Online learning of autonomous helicopter control

This paper details the development of an online adaptive control system, designed to learn from the actions of an instructing pilot. Three learning architectures, single layer neural networks (SLNN), multi-layer neural networks (MLNN), and fuzzy associative memories (FAM) are considerd. Each method has been tested in simulation. While the SLNN and MLNN provided adequate control under some simulation conditions, the addition of pilot noise and pilot variation during simulation training caused these methods to fail.

Obstacle detection for a mining vehicle using a 2D laser

This paper discusses a number of key issues for the development of robust obstacle detection systems for autonomous mining vehicles. Strategies for obstacle detection are described and an overview of the state-of-the-art in obstacle detection for outdoor autonomous vehicles using lasers is presented, with their applicability to the mining environment noted. The development of an obstacle detection system for a mining vehicle is then detailed. This system uses a 2D laser scanner as the prime sensor and combines dead-reckoning data with laser data to create local terrain maps. The slope of the terrain maps is then used to detect potential obstacles.

System design for a small autonomous helicopter

The detailed system design of a small experimental autonomous helicopter is described. The system requires no ground-to-helicopter communications and hence all automation hardware is on-board the helicopter. All elements of the system are described including the control computer, the flight computer (the helicopter-to-control-computer interface), the sensors and the software. A number of critical implementation issues are also discussed.

Height estimation for an autonomous helicopter

Height is a critical variable for helicopter hover control. In this paper we discuss, and present experimental results for, two different height sensing techniques: ultrasonic and stereo imaging, which have complementary characteristics. Feature-based stereo is used which provides a basis for visual odometry and attitude estimation in the future.

Field and Service Robotics: Results of the 9th International Conference

The Field and Service Robotics (FSR) conference is a single track conference with a specific focus on field and service applications of robotics technology. The goal of FSR is to report and encourage the development of field and service robotics. These are non-factory robots, typically mobile, that must operate in complex and dynamic environments. Typical field robotics applications include mining, agriculture, building and construction, forestry, cargo handling and so on. Field robots may operate on the ground (of Earth or planets), under the ground, underwater, in the air or in space. Service robots are those that work closely with humans, importantly the elderly and sick, to help them with their lives. The first FSR conference was held in Canberra, Australia, in 1997. Since then the meeting has been held every 2 years in Asia, America, Europe and Australia. It has been held in Canberra, Australia (1997), Pittsburgh, USA (1999), Helsinki, Finland (2001), Mount Fuji, Japan (2003), Port Douglas, Australia (2005), Chamonix, France (2007), Cambridge, USA (2009), Sendai, Japan (2012) and most recently in Brisbane, Australia (2013). This year we had 54 submissions of which 36 were selected for oral presentation. The organisers would like to thank the international committee for their invaluable contribution in the review process ensuring the overall quality of contributions. The organising committee would also like to thank Ben Upcroft, Felipe Gonzalez and Aaron McFadyen for helping with the organisation and proceedings. and proceedings. The conference was sponsored by the Australian Robotics and Automation Association (ARAA), CSIRO, Queensland University of Technology (QUT), Defence Science and Technology Organisation Australia (DSTO) and the Rio Tinto Centre for Mine Automation, University of Sydney.

Repeatable Condition-Invariant Visual Odometry for Sequence-Based Place Recognition

This paper describes a vision-only system for place recognition in environments that are tra- versed at different times of day, when chang- ing conditions drastically affect visual appear- ance, and at different speeds, where places aren’t visited at a consistent linear rate. The ma- jor contribution is the removal of wheel-based odometry from the previously presented algo- rithm (SMART), allowing the technique to op- erate on any camera-based device; in our case a mobile phone. While we show that the di- rect application of visual odometry to our night- time datasets does not achieve a level of perfor- mance typically needed, the VO requirements of SMART are orthogonal to typical usage: firstly only the magnitude of the velocity is required, and secondly the calculated velocity signal only needs to be repeatable in any one part of the environment over day and night cycles, but not necessarily globally consistent. Our results show that the smoothing effect of motion constraints is highly beneficial for achieving a locally consis- tent, lighting-independent velocity estimate. We also show that the advantage of our patch-based technique used previously for frame recogni- tion, surprisingly, does not transfer to VO, where SIFT demonstrates equally good performance. Nevertheless, we present the SMART system us- ing only vision, which performs sequence-base place recognition in extreme low-light condi- tions where standard 6-DOF VO fails and that improves place recognition performance over odometry-less benchmarks, approaching that of wheel odometry.

Reasoning about natural language phrases for semantic goal driven exploration

This paper presents a symbolic navigation system that uses spatial language descriptions to inform goal-directed exploration in unfamiliar office environments. An abstract map is created from a collection of natural language phrases describing the spatial layout of the environment. The spatial representation in the abstract map is controlled by a constraint based interpretation of each natural language phrase. In goal-directed exploration of an unseen office environment, the robot links the information in the abstract map to observed symbolic information and its grounded world representation. This paper demonstrates the ability of the system, in both simulated and real-world trials, to efficiently find target rooms in environments that it has never been to previously. In three unexplored environments, it is shown that on average the system travels only 8.42% further than the optimal path when using only natural language phrases to complete navigation tasks.

