Rapid prototyping framework for visual control of autonomous micro aerial vehicles

Rapid prototyping environments can speed up the research of visual control algorithms. We have designed and implemented a software framework for fast prototyping of visual control algorithms for Micro Aerial Vehicles (MAV). We have applied a combination of a proxy-based network communication architecture and a custom Application Programming Interface. This allows multiple experimental configurations, like drone swarms or distributed processing of a drone's video stream. Currently, the framework supports a low-cost MAV: the Parrot AR.Drone. Real tests have been performed on this platform and the results show comparatively low figures of the extra communication delay introduced by the framework, while adding new functionalities and flexibility to the selected drone. This implementation is open-source and can be downloaded from www.vision4uav.com/?q=VC4MAV-FW

Experimental validation of an unpowered unmanned aerial system : application to forced landing scenarios

The ability to perform autonomous emergency (forced) landings is one of the key technology enablers identified for UAS. This paper presents the flight test results of forced landings involving a UAS, in a controlled environment, and which was conducted to ascertain the performances of previously developed (and published) path planning and guidance algorithms. These novel 3-D nonlinear algorithms have been designed to control the vehicle in both the lateral and longitudinal planes of motion. These algorithms have hitherto been verified in simulation. A modified Boomerang 60 RC aircraft is used as the flight test platform, with associated onboard and ground support equipment sourced Off-the-Shelf or developed in-house at the Australian Research Centre for Aerospace Automation(ARCAA). HITL simulations were conducted prior to the flight tests and displayed good landing performance, however, due to certain identified interfacing errors, the flight results differed from that obtained in simulation. This paper details the lessons learnt and presents a plausible solution for the way forward.

A spatial collision avoidance strategy for UAVs in a non-cooperative environment

This paper presents a feasible spatial collision avoidance approach for fixed-wing unmanned aerial vehicles (UAVs). The proposed strategy aims to achieve the desired relative bearing in the horizontal plane and relative elevation in the vertical plane so that the host aircraft is able to avoid collision with the intruder aircraft in 3D. The host aircraft will follow a desired trajectory in the collision avoidance course and resume the pre-arranged trajectory after collision is avoided. The approaching stopping condition is determined for the host aircraft to trigger an evasion maneuver to avoid collision in terms of measured heading. A switching controller is designed to achieve the spatial collision avoidance strategy. Simulation results demonstrate that the proposed approach can effectively avoid spatial collision, making it suitable for integration into flight control systems of UAVs.

A gust-attenuation controller for fixed-wing UAVs during collision avoidance course

This paper presents a nonlinear gust-attenuation controller to stabilize velocities, attitudes and angular rates of a fixed-wing unmanned aerial vehicle (UAV) in the presence of wind gusts. The proposed controller aims to achieve a steady-state flight condition such that the host UAV can avoid airspace collision with other UAVs during the cruise flight. Based on the typical UAV model capturing flight aerodynamics, a nonlinear Hinf controller is developed with rapid response property in consideration of actuator constraints. Simulations are conducted for the Shadow UAV to verify performance of the proposed controller. Comparative studies with the proportional-integral derivative (PID) controllers demonstrate that the proposed controller exhibits great performance improvement in a gusty environment, making it suitable for integration into the design of flight control systems for cruise flight with safety guarantees.

See-and-avoid quadcopter using fuzzy control optimized by cross-entropy

In this work we present an optimized fuzzy visual servoing system for obstacle avoidance using an unmanned aerial vehicle. The cross-entropy theory is used to optimise the gains of our controllers. The optimization process was made using the ROS-Gazebo 3D simulation with purposeful extensions developed for our experiments. Visual servoing is achieved through an image processing front-end that uses the Camshift algorithm to detect and track objects in the scene. Experimental flight trials using a small quadrotor were performed to validate the parameters estimated from simulation. The integration of cross- entropy methods is a straightforward way to estimate optimal gains achieving excellent results when tested in real flights.

Quadcopter see and avoid using a fuzzy controller

Unmanned Aerial Vehicles (UAVs) industry is a fast growing sector. Nowadays, the market offers numerous possibilities for off-the-shelf UAVs such as quadrotors or fixed-wings. Until UAVs demonstrate advance capabilities such as autonomous collision avoidance they will be segregated and restricted to flight in controlled environments. This work presents a visual fuzzy servoing system for obstacle avoidance using UAVs. To accomplish this task we used the visual information from the front camera. Images are processed off-board and the result send to the Fuzzy Logic controller which then send commands to modify the orientation of the aircraft. Results from flight test are presented with a commercial off-the-shelf platform.

