dimensional frameworks, a first contribution of this paper is to extend these results to arbitrary dimensions It is shown that a framework in an arbitrary dimension can be uniquely determined up to a translation and a scaling factor by the bearings if and only if the framework is infinitesimally bearing rigid In this paper, the proposed bearing rigidity theory is further applied to the bearing-only formation stabilization problem where the target formation is defined by inter-neighbor bearings and the feedback control uses only bearing measurements Nonlinear distributed bearing-only formation control laws are proposed for the cases with and without a global orientation It is proved that the control laws can almost globally stabilize infinitesimally bearing rigid formations Numerical simulations are provided to support the analysis

/pdf/bearing-rigidity-and-almost-global-bearing-only-formation-2nkkfr4vub.pdf

Bearing Rigidity and Almost Global Bearing-Only Formation Stabilization

Erbium-doped fiber devices have been extraordinarily successful due to their broad optical gain around 1.5–1.6 μm. Er-doped fiber amplifiers enable efficient, stable amplification of high-speed, wavelength-division-multiplexed signals, thus continue to dominate as part of the backbone of longhaul telecommunications networks. At the same time, Er-doped fiber lasers see many applications in telecommunications as well as in biomedical and sensing environments. Over the last 20 years significant efforts have been made to bring these advantages to the chip level. Device integration decreases the overall size and cost and potentially allows for the combination of many functions on a single tiny chip. Besides technological issues connected to the shorter device lengths and correspondingly higher Er concentrations required for high gain, the choice of appropriate host material as well as many design issues come into play in such devices. In this contribution the important developments in the field of Er-doped integrated waveguide amplifiers and lasers are reviewed and current and future potential applications are explored. The vision of integrating such Er-doped gain devices with other, passive materials platforms, such as silicon photonics, is discussed.

Erbium-doped integrated waveguide amplifiers and lasers

In this brief, a novel distributed cascade robust feedback control approach is proposed for formation and reconfiguration control of a team of vertical takeoff and landing (VTOL) unmanned air vehicles (UAVs). This approach is based on dynamic communication network. It guarantees intervehicle collision avoidance and considers dynamic constraints of UAVs. In the outer loop of the cascade formation control, a potential field approach is used to generate a desired velocity for each UAV, which ensures that the team of UAVs can perform formation flying, formation rotating and reconfiguration, avoid intervehicle collision, as well as track a specified virtual leader. In the inner loop of the cascade formation control, the velocity of each UAV is designed to track its desired velocity generated by the outer loop, subject to dynamic constraints. The proposed approach is demonstrated via both simulation and flight test.

Distributed Formation and Reconfiguration Control of VTOL UAVs

A novel multiwavelength fibre laser is proposed, which is based on a fibre loop mirror formed by a high-birefringence (HiBi) fibre, a polarisation controller, and a directional coupler By setting the polarisation controller properly, the HiBi fibre loop mirror acts as a polarisation-independent wavelength filter With this configuration, the wavelength spacing of the laser can be varied accurately by adjusting the length of the HiBi fibre Experimentally, by cooling the erbium-doped fibre with liquid nitrogen to reduce its homogeneous linewidth, stable emission at 16 wavelengths with a spacing of 08 nm and an amplitude variation of < 5 dB was achieved

Multiwavelength erbium-doped fibre laser based on a high-birefringence fibre loop mirror

Design and implementation of a robust and nonlinear flight control system for an unmanned helicopter

In this paper, we present the systematic design and implementation of a robust real-time embedded vision system for an unmanned rotorcraft for ground target following. The hardware construction of the vision system is presented, and an onboard software system is developed based on a multithread technique capable of coordinating multiple tasks. To realize the autonomous ground target following, a sophisticated feature-based vision algorithm is proposed by using an onboard color camera and navigation sensors. The vision feedback is integrated with the flight control system to guide the unmanned rotorcraft to follow a ground target in flight. The overall vision system has been tested in actual flight missions, and the results obtained show that the overall system is very robust and efficient.

A Robust Real-Time Embedded Vision System on an Unmanned Rotorcraft for Ground Target Following

Motivated by the 2013 International UAV Innovation Grand Prix, we design and implement a real-time vision system for an unmanned helicopter autonomously transferring cargoes between two platforms. In the competition, four cargoes are initially placed inside four circles on one platform, respectively. They are required to be transferred one by one into the four circles on the other platform. This paper presents the core algorithms of the proposed vision system on ellipse detection, ellipse tracking, and single-circle-based position estimation. Experiments and the great success of our team in the competition have verified the efficiency, accuracy, and robustness of the algorithms. Our team was ranked first in the final round competition.

Xiangxu Dong

Papers

Distributed Formation and Reconfiguration Control of VTOL UAVs

Multiwavelength erbium-doped fibre laser based on a high-birefringence fibre loop mirror

Design and implementation of a robust and nonlinear flight control system for an unmanned helicopter

A Robust Real-Time Embedded Vision System on an Unmanned Rotorcraft for Ground Target Following

A Robust Real-Time Vision System for Autonomous Cargo Transfer by an Unmanned Helicopter