Distributed Robotic Vision as a service

The vision sense of standalone robots is limited by line of sight and onboard camera capabilities, but processing video from remote cameras puts a high computational burden on robots. This paper describes the Distributed Robotic Vision Service, DRVS, which implements an on-demand distributed visual object detection service. Robots specify visual information requirements in terms of regions of interest and object detection algorithms. DRVS dynamically distributes the object detection computation to remote vision systems with processing capabilities, and the robots receive high-level object detection information. DRVS relieves robots of managing sensor discovery and reduces data transmission compared to image sharing models of distributed vision. Navigating a sensorless robot from remote vision systems is demonstrated in simulation as a proof of concept.

Enhancing human action recognition with region proposals

Deep convolutional network models have dominated recent work in human action recognition as well as image classification. However, these methods are often unduly influenced by the image background, learning and exploiting the presence of cues in typical computer vision datasets. For unbiased robotics applications, the degree of variation and novelty in action backgrounds is far greater than in computer vision datasets. To address this challenge, we propose an “action region proposal” method that, informed by optical flow, extracts image regions likely to contain actions for input into the network both during training and testing. In a range of experiments, we demonstrate that manually segmenting the background is not enough; but through active action region proposals during training and testing, state-of-the-art or better performance can be achieved on individual spatial and temporal video components. Finally, we show by focusing attention through action region proposals, we can further improve upon the existing state-of-the-art in spatio-temporally fused action recognition performance.

Towards vision-based deep reinforcement learning for robotic motion control

This paper introduces a machine learning based system for controlling a robotic manipulator with visual perception only. The capability to autonomously learn robot controllers solely from raw-pixel images and without any prior knowledge of configuration is shown for the first time. We build upon the success of recent deep reinforcement learning and develop a system for learning target reaching with a three-joint robot manipulator using external visual observation. A Deep Q Network (DQN) was demonstrated to perform target reaching after training in simulation. Transferring the network to real hardware and real observation in a naive approach failed, but experiments show that the network works when replacing camera images with synthetic images.

Characterisation of the Delphi Electronically Scanning Radar for robotics applications

Mm-wave radars have an important role to play in field robotics for applications that require reliable perception in challenging environmental conditions. This paper presents an experimental characterisation of the Delphi Electronically Scanning Radar (ESR) for mobile robotics applications. The performance of the sensor is evaluated in terms of detection ability and accuracy, for varying factors including: sensor temperature, time, target’s position, speed, shape and material. We also evaluate the sensor’s target separability performance.

Analysing the Impact of Learning Inputs - Application to Terrain Traversability Estimation

Data-driven approaches such as Gaussian Process (GP) regression have been used extensively in recent robotics literature to achieve estimation by learning from experience. To ensure satisfactory performance, in most cases, multiple learning inputs are required. Intuitively, adding new inputs can often contribute to better estimation accuracy, however, it may come at the cost of a new sensor, larger training dataset and/or more complex learning, some- times for limited benefits. Therefore, it is crucial to have a systematic procedure to determine the actual impact each input has on the estimation performance. To address this issue, in this paper we propose to analyse the impact of each input on the estimate using a variance-based sensitivity analysis method. We propose an approach built on Analysis of Variance (ANOVA) decomposition, which can characterise how the prediction changes as one or more of the input changes, and also quantify the prediction uncertainty as attributed from each of the inputs in the framework of dependent inputs. We apply the proposed approach to a terrain-traversability estimation method we proposed in prior work, which is based on multi-task GP regression, and we validate this implementation experimentally using a rover on a Mars-analogue terrain.

Evaluación de productos botánicos y biológicos para el control de Plutella xylostella en el cultivo del repollo (Brassica oleraceae L.) hibrido Izalco en época de apante

Con el fin de encontrar el mejor producto para el control de Plutella xylostella en el cultivo del repollo, se llevó a cabo un ensayo a nivel de campo en época seca (Die 91-Mar 92) en el valle de Sébaco-Matagalpa donde se evaluaron los tratamientos Bacillus thuringiensis nacional, Dipel comercial, Javelin, Nim, Mamey y Júpiter, con un criterio de aplicación de 0.5 larvas por plantas. Las poblaciones de Plutella xylostella fueron relativamente bajas en la etapa de crecimiento vegetativo disminuyendo en las últimas dos etapas formación y llenado de cabeza. Durante las tres fases del cultivo las poblaciones de Plutella xylostella fueron menores en los tratamientos Javelin Mamey y Júpiter. Los insecticidas Dipel. Javelin y Mamey fueron diferentes estadísticamente del testigo (sin aplicación), según el análisis económico los primeros dos insecticidas son rentables económicamente sucediendo lo contrario con el insecticida Mamey por lo tanto su uso no es recomendado para el manejo de la plaga. El insecticida Júpiter puede ser utilizado contra la plaga ya que muestra una tasa de retorno marginal superior a la tasa comparativa. La presencia de enemigos naturales (Araña, Polybia sppy el parasitoide Diadegma insularis) fue notoria en el cultivo, cabe señalar su importancia ya que intervienen en el equilibrio del ecosistema dentro del cultivo (plaga-repollo). Estos predadores no se vieron afectados por las aplicaciones de los insecticidas botánicos y biológicos evaluados en el cultivo. El uso de estos productos parecen ser una alternativa de manejo de las plagas del cultivo a largo plazo ya que el establecimiento de la fauna benéfica en el sistema y el no uso de productos sintéticos evitan los problemas de resistencia en las plagas y la contaminación ambiental.