UAS See-and-Avoid using two different approaches of Fuzzy Control

This work presents two UAS See and Avoid approaches using Fuzzy Control. We compare the performance of each controller when a Cross-Entropy method is applied to optimase the parameters for one of the controllers. Each controller receive information from an image processing front-end that detect and track targets in the environment. Visual information is then used under a visual servoing approach to perform autonomous avoidance. Experimental flight trials using a small quadrotor were performed to validate and compare the behaviour of both controllers

Flight trial of an electro-optical sense-and-avoid system

This paper presents the flight trials of an electro-optical (EO) sense-and-avoid system onboard a Cessna host aircraft (camera aircraft). We focus on the autonomous collision avoidance capability of the sense-and-avoid system; that is, closed-loop integration with the onboard aircraft autopilot. We also discuss the system’s approach to target detection and avoidance control, as well as the methodology of the flight trials. The results demonstrate the ability of the sense-and-avoid system to automatically detect potential conflicting aircraft and engage the host Cessna autopilot to perform an avoidance manoeuvre, all without any human intervention

Time-varying bispectral analysis of auditory evoked multi-channel scalp EEG

Time-varying bispectra, computed using a classical sliding window short-time Fourier approach, are analyzed for scalp EEG potentials evoked by an auditory stimulus and new observations are presented. A single, short duration tone is presented from the left or the right, direction unknown to the test subject. The subject responds by moving the eyes to the direction of the sound. EEG epochs sampled at 200 Hz for repeated trials are processed between -70 ms and +1200 ms with reference to the stimulus. It is observed that for an ensemble of correctly recognized cases, the best matching timevarying bispectra at (8 Hz, 8Hz) are for PZ-FZ channels and this is also largely the case for grand averages but not for power spectra at 8 Hz. Out of 11 subjects, the only exception for time-varying bispectral match was a subject with family history of Alzheimer’s disease and the difference was in bicoherence, not biphase.

Sequential fusion of decisions from adaptive and random samples for controlled verification of errors

Fusion techniques have received considerable attention for achieving performance improvement with biometrics. While a multi-sample fusion architecture reduces false rejects, it also increases false accepts. This impact on performance also depends on the nature of subsequent attempts, i.e., random or adaptive. Expressions for error rates are presented and experimentally evaluated in this work by considering the multi-sample fusion architecture for text-dependent speaker verification using HMM based digit dependent speaker models. Analysis incorporating correlation modeling demonstrates that the use of adaptive samples improves overall fusion performance compared to randomly repeated samples. For a text dependent speaker verification system using digit strings, sequential decision fusion of seven instances with three random samples is shown to reduce the overall error of the verification system by 26% which can be further reduced by 6% for adaptive samples. This analysis novel in its treatment of random and adaptive multiple presentations within a sequential fused decision architecture, is also applicable to other biometric modalities such as finger prints and handwriting samples.

Sequential fusion of decisions with favorable dependence for controlled verification errors

Statistical dependence between classifier decisions is often shown to improve performance over statistically independent decisions. Though the solution for favourable dependence between two classifier decisions has been derived, the theoretical analysis for the general case of 'n' client and impostor decision fusion has not been presented before. This paper presents the expressions developed for favourable dependence of multi-instance and multi-sample fusion schemes that employ 'AND' and 'OR' rules. The expressions are experimentally evaluated by considering the proposed architecture for text-dependent speaker verification using HMM based digit dependent speaker models. The improvement in fusion performance is found to be higher when digit combinations with favourable client and impostor decisions are used for speaker verification. The total error rate of 20% for fusion of independent decisions is reduced to 2.1% for fusion of decisions that are favourable for both client and impostors. The expressions developed here are also applicable to other biometric modalities, such as finger prints and handwriting samples, for reliable identity verification.

Improved Subject Identification in Surveillance Video using Super Resolution

The time consuming and labour intensive task of identifying individuals in surveillance video is often challenged by poor resolution and the sheer volume of stored video. Faces or identifying marks such as tattoos are often too coarse for direct matching by machine or human vision. Object tracking and super-resolution can then be combined to facilitate the automated detection and enhancement of areas of interest. The object tracking process enables the automatic detection of people of interest, greatly reducing the amount of data for super-resolution. Smaller regions such as faces can also be tracked. A number of instances of such regions can then be utilized to obtain a super-resolved version for matching. Performance improvement from super-resolution is demonstrated using a face verification task. It is shown that there is a consistent improvement of approximately 7% in verification accuracy, using both Eigenface and Elastic Bunch Graph Matching approaches for automatic face verification, starting from faces with an eye to eye distance of 14 pixels. Visual improvement in image fidelity from super-resolved images over low-resolution and interpolated images is demonstrated on a small database. Current research and future directions in this area are also summarized.

