Three-dimensional mapping of real environments for cognitive robots navigation

Abstract The development of cognitive robots needs a strong “sensorial” support which should allow it to perceive the real world for interacting with it properly. Therefore the development of efficient visual-processing software to be equipped in effective artificial agents is a must. In this project we study and develop a visual-processing software that will work as the “eyes” of a cognitive robot. This software performs a three-dimensional mapping of the robot’s environment, providing it with the essential information required to make proper decisions during its navigation. Due to the complexity of this objective we have adopted the Scrum methodology in order to achieve an agile development process, which has allowed us to correct and improve in a fast way the successive versions of the product. The present project is structured in Sprints, which cover the different stages of the software development based on the requirements imposed by the robot and its real necessities. We have initially explored different commercial devices oriented to the acquisition of the required visual information, adopting the Kinect Sensor camera (Microsoft) as the most suitable option. Later on, we have studied the available software to manage the obtained visual information as well as its integration with the robot’s software, choosing the high-level platform Matlab as the common nexus to join the management of the camera, the management of the robot and the implementation of the behavioral algorithms. During the last stages the software has been developed to include the fundamental functionalities required to process the real environment, such as depth representation, segmentation, and clustering. Finally the software has been optimized to exhibit real-time processing and a suitable performance to fulfill the robot’s requirements during its operation in real situations.

A General Purpose Configurable Controller for Indoors and Outdoors GPS-Denied Navigation for Multirotor Unmanned Aerial Vehicles

This research on odometry based GPS-denied navigation on multirotor Unmanned Aerial Vehicles is focused among the interactions between the odometry sensors and the navigation controller. More precisely, we present a controller architecture that allows to specify a speed specified flight envelope where the quality of the odometry measurements is guaranteed. The controller utilizes a simple point mass kinematic model, described by a set of configurable parameters, to generate a complying speed plan. For experimental testing, we have used down-facing camera optical-flow as odometry measurement. This work is a continuation of prior research to outdoors environments using an AR Drone 2.0 vehicle, as it provides reliable optical flow on a wide range of flying conditions and floor textures. Our experiments show that the architecture is realiable for outdoors flight on altitudes lower than 9 m. A prior version of our code was utilized to compete in the International Micro Air Vehicle Conference and Flight Competition IMAV 2012. The code will be released as an open-source ROS stack hosted on GitHub.

A General Purpose Configurable Navigation Controller for Micro Aerial Multirotor Vehicles

In this paper, we consider the problem of autonomous navigation of multirotor platforms in GPS-denied environments. The focus of this work is on safe navigation based on unperfect odometry measurements, such as on-board optical flow measurements. The multirotor platform is modeled as a flying object with specific kinematic constraints that must be taken into account in order to obtain successful results. A navigation controller is proposed featuring a set of configurable parameters that allow, for instance, to have a configuration setup for fast trajectory following, and another to soften the control laws and make the vehicle navigation more precise and slow whenever necessary. The proposed controller has been successfully implemented in two different multirotor platforms with similar sensoring capabilities showing the openness and tolerance of the approach. This research is focused around the Computer Vision Group's objective of applying multirotor vehicles to civilian service applications. The presented work was implemented to compete in the International Micro Air Vehicle Conference and Flight Competition IMAV 2012, gaining two awards: the Special Award on "Best Automatic Performance - IMAV 2012" and the second overall prize in the participating category "Indoor Flight Dynamics - Rotary Wing MAV". Most of the code related to the present work is available as two open-source projects hosted in GitHub.

Monarch butterflies (Danaus plexippus L.) use a magnetic compass for navigation

Fall migratory monarch butterflies, tested for their directional responses to magnetic cues under three conditions, amagnetic, normal, and reversed magnetic fields, showed three distinct patterns. In the absence of a magnetic field, monarchs lacked directionality as a group. In the normal magnetic field, monarchs oriented to the southwest with a group pattern typical for migrants. When the horizontal component of the magnetic field was reversed, the butterflies oriented to the northeast. In contrast, nonmigratory monarchs lacked directionality in the normal magnetic field. The results are a direct demonstration of magnetic compass orientation in migratory insects.

Comparison of potency of inhaled beclomethasone and budesonide in New Zealand: retrospective study of computerised general practice records

Objective To determine whether inhaled budesonide and beclomethasone are equipotent in the treatment of asthma in primary care.

Substratal idiothetic navigation of rats is impaired by removal or devaluation of extramaze and intramaze cues

The spatial orientation of vertebrates is implemented by two complementary mechanisms: allothesis, processing the information about spatial relationships between the animal and perceptible landmarks, and idiothesis, processing the substratal and inertial information produced by the animal's active or passive movement through the environment. Both systems allow the animal to compute its position with respect to perceptible landmarks and to the already traversed portion of the path. In the present study, we examined the properties of substratal idiothesis deprived of relevant exteroceptive information. Rats searching for food pellets in an arena formed by a movable inner disk and a peripheral immobile belt were trained in darkness to avoid a 60° sector; rats that entered this sector received a mild foot shock. The punished sector was defined in the substratal idiothetic frame, and the rats had to determine the location of the shock sector with the use of substratal idiothesis only, because all putative intramaze cues were made irrelevant by angular displacements of the disk relative to the belt. Striking impairment of place avoidance by this “shuffling procedure” indicates that effective substratal idiothesis must be updated by exteroceptive intramaze cues.

