The range camera in Microsoft's Kinect, intended for the Xbox 360 gaming console, offers a powerful alternative to the many standard sensors used in robotics for gathering spatial information about a robot’s surroundings. The recently-released Kinect is the first commercially available product to provide depth data of its resolution and accuracy with a price tag within reach of many robotics projects. The work described in this paper explores the feasibility of using this sensor by developing a robot that relies solely on the Kinect for sensory data. This robot successfully performs standard navigational procedures, demonstrating the possibility of integrating spatial information from the Kinect into a real-time robotics application. This paper documents the techniques used to integrate the Kinect into the system, highlighting the key benefits and limitations of the sensor. / text

The use of potential field based navigation schemes in robotics has been limited by inherent local minima issues. Local minima traps, small passages, unstable motion, and targets positioned near objects all pose major concerns when using potential fields for local vehicle control. This work proposes a new algorithm, "Re-Active Vector Equilibrium" (RAVE) that mitigates many of these issues. The vehicle representation model is expanded to use multiple points subject to potential calculation and the addition of two forces, a velocity dependent "risk force" (F_rsk) and a velocity and direction dependent "tangential force" (F_tan). The vehicle representation model is also expanded from a single reactive point to a series of points that define the vehicle body, providing better and simpler vehicle control. This has the effect of simplifying the required calculations at the cost of increasing the calculation count. The risk force, F_rsk, allows for dynamic adaptation to the immediate environment by acting in opposition to the net obstacle force, and is inversely proportional to the vehicle speed. The tangential force, F_tan, encourages better wall-following behaviour and provides a biasing mechanism to resolve obstacle aligned with target local minima issues.

<div>We describe a new task called The Amazing Race: Robot Edition. In this task, the robot is placed in a real, unknown environment, without a map, and asked to find a designated location. It will need to explore its surroundings, find and approach people, engage them in a dialogue to obtain directions to the goal, and follow those directions to the hallway with the goal. We describe and implement a variety of robotic behaviors that performs each of these functions. We test these in the real world in test environments that were distinct from the training environments where we developed our methods and trained our models. Additionally, these test environments were completely unmodified and reflect the state of the real world.</div><div>First, we describe how our robotic system solves this problem where the environment is constrained to a single floor or a single building. We demonstrate that we are able to find a goal location in never-before-seen environments. Next, we describe a machine-learned approach to the dialogue and components of our system to make it more robust to the diversity and noisiness of navigational instructions someone may provide.</div>

No description available.

There are two commonly accepted paradigms for organizing intelligence in robotic vehicles, namely reactive and deliberative. A third, a hybrid paradigm called integrated planning and execution, is considered a combination of the original two. Although these paradigms are well known to researchers, there are few published examples directly comparing their application and performance on similar vehicles operating in identical environments. Virginia Tech's participation with two nearly identical vehicles in the DARPA Grand Challenge afforded a practical opportunity for such a case study. Both base vehicles were developed by modifying Club Car Pioneer XRT 1500 on-demand four wheel drive base platforms. Cliff was designed to use the reactive paradigm, while Rocky was designed to use the deliberative paradigm. Both vehicles were initially outfitted with sensor suites and computational capabilities commensurate with the paradigm being employed. The author of this thesis coordinated the activities of the two teams of undergraduate and graduate students who implemented the respective designs and software. Both vehicles proved capable of off-road navigation, including road following and obstacle avoidance in complex desert terrain. In the end, however, the reactive paradigm proved to be smoother and more reliable than the deliberative paradigm under the conditions of our testing. While both vehicles were extensively tested and compared using the competing paradigms, the team modified Rocky to use the more effective reactive paradigm for the Grand Challenge events. The deliberative case shows much promise for complex navigation, but added unnecessary complexity to desert road navigation. This case study, while necessarily limited in scope, may help to shed additional light on the tradeoffs and performance of competing approaches to machine intelligence. / Master of Science

An issue of concern for maritime safety when operating a small to medium-sized sailboat is that the presence of hazards in the navigational route in the form of floating logs can lead to a severe collision if undetected. As a precautionary measure to prevent such a collision with a log, a 2D vision-based detection system is proposed. We take a combined approach involving predictive mapping by linear regression and saliency detection. This approach is found to overcome specific issues related to the illumination changes and unstructured environment in the dataset. The proposed method has been evaluated using precision and recall measures. This proof of concept demonstrates the potential of the method for deployment on a real-time onboard detection system. The algorithm is robust and of reasonable computational complexity. / Graduate