Field-of-view, detection range, and false alarm trade-offs in vision-based aircraft detection

This paper presents a survey of previously presented vision based aircraft detection flight test, and then presents new flight test results examining the impact of camera field-of view choice on the detection range and false alarm rate characteristics of a vision-based aircraft detection technique. Using data collected from approaching aircraft, we examine the impact of camera fieldof-view choice and confirm that, when aiming for similar levels of detection confidence, an improvement in detection range can be obtained by choosing a smaller effective field-of-view (in terms of degrees per pixel).

Efficient safety message dissemination for cooperative collision warning via context modelling

A Cooperative Collision Warning System (CCWS) is an active safety techno- logy for road vehicles that can potentially reduce traffic accidents. It provides a driver with situational awareness and early warnings of any possible colli- sions through an on-board unit. CCWS is still under active research, and one of the important technical problems is safety message dissemination. Safety messages are disseminated in a high-speed mobile environment using wireless communication technology such as Dedicated Short Range Communication (DSRC). The wireless communication in CCWS has a limited bandwidth and can become unreliable when used inefficiently, particularly given the dynamic nature of road traffic conditions. Unreliable communication may significantly reduce the performance of CCWS in preventing collisions. There are two types of safety messages: Routine Safety Messages (RSMs) and Event Safety Messages (ESMs). An RSM contains the up-to-date state of a vehicle, and it must be disseminated repeatedly to its neighbouring vehicles. An ESM is a warning message that must be sent to all the endangered vehi- cles. Existing RSM and ESM dissemination schemes are inefficient, unscalable, and unable to give priority to vehicles in the most danger. Thus, this study investigates more efficient and scalable RSM and ESM dissemination schemes that can make use of the context information generated from a particular traffic scenario. Therefore, this study tackles three technical research prob- lems, vehicular traffic scenario modelling and context information generation, context-aware RSM dissemination, and context-aware ESM dissemination. The most relevant context information in CCWS is the information about possible collisions among vehicles given a current vehicular traffic situation. To generate the context information, this study investigates techniques to model interactions among multiple vehicles based on their up-to-date motion state obtained via RSM. To date, there is no existing model that can represent interactions among multiple vehicles in a speciffic region and at a particular time. The major outcome from the first problem is a new interaction graph model that can be used to easily identify the endangered vehicles and their danger severity. By identifying the endangered vehicles, RSM and ESM dis- semination can be optimised while improving safety at the same time. The new model enables the development of context-aware RSM and ESM dissemination schemes. To disseminate RSM efficiently, this study investigates a context-aware dis- semination scheme that can optimise the RSM dissemination rate to improve safety in various vehicle densities. The major outcome from the second problem is a context-aware RSM dissemination protocol. The context-aware protocol can adaptively adjust the dissemination rate based on an estimated channel load and danger severity of vehicle interactions given by the interaction graph model. Unlike existing RSM dissemination schemes, the proposed adaptive scheme can reduce channel congestion and improve safety by prioritising ve- hicles that are most likely to crash with other vehicles. The proposed RSM protocol has been implemented and evaluated by simulation. The simulation results have shown that the proposed RSM protocol outperforms existing pro- tocols in terms of efficiency, scalability and safety. To disseminate ESM efficiently, this study investigates a context-aware ESM dissemination scheme that can reduce unnecessary transmissions and deliver ESMs to endangered vehicles as fast as possible. The major outcome from the third problem is a context-aware ESM dissemination protocol that uses a multicast routing strategy. Existing ESM protocols use broadcast rout- ing, which is not efficient because ESMs may be sent to a large number of ve- hicles in the area. Using multicast routing improves efficiency because ESMs are sent only to the endangered vehicles. The endangered vehicles can be identified using the interaction graph model. The proposed ESM protocol has been implemented and evaluated by simulation. The simulation results have shown that the proposed ESM protocol can prevent potential accidents from occurring better than existing ESM protocols. The context model and the RSM and ESM dissemination protocols can be implemented in any CCWS development to improve the communication and safety performance of CCWS. In effect, the outcomes contribute to the realisation of CCWS that will ultimately improve road safety and save lives.

Direct evaluation of IEC 61850-9-2 process bus network performance

This letter presents a technique to assess the overall network performance of sampled value process buses based on IEC 61850-9-2 using measurements from a single location in the network. The method is based upon the use of Ethernet cards with externally synchronized time stamping, and characteristics of the process bus protocol. The application and utility of the method is demonstrated by measuring latency introduced by Ethernet switches. Network latency can be measured from a single set of captures, rather than comparing source and destination captures. Absolute latency measures will greatly assist the design testing, commissioning and maintenance of these critical data networks.