Vestibular navigation directed by the slope of terrain.

Slope of terrain is an important orienting gradient affecting the goal-directed locomotion of animals. Its significance was assessed in experiment 1 by training rats to find in darkness a feeder on the top of a low cone (80-cm base, 0- to 4-cm high). A computerized infrared tracking system monitoring the rat's position in darkness showed that the path length on the cone surface was inversely proportional to cone height. A device allowing continuous generation of slope-guided locomotion was used in experiment 2. This device consists of a 1-m arena, the floor of which can be supported at a point corresponding to the position of one of three equidistant feeders located 17 cm from its center. The arena is inclined by the locomotion of the rat to a plane passing through the elevated (2- or 4-cm) feeder, the rat's center of gravity, and a point at the edge of the arena resting on the floor. The multitude of such planes generated by the rat's locomotion forms the surface of a virtual cone, the top of which is formed by the feeder. Additional path (difference between distance traveled and shortest distance of the animal from the goal at the onset of inclination) is inversely related to the incline of the arena and is a sensitive measure of performance in this type of vestibular navigation.

Successful Navigation of the Conflict between Doctoral Education and Cultural Expectations of Child Rearing in Hispanic Culture

While the numbers are slowly rising, Hispanic students continue to be disproportionately underrepresented in all levels of higher education, including doctoral education. There are many factors that may contribute to the low numbers of Hispanic doctoral students; for Hispanic women, one of these factors may be the perceived conflict between cultural expectations of childrearing and doctoral education. For Hispanic students who hold strong cultural values, this conflict may prevent enrollment in, or result in attrition from, doctoral education. As the number of Hispanic college enrollment increases, we will see more students trying to navigate between the collectivistic value of childrearing and the individualistic value of pursuing higher education. Thus, it is important to understand the needs of these students to aid in recruitment and retention of student-parents in all levels of higher education. This paper explores the barriers and supportive factors for current Hispanic doctoral student-parents. Suggestions are made to increase support which will allow these individuals to successfully complete a doctoral education, while attending to the responsibilities of parenting.

Learning Probabilistic Features for Robotic Navigation Using Laser Sensors

SLAM is a popular task used by robots and autonomous vehicles to build a map of an unknown environment and, at the same time, to determine their location within the map. This paper describes a SLAM-based, probabilistic robotic system able to learn the essential features of different parts of its environment. Some previous SLAM implementations had computational complexities ranging from O(Nlog(N)) to O(N2), where N is the number of map features. Unlike these methods, our approach reduces the computational complexity to O(N) by using a model to fuse the information from the sensors after applying the Bayesian paradigm. Once the training process is completed, the robot identifies and locates those areas that potentially match the sections that have been previously learned. After the training, the robot navigates and extracts a three-dimensional map of the environment using a single laser sensor. Thus, it perceives different sections of its world. In addition, in order to make our system able to be used in a low-cost robot, low-complexity algorithms that can be easily implemented on embedded processors or microcontrollers are used.

Notebook on geometry, geography, astronomy, and navigation, ca. 1714-1718

This heavily illustrated notebook contains entries on the following topics: geometrical definitions and axioms, geographical and astronomical definitions, compasses, plain sailing, parallel sailing, and Mercator's sailing. It also contains pages designated for notes on "Currents, Lee Way, & Variation," but these pages have been left blank. The back cover contains calculations which appear to relate to charting a course from Jamaica to "Lizzard."

Notebook on geography, navigation, mensuration, and other subjects, ca. 1723-1743

This heavily illustrated notebook contains entries on the following topics, among others: geography; mensuration; navigation and the history of navigation; "the use of Gunter's Scale in plain sailing;" compasses; quadrants and their use; "the refraction of the stars observed by the famous Tycho Brahe;" the latitude and longitude of coasts in America, Europe, and Africa; oceans and islands; mountains and "burning mountains" (volcanoes); rivers and lakes; forests and deserts; maps and sea charts; and the uses of geometry and other measurements by carpenters, joiners, painters, glaziers, masons, and bricklayers. Many pages contain navigational problems and their detailed solutions, as well as chronologies of global exploration and lists of all known rivers, mountains, and other geographic features across the world, many with vivid descriptions. The last pages of the notebook contain entries made in December of 1743 regarding celestial measurements Prince took in Stratford, Connecticut, where he was staying with his brother.

Opinions filed by the commissioners acting under the VII. article of the Treaty of Amity Commerce and Navigation between Great Britain and the United States of America : manuscript, 1797-1799

Opinions concerning the 7th article of the treaty.

Manual of navigation : manuscript, [1697?]

Consists of lessons on various computations (ff. 1-4), geometry (5-10), and navigation (11-74), mostly in the form of problems and solutions.