Autonomous robots can replace humans to explore hostile areas, such as Mars and other inhospitable regions. A fundamental task for the autonomous robot is navigation. Due to the inherent difficulties in understanding natural objects and changing environments, navigation for unstructured environments, such as natural environments, has largely unsolved problems. However, navigation for ill-structured environments [1], where roads do not disappear completely, increases the understanding of these difficulties. We develop algorithms for robot navigation on ill-structured roads with monocular vision based on two elements: the appearance information and the geometric information. The fundamental problem of the appearance information-based navigation is road presentation. We propose a new type of road description, a vision vector space (V2-Space), which is a set of local collision-free directions in image space. We report how the V2-Space is constructed and how the V2-Space can be used to incorporate vehicle kinematic, dynamic, and time-delay constraints in motion planning. Failures occur due to the limitations of the appearance information-based navigation, such as a lack of geometric information. We expand the research to include consideration of geometric information. We present the vision-based navigation system using the geometric information. To compute depth with monocular vision, we use images obtained from different camera perspectives during robot navigation. For any given image pair, the depth error in regions close to the camera baseline can be excessively large. This degenerated region is named untrusted area, which could lead to collisions. We analyze how the untrusted areas are distributed on the road plane and predict them accordingly before the robot makes its move. We propose an algorithm to assist the robot in avoiding the untrusted area by selecting optimal locations to take frames while navigating. Experiments show that the algorithm can significantly reduce the depth error and hence reduce the risk of collisions. Although this approach is developed for monocular vision, it can be applied to multiple cameras to control the depth error. The concept of an untrusted area can be applied to 3D reconstruction with a two-view approach.

In this document, we propose and examine the novel use of a learning mechanism between the reactive and deliberative layers of a hybrid robot control architecture. Balancing the need to achieve complex goals and meet real-time constraints, many modern mobile robot navigation control systems make use of a hybrid deliberative-reactive architecture. In this paradigm, a high-level deliberative layer plans routes or actions toward a known goal, based on accumulated world knowledge. A low-level reactive layer selects motor commands based on current sensor data and the deliberative layer's plan. The desired system-level effect of this architecture is that the robot is able to combine complex reasoning toward global objectives with quick reaction to local constraints. Implicit in this type of architecture, is the assumption that both layers are using the same model of the robot's capabilities and constraints. It may happen, for example, due to differences in representation of the robot's kinematic constraints, that the deliberative layer creates a plan that the reactive layer cannot follow. This sort of conflict may cause a degradation in system-level performance, if not complete navigational deadlock. Traditionally, it has been the task of the robot designer to ensure that the layers operate in a compatible manner. However, this is a complex, empirical task. Working to improve system-level performance and navigational robustness, we propose introducing a learning mechanism between the reactive layer and the deliberative layer, allowing the deliberative layer to learn a model of the reactive layer's execution of its plans. First, we focus on detecting this inter-layer conflict, and acting based on a corrected model. This is demonstrated on a physical robotic platform in an unstructured outdoor environment. Next, we focus on learning a model to predict instances of inter-layer conflict, and planning to act with respect to this model. This is demonstrated using supervised learning in a physics-based simulation environment. Results and algorithms are presented.

The purpose of this thesis is to develop a testing environment for mobile robot experiments, to examine methods for multi-robot platooning through hostile environments, and test these algorithms on mobile robots. Such a system will allow us to rapidly address and test problems that arise concerning robot swarms and consequent interactions. In order to create this hardware simulation environment a test bed will be created using ROS or Robot Operating System. This platform is highly modular and extensible for future development. Trajectory generation for the robots will use smoothing splines, B-splines, and A* search. Each method has distinct properties which will be analyzed and rated with respect to its effectiveness with regards to robotic platooning. A few issues to be considered include: Is the optimal path taken with respect to distance and threats? Is the formation of the robots maintained or compromised during traversal of the path? And finally, what sorts of compromises or additions are needed to make each method effective? This work will be helpful for choosing route planning methods in future work and will provide a large code base for rapid prototyping.

Thesis (M.S.)--Florida State University, 2004. / Advisor: Dr. Patrick Hollis, Florida State University, College of Engineering, Dept. of Mechanical Engineering. Title and description from dissertation home page (viewed June 17, 2004). Includes bibliographical references.

Thesis (M.S. in Electrical Engineering and Computer Science)--Massachusetts Institute of Technology. / Includes bibliographical references (p. [127]-132). Also available online.

Thesis (Ph.D)--Computing, Georgia Institute of Technology, 2010. / Committee Chair: Rehg, James M.; Committee Member: Christensen, Henrik; Committee Member: Dellaert, Frank; Committee Member: Essa, Irfan; Committee Member: Malik, Jitendra. Part of the SMARTech Electronic Thesis and Dissertation Collection.