FundaÃÃo Cearense de Apoio ao Desenvolvimento Cientifico e TecnolÃgico / Sistemas de navegaÃÃo autÃnomos devem ser capazes de definir uma seqÃÃncia de aÃÃes a serem tomadas por robÃs mÃveis, dotados de um conjunto limitado de sensores, quando expostos a um ambiente externo suposto desconhecido e tendo que atender simultaneamente a um elenco de objetivos previamente especificados. O interesse cientÃfico no estudo de sistemas de navegaÃÃo em ambientes desconhecidos e sujeitos ao atendimento de mÃltiplos objetivos à motivado basicamente pelo seu evidente potencial em aplicaÃÃes industriais e pelo fato de demandarem a implementaÃÃo de estratÃgias de soluÃÃes complexas. Este trabalho apresenta a modelagem de um sistema de navegaÃÃo para robÃs moveis por meio de Redes de Petri Coloridas. O modelo apresentado consegue simular vÃrias situaÃÃes, tais como a representaÃÃo do mundo em volta do robÃ, interaÃÃo com o ambiente, planejamento de trajetÃria, localizaÃÃo do robà e anÃlise das baterias, bem como servir de base para implementaÃÃo em um robà mÃvel real e otimizaÃÃo do sistema. / Systems of autonomous navigation must be able to define a sequence of actions to be taken bymobile robots endowed with a set of limited sensors, while exposed to an unknown environment and having to serve simultaneously a set of objectives previously specified. The scientific interest in the study of systems of navigation in unknown environment which are subject of serving to several objectives is motivated basically by its evident potential in industrial applications and by the fact of demanding the implementation of complex solutions strategies. This research presents the modeling of a navigation system for mobile robots through coloured Petri nets. The model presented here can simulate several situations, such as: the representation of the world around the robot, interaction with the environment, trajectory planning, robot location, battery analysis, as well as how to serve as a basis for implementation in a real mobile robot and optimization of the system.

Mobile robotics research is currently interested on exporting autonomous navigation results achieved in indoor environments, to more challenging environments, such as, for instance, urban pedestrian areas. Developing mobile robots with autonomous navigation capabilities in such urban environments supposes a basic requirement for a upperlevel service set that could be provided to an users community. However, exporting indoor techniques to outdoor urban pedestrian scenarios is not evident due to the larger size of the environment, the dynamism of the scene due to pedestrians and other moving obstacles, the sunlight conditions, and the high presence of three dimensional elements such as ramps, steps, curbs or holes. Moreover, GPS-based mobile robot localization has demonstrated insufficient performance for robust long-term navigation in urban environments. One of the key modules within autonomous navigation is localization. If localization supposes an a priori map, even if it is not a complete model of the environment, localization is called map-based. This assumption is realistic since current trends of city councils are on building precise maps of their cities, specially of the most interesting places such as city downtowns. Having robots localized within a map allows for a high-level planning and monitoring, so that robots can achieve goal points expressed on the map, by following in a deliberative way a previously planned route. This thesis deals with the mobile robot map-based localization issue in urban pedestrian areas. The thesis approach uses the particle filter algorithm, a well-known and widely used probabilistic and recursive method for data fusion and state estimation. The main contributions of the thesis are divided on four aspects: (1) long-term experiments of mobile robot 2D and 3D position tracking in real urban pedestrian scenarios within a full autonomous navigation framework, (2) developing a fast and accurate technique to compute on-line range observation models in 3D environments, a basic step required by the real-time performance of the developed particle filter, (3) formulation of a particle filter that integrates asynchronous data streams and (4) a theoretical proposal to solve the global localization problem in an active and cooperative way, defining cooperation as either information sharing among the robots or planning joint actions to solve a common goal. / Actualment, la recerca en robòtica mòbil té un interés creixent en exportar els resultats de navegació autònoma aconseguits en entorns interiors cap a d'altres tipus d'entorns més exigents, com, per exemple, les àrees urbanes peatonals. Desenvolupar capacitats de navegació autònoma en aquests entorns urbans és un requisit bàsic per poder proporcionar un conjunt de serveis de més alt nivell a una comunitat d'usuaris. Malgrat tot, exportar les tècniques d'interiors cap a entorns exteriors peatonals no és evident, a causa de la major dimensió de l'entorn, del dinamisme de l'escena provocada pels peatons i per altres obstacles en moviment, de la resposta de certs sensors a la il.luminació natural, i de la constant presència d'elements tridimensionals tals com rampes, escales, voreres o forats. D'altra banda, la localització de robots mòbils basada en GPS ha demostrat uns resultats insuficients de cara a una navegació robusta i de llarga durada en entorns urbans. Una de les peces clau en la navegació autònoma és la localització. En el cas que la localització consideri un mapa conegut a priori, encara que no sigui un model complet de l'entorn, parlem d'una localització basada en un mapa. Aquesta assumpció és realista ja que la tendència actual de les administracions locals és de construir mapes precisos de les ciutats, especialment dels llocs d'interés tals com les zones més cèntriques. El fet de tenir els robots localitzats en un mapa permet una planificació i una monitorització d'alt nivell, i així els robots poden arribar a destinacions indicades sobre el mapa, tot seguint de forma deliberativa una ruta prèviament planificada. Aquesta tesi tracta el tema de la localització de robots mòbils, basada en un mapa i per entorns urbans peatonals. La proposta de la tesi utilitza el filtre de partícules, un mètode probabilístic i recursiu, ben conegut i àmpliament utilitzat per la fusió de dades i l'estimació d'estats. Les principals contribucions de la tesi queden dividides en quatre aspectes: (1) experimentació de llarga durada del seguiment de la posició, tant en 2D com en 3D, d'un robot mòbil en entorns urbans reals, en el context de la navegació autònoma, (2) desenvolupament d'una tècnica ràpida i precisa per calcular en temps d'execució els models d'observació de distàncies en entorns 3D, un requisit bàsic pel rendiment del filtre de partícules a temps real, (3) formulació d'un filtre de partícules que integra conjunts de dades asíncrones i (4) proposta teòrica per solucionar la localització global d'una manera activa i cooperativa, entenent la cooperació com el fet de compartir informació, o bé com el de planificar accions conjuntes per solucionar un objectiu comú.