Toxicología veterinaria

La presente recopilación bibliográfica especializada en Toxicología Veterinaria, es un esfuerzo académico que refleja los logros en esta área de la ciencia por diversos investigadores, el cual va encaminado a fortalecer los conocimientos de los estudiantes de Medicina Veterinaria y como fuente de consulta para profesionales de las ciencias veterinarias. El clínico es quien debe enfrentarse a diario con pacientes potencialmente envenenados, y decidir si el diagnóstico de “envenenamiento” es verdadero y, si es así, cual de entre los miles de sustancias químicas o naturales (plantas tóxicas y animales de ponzoña) existentes puede ser la responsable del caso que lo ocupa. Con este documento no se pretende sustituir las diversas publicaciones existentes sobre este tema, pero que sirva de un medio de orientación en el campo de la toxicología veterinaria, ya que resalta los problemas toxicológicos que se presentan comúnmente en la producción de alimentos de naturaleza animal y en mantenimiento de animales de compañía. Se incluye información básica sobre dosisrespuesta y tipos de comprobaciones toxicológicas a que se someten los nuevos compuestos para determinar su seguridad y toxicidad, de forma que el estudiante tenga una idea del tipo de información disponible y de cómo se obtiene. Al organizar este documento se puso énfasis en las intoxicaciones por especie que se observan comúnmente en la práctica diaria. Se espera que el estudiante, veterinario toxicólogo se beneficien al disponer de una información adecuada y útil para tratar las intoxicaciones clínicas y de campo que se observan diariamente. La toxicología, es la ciencia que estudia los venenos o agentes tóxicos, incluyendo sus propiedades químicas, identificación, efectos biológicos y los posibles tratamientos de los efectos que producen. El toxicólogo veterinario requiere de entrenamiento especializado, así como de experiencia en el manejo de varias sustancias venenosas sintéticas o naturales (producida por plantas o animales). Debe además diferenciar las enfermedades infecciosas de las condiciones metabólicas causadas por venenos, también debe conocer la gran variedad de productos químicos agrícolas, aditivos de alimentos, contaminantes ambientales, radiaciones diversas, gases venenosos y venenos de origen vegetal y animal que puedan afectar la salud de los animales. La farmacología y la toxicología comparten muchos intereses, incluyendo mecanismo de absorción y eliminación, mecanismo de acción, principios de tratamiento y relaciones dosis–respuesta. Algunos medicamentos pueden actuar como venenos en ciertas condiciones, por lo tanto el farmacólogo como el toxicólogo comparten un interés por las reacciones adversas de los fármacos. La toxicología se divide en dos aspectos: La toxicología general. La toxicología específica.

Evaluación de tres insecticidas botánicos y dos químico contra el complejo mosca blanca (Bemisia tabací, Genn)- Geminivirus en el cultivo de tomate (Lycopersicum esculentum, Mili) en Camoapa, Boaco

El presente trabajo se realizó entre el periodo comprendido de Abril a Julio del 2010, en la comunidad de Mombachito, municipio Camoapa, departamento de Boaco. El objetivo fue evaluar cinco alternativas de manejos contra el complejo Bemisia tabaci- Geminivirus, en el cultivo de tomate. El híbrido utilizado fue Shanty, estableciendo el semillero bajo condiciones de micro-invernadero, para evaluar las alternativas de manejo se utilizo un diseño de bloque completo al azar (BCA), arreglando los siguientes tratamientos: actara 25 WG ITbiametoxam); engeo 24,7 SC (Thiarnetoxam + Lambda-Cihalotrina); macerado de hojas de madero negro ( Gliricidia sepium ); aceite vegetal + jabón liquido, macerados de ajo (A/luim sativum)+ chile (Capsicum sp)+ jabón y un testigo (sin aplicación). En las variables evaluadas (promedio de mosca blanca, incidencia de virus, severidad de virus, otros insectos, rendimiento y análisis económico). Se registraron los siguientes resultados: promedio de mosca blanca/plantas más bajos actara (1.20 ± 0.12; Pr S 0.0001), aceite vegetal (1.57 ± 0.16) y madero negro (1.66 ± 0.18). Los menores porcentajes de incidencia y severidad de virus fue el actara. En el tratamiento de madero negro se registraron los promedios más alto de araña, después del tratamiento testigo. Los rendimientos promedios registrado por tratamientos más altos fue en engeo y madero negro, el tratamiento que mostró la tasa de retorno marginal más alta fue engeo con 638%.