A map is a description of an environment allowing an agent--a human, or in our case a mobile robot--to plan and perform effective actions. From a single location, an agent’s sensors can not observe the whole structure of a complex, large environment. For this reason, the agent must build a map from observations gathered over time and space. We distinguish between large-scale space, with spatial structure larger than the agent’s sensory horizon, and small-scale space, with structure within the sensory horizon. We propose a factored approach to mobile robot map-building that handles qualitatively different types of uncertainty by combining the strengths of topological and metrical approaches. Our framework is based on a computational model of the human cognitive map; thus it allows robust navigation and communication within several different spatial ontologies. Our approach factors the mapping problem into natural sub-goals: building a metrical representation for local small-scale spaces; finding a topological map that represents the qualitative structure of large-scale space; and (when necessary) constructing a metrical representation for large-scale space using the skeleton provided by the topological map. The core contributions of this thesis are a formal description of the Hybrid Spatial Semantic Hierarchy (HSSH), a framework for both small-scale and large-scale representations of space, and an implementation of the HSSH that allows a robot to ground the largescale concepts of place and path in a metrical model of the local surround. Given metrical models of the robot’s local surround, we argue that places at decision points in the world can be grounded by the use of a primitive called a gateway. Gateways separate different regions in space and have a natural description at intersections and in doorways. We provide an algorithmic definition of gateways, a theory of how they contribute to the description of paths and places, and practical uses of gateways in spatial mapping and learning. / text

This doctoral thesis extends analytical terramechanic modelling for small lightweight mobile robots operating on sandy soil. Previous terramechanic models were designed to capture and predict the mean values of the forces and sinkage that a wheel may experience. However, these models do not capture the fluctuations in the forces and sinkage that were observed in experimental data. The model developed through the course of this research enhances existing terramechanic models by proposing and validating a new pressure-sinkage relationship. The resulting two-dimensional model was validated with a unique high fidelity single-wheel testbed (SWTB) which was installed on a Blohm Planomat 408 computer-numerically controlled creepfeed grinding machine. The new SWTB translates the terrain in the horizontal direction while the drivetrain and wheel support systems are constrained in the horizontal direction but allowed to freely move in the vertical direction. The design of the SWTB allowed for a counterbalance to be installed and, as a result, low normal loads could be examined. The design also took advantage of the grinding machine's high load capacity and precise velocity control. Experiments were carried out with the new SWTB and predictable repeating ridges were found in the track of a smooth rigid wheel operating in sandy soil. To ensure that these ridges were not an artifact of the new SWTB a mobile robot was used to validate the SWTB findings, which it did. The new SWTB is a viable method for investigating fundamental terramechanic issues. A series of experiments at different slip ratios and normal loads were carried out on the SWTB to validate the new pressure-sinkage relationship which explicitly captures and predicts the oscillations about the mean values for the forces and sinkage values for both a smooth wheel and a wheel with grousers. The new pressure-sinkage relationship adds two new dimensionless empirical factors to the well known pressure-sinkage relationship for a rigid wheel. The first new factor accounts for changes in the local density of the terrain around the wheel and the second factor accounts for the effects grousers have on the forces and sinkage.

This research project proposes the development of an autonomous, omnidirectional vehicle that will be used for general indoor service applications. A suggested trial application for this service robot will be to deliver printouts to various network users in their offices. The robot will serve as a technology demonstrator and could later also be used for other tasks in an office, medical or industrial environment. The robot will use Mecanum wheels (also known as Swedish 45° or Ilon wheels) to achieve omnidirectionality. This will be especially useful in the often cramped target environments, because the vehicle effectively has a zero radius turning circle and is able to change direction of motion without changing its pose. Part of the research will also be to investigate a novel propulsion system based on the Mecanum wheel. The robot will form part of a portfolio of service robots that the Mechatronics and Micro Manufacturing (MMM) group at the CSIR is busy developing. Service robots are typically used to perform Dull, Dangerous or Dirty work, where human presence is not essential if the robot can perform the task reliably and successfully. / Thesis (M.Sc.Eng.)-University of KwaZulu-Natal, Durban, 2011.

This project details the construction and development of, and experimentation with a mobile service courier robot named Meercat. This robot has been built from the ground up using parts sourced from various places. The application for this service robot is the delivery of internal mail parcels between the buildings situated on the campus of the Council for Scientific and Industrial Research (CSIR) in Pretoria. To achieve this, the robot has to be able to localise and navigate through indoor office and laboratory environments and over outdoor tarred roads which interconnect the various buildings. Not many robots are intended for operation in both indoor and outdoor environments, and to achieve this, multiple sensing systems are implemented on the platform, where the correct selection of sensing inputs is a key aspect. Further testing and experiments will take place with algorithms for localisation and navigation. As a limited budget was available for the development of this robot, cost-effective solutions had to be found for the mechanical, sensing and computation needs. The Mechatronics group from the Mechatronics and Micro Manufacturing (MMM) competency area at the CSIR is involved with the development of various autonomous mobile robots. The particular robot developed in this project will be an addition to the CSIR’s current fleet of robots and will be used as a stepping stone for experimentation with new sensors and electronics, and the development of further positioning and navigation algorithms. / Thesis (M.Sc.Eng.)-University of KwaZulu-Natal, Durban, 2011.