As the number of spacecraft in simultaneous operation continues to grow, there is an increased dependency on ground-based navigation support. The current baseline system for deep space navigation utilizes Earth-based radiometric tracking, which requires long duration, often global, observations to perform orbit determination and generate a state update. The age, complexity, and high utilization of the assets that make up the Deep Space Network (DSN) pose a risk to spacecraft navigation performance. With increasingly complex mission operations, such as automated asteroid rendezvous or pinpoint planetary landing, the need for high accuracy and autonomous navigation capability is further reinforced. The Network-Based Navigation (NNAV) method developed in this research takes advantage of the growing inter-spacecraft communication network infrastructure to allow for autonomous state measurement. By embedding navigation headers into the data packets transmitted between nodes in the communication network, it is possible to provide an additional source of navigation capability. Simulation results indicate that as NNAV is implemented across the deep space network, the state estimation capability continues to improve, providing an embedded navigation network. To analyze the capabilities of NNAV, an analysis and simulation framework is designed that integrates navigation and communication analysis. Model-Based Systems Engineering (MBSE) and Agent-Based Modeling (ABM) techniques are utilized to foster a modular, expandable, and robust framework. This research has developed the Space Navigation Analysis and Performance Evaluation (SNAPE) framework. This framework allows for design, analysis, and optimization of deep space navigation and communication architectures. SNAPE captures high-level performance requirements and bridges them to specific functional requirements of the analytical implementation. The SNAPE framework is implemented in a representative prototype environment using the Python language and verified using industry standard packages. The capability of SNAPE is validated through a series of example test cases. These analyses focus on the performance of specific state measurements to state estimation performance, and demonstrate the core analytic functionality of the framework. Specific cases analyze the effects of initial error and measurement uncertainty on state estimation performance. The timing and frequency of state measurements are also investigated to show the need for frequent state measurements to minimize navigation errors. The dependence of navigation accuracy on timing stability and accuracy is also demonstrated. These test cases capture the functionality of the tool as well as validate its performance. The SNAPE framework is utilized to capture and analyze NNAV, both conceptually and analytically. Multiple evaluation cases are presented that focus on the Mars Science Laboratory's (MSL) Martian transfer mission phase. These evaluation cases validate NNAV and provide concrete evidence of its operational capability for this particular application. Improvement to onboard state estimation performance and reduced reliance on Earth-based assets is demonstrated through simulation of the MSL spacecraft utilizing NNAV processes and embedded packets within a limited network containing DSN and MRO. From the demonstrated state estimation performance, NNAV is shown to be a capable and viable method of deep space navigation. Through its implementation as a state augmentation method, the concept integrates with traditional measurements and reduces the dependence on Earth-based updates. Future development of this concept focuses on a growing network of assets and spacecraft, which allows for improved operational flexibility and accuracy in spacecraft state estimation capability and a growing solar system-wide navigation network.

The aim of this thesis is to investigate how well a generic monocular camera, placed on the vehicle, can be employed to localize an autonomous vehicle in a warehouse setting. The main function is to ascertain which zone the vehicle is currently in, as well as update the status when entering a new zone. Two zones are defined, where one has a lower allowed top velocity and the other a higher one. For this purpose ArUco markers are used to signal the system as to where it currently is. Markers are strategically placed around the laboratory area to saturate the environment with possible detections. Multiple sequences are recorded while varying camera placement, angles, and paths to determine the optimal number and placement of markers. In addition to this, a SLAM solution is tested in order to explore what benefits can be found. The idea is to provide fine-grained localization as well as a map of the warehouse environment, to provide more options for further development. To solve the SLAM problem, an implemented particle filter approach initializes a set of particles uniformly distributed within the world frame. For each frame, the particles undergo pose prediction, weight assignment based on likelihood, and resampling. This iterative process gradually converges the particles toward the camera's true position. Visual odometry techniques are used to estimate the camera's ego-motion. The process involves acquiring a sequence of images, detecting distinctive features, matching features between consecutive frames, estimating camera motion, and optionally applying local optimization techniques for further refinement. The implementation shows promise and all test cases performed during the project have been successful as for the zone localization. The SLAM solution can detect and track specific features or landmarks over consecutive frames. By triangulating the positions of these features, their depth and distance can be determined. However, the visualization of these features on a top-down map, which was part of the plan, has not been completed yet despite finishing the particle filter implementation.