In order for autonomous vehicles to achieve life-long operation in outdoor environments, navigation systems must be able to cope with visual change---whether it's short term, such as variable lighting or weather conditions, or long term, such as different seasons. As a GPS is not always reliable, autonomous vehicles must be self sufficient with onboard sensors. This thesis examines the problem of localisation against a known map across extreme lighting and weather conditions using only a stereo camera as the primary sensor. The method presented departs from traditional techniques that blindly apply out-of-the-box interest-point detectors to all images of all places. This naive approach fails to take into account any prior knowledge that exists about the environment in which the robot is operating. Furthermore, the point-feature approach often fails when there are dramatic appearance changes, as associating low-level features such as corners or edges is extremely difficult and sometimes not possible. By leveraging knowledge of prior appearance, this thesis presents an unsupervised method for learning a set of distinctive and stable (i.e., stable under appearance changes) feature detectors that are unique to a specific place in the environment. In other words, we learn place-dependent feature detectors that enable vastly superior performance in terms of robustness in exchange for a reduced, but tolerable metric precision. By folding in a method for masking distracting objects in dynamic environments and examining a simple model for external illuminates, such as the sun, this thesis presents a robust localisation system that is able to achieve metric estimates from night-today or summer-to-winter conditions. Results are presented from various locations in the UK, including the Begbroke Science Park, Woodstock, Oxford, and central London.

Accurate and robust localisation is a fundamental aspect of any autonomous mobile robot. However, if these are to become widespread, it must also be available at low-cost. In this thesis, we develop a new approach to localisation using monocular cameras by leveraging a coloured 3D pointcloud prior of the environment, captured previously by a survey vehicle. We make no assumptions about the external conditions during the robot's traversal relative to those experienced by the survey vehicle, nor do we make any assumptions about their relative sensor configurations. Our method uses no extracted image features. Instead, it explicitly optimises for the pose which harmonises the information, in a Shannon sense, about the appearance of the scene from the captured images conditioned on the pose, with that of the prior. We use as our objective the Normalised Information Distance (NID), a true metric for information, and demonstrate as a consequence the robustness of our localisation formulation to illumination changes, occlusions and colourspace transformations. We present how, by construction of the joint distribution of the appearance of the scene from the prior and the live imagery, the gradients of the NID can be computed and how these can be used to efficiently solve our formulation using Quasi-Newton methods. In order to reliably identify any localisation failures, we present a new classifier using the local shape of the NID about the candidate pose and demonstrate the performance gains of the complete system from its use. Finally, we detail the development of a real-time capable implementation of our approach using commodity GPUs and demonstrate that it outperforms a high-grade, commercial GPS-aided INS on 57km of driving in central Oxford, over a range of different conditions, times of day and year.

Quando um robô autônomo tenta resolver as tarefas de navegação dentro de um ambiente real interno usando relações qualitativas, vários problemas aparecem tais como observação parcial do ambiente e percepção incerta. Isso ocorre porque os sensores do robô não proporcionam informação suficiente para perceber completamente as situações do ambiente, além de incorporarem ruído no processo. A web semântica dota o robô autônomo com a habilidade de obter conhecimento de senso comum extraído da web, conhecimento este que os sensores do robô não podem proporcionar. Porém, nem sempre é fácil levar efetivamente estes recursos semânticos da web ao uso prático. Neste trabalho, foi examinado o uso de recursos semânticos da web na navegação robótica; mais especificamente, em uma navegação qualitativa onde o raciocínio incerto desempenha um papel significativo. Nós avaliamos o uso de uma representação relacional; particularmente, na combinação da informação semântica web e dos dados de baixo nível proporcionados pelos sensores, permitindo uma descrição de objetos e das relações entre os mesmos. Esta representação também permite o uso de abstração e generalização das situações do ambiente. Este trabalho propõe a arquitetura Web-based Relational Robotic Architecture (WRRA )para navegação robótica que combina os dados de baixo nível dos sensores do robô e os recursos web semânticos existentes baseados em lógica descritiva probabilística, como aprendizagem e planejamento relacional probabilístico. Neste trabalho, mostramos os benefícios desta arquitetura em um robô simulado, apresentando um estudo de caso sobre como os recursos semânticos podem ser usados para lidar com a incerteza da localização e o mapeamento em um problema prático. / When an autonomous robot attempts to solve navigation tasks in a qualitative relational way within a real indoor environments, several problems appear such as partial observation of the environment, and uncertain perception, since the robots sensors do not provide enough information to perceive completely the environment situations, besides the sensors incorporate noise in the process. The semantic web information endows the autonomous robot with the ability to obtain common sense knowledge from the web that the robot\'s sensors cannot provide. However, it is not always easy to effectively bring these semantic web resources into practical use. In this work, we examine the use of semantic web resources in robot navigation; more specifically, in qualitative navigation where uncertain reasoning plays a significant role. We evaluate the use of a relational representation; particularly, in the combination of the semantic web and the low-level data sensor information, which allows a description of relationships among objects. This representation also allows the use of abstraction and generalization of the environment situations. This work proposes the framework Web-based Relational Robotic Architecture WRRA for robot navigation that connects the low-level data from robot\'s sensors and existing semantic web resources based on probabilistic description logics, with probabilistic relational learning and planning. We show the benefits of this framework in a simulated robot, presenting a case study on how semantic web resources can be used to face location and mapping uncertain in a practical problem.

