Bøger i Springer Tracts in Advanced Robotics serien

This book presents theoretical foundations and technical implementation guidelines for multi-vehicle fleet maneuvering, which can be implemented by readers and can also be a basis for future research. As a research monograph, this book presents fundamental concepts, theories, and technologies for localization, motion planning, and control of multi-vehicle systems, which can be a reference book for researchers and graduate students from different levels. As a technical guide, this book provides implementation guidelines, pseudocode, and flow diagrams for practitioners to develop their own systems. Readers should have a preliminary knowledge of mobile robotics, state estimation and automatic control to fully understand the contents in this book. To make this book more readable and understandable, extensive experimental results are presented to support each chapter.

Simultaneous Localization and Mapping (SLAM) has been a long-standing research problem in robotics. It describes the problem of a robot mapping an unknown environment, while simultaneously localizing in it with the help of the incomplete map. This book describes a technique called Switchable Constraints.Switchable Constraints help to increase the robustness of SLAM against data association errors and in particular against false positive loop closure detections. Such false positive loop closure detections can occur when the robot erroneously assumes it re-observed a landmark it has already mapped or when the appearance of the observed surroundings is very similar to the appearance of other places in the map. Ambiguous observations and appearances are very common in human-made environments such as office floors or suburban streets, making robustness against spurious observations a key challenge in SLAM. The book summarizes the foundations of factor graph-based SLAM techniques. Itexplains the problem of data association errors before introducing the novel idea of Switchable Constraints. We present a mathematical derivation and probabilistic interpretation of Switchable Constraints along with evaluations on different datasets. The book shows that Switchable Constraints are applicable beyond SLAM problems and demonstrates the efficacy of this technique to improve the quality of satellite-based localization in urban environments, where multipath and non-line-of-sight situations are common error sources.

This book presents the astonishing potential of deep sensorimotor policies for agile vision-based quadrotor flight. Quadrotors are among the most agile and dynamic machines ever created. However, developing fully autonomous quadrotors that can approach or even outperform the agility of birds or human drone pilots with only onboard sensing and computing is challenging and still unsolved.Deep sensorimotor policies, generally trained in simulation, enable autonomous quadrotors to fly faster and more agile than what was possible before. While humans and birds still have the advantage over drones, the author shows the current research gaps and discusses possible future solutions.

This book provides a concise survey and description of recent collision detection methods for robot manipulators. Beginning with a review of robot kinodynamic models and preliminaries on basic statistical learning methods, the book covers fundamental aspects of the collision detection problem, from collision types and collision detection performance criteria to model-free versus model-based methods, and the more recent data-driven learning-based approaches to collision detection. Special effort has been given to describing and evaluating existing methods with a unified set of notation, systematically categorizing these methods according to a basic set of criteria, and summarizing the advantages and disadvantages of each method. This book is the first to comprehensively organize the growing body of learning-based collision detection methods, ranging from basic supervised learning methods to more advanced approaches based on unsupervised learning and transfer learning techniques. Step-by-step implementation details and pseudocode descriptions are provided for key algorithms. Collision detection performance is measured with respect to both conventional criteria such as detection delay and the number of false alarms, as well as criteria that measure generalization capability for learning-based methods. Whether it be for research or commercial applications, in settings ranging from industrial factories to physical human¿robot interaction experiments, this book can help the reader choose and successfully implement the most appropriate detection method that suits their robot system and application.

Using a designed vector field to guide robots to follow a given geometric desired path has found a range of practical applications, such as underwater pipeline inspection, warehouse navigation, and highway traffic monitoring. It is thus in great need to build a rigorous theory to guide practical implementations with formal guarantees. It is even so when multiple robots are required to follow predefined desired paths or maneuver on surfaces and coordinate their motions to efficiently accomplish repetitive and laborious tasks.The book introduces guiding vector fields on Euclidean spaces and Riemannian manifolds for single-robot and multi-robot path-following and motion coordination, provides rigorous theoretical guarantees of vector field guided motion control of robotic systems, and elaborates on the practical implementation of the proposed algorithms on mobile wheeled robots and fixed-wing aircraft. It provides guidelines for the robust, reliable, and safe practical implementations for robotic tasks, including path-following navigation, obstacle-avoidance, and multi-robot motion coordination. In particular, the book reveals fundamental theoretic underpinnings of guiding vector fields and applies to addressing various robot motion control problems. Notably, it answers many crucial and challenging questions such as:· How to generate a general guiding vector field on any n-dimensional Riemannian manifold for robot motion control tasks?· Do singular points always exist in a general guiding vector field? · How to generate a guiding vector field that is free of singular points?· How to design control algorithms based on guiding vector fields for different robot motion control tasks including path-following, obstacle-avoidance, and multi-robot distributed motion coordination?Answering these questions has led to the discovery of fundamental assumptions, a ¿topological surgery¿ to create a singularity-free guiding vector field, a robot navigation algorithm with the global convergence property, a provably safe collision-avoidance algorithm and an effective distributed motion control algorithm, etc

This book deals with the study of tilt-rotor omnidirectional aerial robots and their application to aerial physical interaction tasks. Omnidirectional aerial robots possess decoupled translational and rotational dynamics, which are important for stable and sustained aerial interaction. The additional ability to dynamically re-orient thrust vectors opens the door to a wide array of possible morphologies and system capabilities. Through modeling, control, prototype design, and experimental evaluation, this book presents a comprehensive methodology and examples for the development of a novel tilt-rotor aerial manipulator. This work serves as a guide for envisioning and constructing innovative systems that will advance the frontier of aerial manipulation.

Robotic research and developments in computing technologies including artificial intelligence have led to significant improvements in autonomous capabilities of robots. Yet, human supervision is advisable and, in many cases, necessary when robots interact with real-world, outside-lab environments. This is due to the fact that complete autonomy in robots has not yet been achieved. When robots encounter challenges beyond their capabilities, a viable solution is to include human operators in the loop, who can support robots through teleoperation, taking complete control or shared control. This monograph focuses on a special form of shared control, namely mixed-initiative, where the final command to the robot is a weighted sum of the commands from the operator and the autonomous controller. The weights (fixed or adaptive), called authority allocation (AA) factors, decide who has more control authority over the robot. Several research groups use different methods toadapt the AA factors online and the benefits of adaptive mixed-initiative shared control have been well established in terms of task completion success and operator usability. However, stability of the overall shared control framework, with communication time-delays between the operator and the robot, is a field that has not been examined extensively. This monograph presents methods to improve performance and stability in shared control so that the possibilities of its applications can be widened. Firstly, methods to improve the haptic feedback performance of teleoperation are developed. Secondly, methods to stabilize adaptive shared control systems, while still ensuring high teleoperation performance, are proposed. The methods are validated on multiple robotic systems and they were applied in several projects, both in space and terrestrial domains. With the aforementioned contributions, this monograph provides an overarching framework to improve synergy between humans and robots. The flexibility of the framework allows integration of existent teleoperation and shared control approaches, which further promotes synergy within the robotics community.