Quando um robô autônomo tenta resolver as tarefas de navegação dentro de um ambiente real interno usando relações qualitativas, vários problemas aparecem tais como observação parcial do ambiente e percepção incerta. Isso ocorre porque os sensores do robô não proporcionam informação suficiente para perceber completamente as situações do ambiente, além de incorporarem ruído no processo. A web semântica dota o robô autônomo com a habilidade de obter conhecimento de senso comum extraído da web, conhecimento este que os sensores do robô não podem proporcionar. Porém, nem sempre é fácil levar efetivamente estes recursos semânticos da web ao uso prático. Neste trabalho, foi examinado o uso de recursos semânticos da web na navegação robótica; mais especificamente, em uma navegação qualitativa onde o raciocínio incerto desempenha um papel significativo. Nós avaliamos o uso de uma representação relacional; particularmente, na combinação da informação semântica web e dos dados de baixo nível proporcionados pelos sensores, permitindo uma descrição de objetos e das relações entre os mesmos. Esta representação também permite o uso de abstração e generalização das situações do ambiente. Este trabalho propõe a arquitetura Web-based Relational Robotic Architecture (WRRA )para navegação robótica que combina os dados de baixo nível dos sensores do robô e os recursos web semânticos existentes baseados em lógica descritiva probabilística, como aprendizagem e planejamento relacional probabilístico. Neste trabalho, mostramos os benefícios desta arquitetura em um robô simulado, apresentando um estudo de caso sobre como os recursos semânticos podem ser usados para lidar com a incerteza da localização e o mapeamento em um problema prático. / When an autonomous robot attempts to solve navigation tasks in a qualitative relational way within a real indoor environments, several problems appear such as partial observation of the environment, and uncertain perception, since the robots sensors do not provide enough information to perceive completely the environment situations, besides the sensors incorporate noise in the process. The semantic web information endows the autonomous robot with the ability to obtain common sense knowledge from the web that the robot\'s sensors cannot provide. However, it is not always easy to effectively bring these semantic web resources into practical use. In this work, we examine the use of semantic web resources in robot navigation; more specifically, in qualitative navigation where uncertain reasoning plays a significant role. We evaluate the use of a relational representation; particularly, in the combination of the semantic web and the low-level data sensor information, which allows a description of relationships among objects. This representation also allows the use of abstraction and generalization of the environment situations. This work proposes the framework Web-based Relational Robotic Architecture WRRA for robot navigation that connects the low-level data from robot\'s sensors and existing semantic web resources based on probabilistic description logics, with probabilistic relational learning and planning. We show the benefits of this framework in a simulated robot, presenting a case study on how semantic web resources can be used to face location and mapping uncertain in a practical problem.

Robotics has been the subject of academic study from as early as 1948. For much of this time, study has focused on very specific applications in very well controlled environments. For example, the first commercial robots (1961) were introduced in order to improve the efficiency of production lines. The tasks undertaken by these robots were simple, and all that was required of a control algorithm was speed, repetitiveness and reliability in these environments. Now however, robots are being used to move around autonomously in increasingly unpredictable environments, and the need for robotic control algorithms that can successfully react to such conditions is ever increasing. In addition to this there is an ever-increasing array of robots available, the control algorithms for which are often incompatible. This can result in extensive redesign and large sections of code being re-written for use on different architectures. The thesis presented here is that a new generic approach can be created that provides robust high quality smooth paths and time-optimal path tracking to substantially increase applicability and efficiency of autonomous motion plans. The control system developed to support this thesis is capable of producing high quality smooth paths, and following these paths to a high level of accuracy in a robust and near time-optimal manner. The system can control a variety of robots in environments that contain 2D obstacles of various shapes and sizes. The system is also resilient to sensor error, spatial drift, and wheel-slip. In achieving the above, this system provides previously unavailable functionality by generically creating and tracking high quality paths so that only minor and clear adjustments are required between different robots and also be being capable of operating in environments that contain high levels of perturbation. The system is comprised of five separate novel component algorithms in order to cater for five different motion challenges facing modern robots. Each algorithm provides guaranteed functionality that has previously been unavailable in respect to its challenges. The challenges are: high quality smooth movement to reach n-dimensional goals in regions without obstacles, the navigation of 2D obstacles with guaranteed completeness, high quality smooth movement for ground robots carrying out 2D obstacle navigation, near time-optimal path tracking, and finally, effective wheel-slip detection and compensation. In meeting these challenges the algorithms have tackled adherence to non-holonomic constraints, applicability to a wide range of robots and tasks, fast real-time creation of paths and controls, sensor error compensation, and compensation for perturbation. This thesis presents each of the above algorithms individually. It is shown that existing methods are unable to produce the results provided by this thesis, before detailing the operation of each algorithm. The methodology employed is varied in accordance with each of the five core challenges. However, a common element of methodology throughout the thesis is that of gradient descent within a new type of potential field, which is dynamic and capable of the simultaneous creation of high-quality paths and the controls required to execute them. By relating global to local considerations through subgoals, this methodology (combined with other elements) is shown to be fully capable of achieving the aims of the thesis. It is concluded that the produced system represents a novel and significant contribution as there is no other system (to the author’s knowledge) that provides all of the functionality given. For each component algorithm there are many control systems that provide one or more of its features, but none that are capable of all of the features. Applications for this work are wide ranging as it is comprised of five component algorithms each applicable in their own right. For example, high quality smooth paths may be created and followed in any dimensionality of space if time optimality and obstacle avoidance are not required. Broadly speaking, and in summary, applications are to ground-based robotics in the areas of smooth path planning, time optimal travel, and compensation for unpredictable perturbation.