This work develops a motion planner that compensates the deficiencies from perception modules by exploiting the reaction capabilities of a vehicle. The work analyzes present uncertainties and defines driving objectives together with constraints that ensure safety. The resulting problem is solved in real-time, in two distinct ways: first, with nonlinear optimization, and secondly, by framing it as a partially observable Markov decision process and approximating the solution with sampling.
Algorithms are a fundamental component of robotic systems. Robot algorithms process inputs from sensors that provide noisy and partial data, build geometric and physical models of the world, plan high-and low-level actions at different time horizons, and execute these actions on actuators with limited precision. The design and analysis of robot algorithms raise a unique combination of questions from many elds, including control theory, computational geometry and topology, geometrical and physical modeling, reasoning under uncertainty, probabilistic algorithms, game theory, and theoretical computer science. The Workshop on Algorithmic Foundations of Robotics (WAFR) is a single-track meeting of leading researchers in the eld of robot algorithms. Since its inception in 1994, WAFR has been held every other year, and has provided one of the premiere venues for the publication of some of the eld's most important and lasting contributions. This books contains the proceedings of the tenth WAFR, held on June 13{15 2012 at the Massachusetts Institute of Technology. The 37 papers included in this book cover a broad range of topics, from fundamental theoretical issues in robot motion planning, control, and perception, to novel applications.
This book is used at the graduate or advanced undergraduate level and many others. Manned and unmanned ground, aerial and marine vehicles enable many promising and revolutionary civilian and military applications that will change our life in the near future. These applications include, but are not limited to, surveillance, search and rescue, environment monitoring, infrastructure monitoring, self-driving cars, contactless last-mile delivery vehicles, autonomous ships, precision agriculture and transmission line inspection to name just a few. These vehicles will benefit from advances of deep learning as a subfield of machine learning able to endow these vehicles with different capability such as perception, situation awareness, planning and intelligent control. Deep learning models also have the ability to generate actionable insights into the complex structures of large data sets. In recent years, deep learning research has received an increasing amount of attention from researchers in academia, government laboratories and industry. These research activities have borne some fruit in tackling some of the challenging problems of manned and unmanned ground, aerial and marine vehicles that are still open. Moreover, deep learning methods have been recently actively developed in other areas of machine learning, including reinforcement training and transfer/meta-learning, whereas standard, deep learning methods such as recent neural network (RNN) and coevolutionary neural networks (CNN). The book is primarily meant for researchers from academia and industry, who are working on in the research areas such as engineering, control engineering, robotics, mechatronics, biomedical engineering, mechanical engineering and computer science. The book chapters deal with the recent research problems in the areas of reinforcement learning-based control of UAVs and deep learning for unmanned aerial systems (UAS) The book chapters present various techniques of deep learning for robotic applications. The book chapters contain a good literature survey with a long list of references. The book chapters are well written with a good exposition of the research problem, methodology, block diagrams and mathematical techniques. The book chapters are lucidly illustrated with numerical examples and simulations. The book chapters discuss details of applications and future research areas.
On-Road Intelligent Vehicles: Motion Planning for Intelligent Transportation Systems deals with the technology of autonomous vehicles, with a special focus on the navigation and planning aspects, presenting the information in three parts. Part One deals with the use of different sensors to perceive the environment, thereafter mapping the multi-domain senses to make a map of the operational scenario, including topics such as proximity sensors which give distances to obstacles, vision cameras, and computer vision techniques that may be used to pre-process the image, extract relevant features, and use classification techniques like neural networks and support vector machines for the identification of roads, lanes, vehicles, obstacles, traffic lights, signs, and pedestrians. With a detailed insight into the technology behind the vehicle, Part Two of the book focuses on the problem of motion planning. Numerous planning techniques are discussed and adapted to work for multi-vehicle traffic scenarios, including the use of sampling based approaches comprised of Genetic Algorithm and Rapidly-exploring Random Trees and Graph search based approaches, including a hierarchical decomposition of the algorithm and heuristic selection of nodes for limited exploration, Reactive Planning based approaches, including Fuzzy based planning, Potential Field based planning, and Elastic Strip and logic based planning. Part Three of the book covers the macroscopic concepts related to Intelligent Transportation Systems with a discussion of various topics and concepts related to transportation systems, including a description of traffic flow, the basic theory behind transportation systems, and generation of shock waves. - Provides an overall coverage of autonomous vehicles and Intelligent Transportation Systems - Presents a detailed overview, followed by the challenging problems of navigation and planning - Teaches how to compare, contrast, and differentiate navigation algorithms
This edited volume includes thoroughly collected on sensing and control for autonomous vehicles. Guidance, navigation and motion control systems for autonomous vehicles are increasingly important in land-based, marine and aerial operations. Autonomous underwater vehicles may be used for pipeline inspection, light intervention work, underwater survey and collection of oceanographic/biological data. Autonomous unmanned aerial systems can be used in a large number of applications such as inspection, monitoring, data collection, surveillance, etc. At present, vehicles operate with limited autonomy and a minimum of intelligence. There is a growing interest for cooperative and coordinated multi-vehicle systems, real-time re-planning, robust autonomous navigation systems and robust autonomous control of vehicles. Unmanned vehicles with high levels of autonomy may be used for safe and efficient collection of environmental data, for assimilation of climate and environmental models and to complement global satellite systems. The target audience primarily comprises research experts in the field of control theory, but the book may also be beneficial for graduate students.
This work presents a behavior planning algorithm for automated driving in urban environments with an uncertain and dynamic nature. The algorithm allows to consider the prediction uncertainty (e.g. different intentions), perception uncertainty (e.g. occlusions) as well as the uncertain interactive behavior of the other agents explicitly. Simulating the most likely future scenarios allows to find an optimal policy online that enables non-conservative planning under uncertainty.
This book describes an effective decision-making and planning architecture for enhancing the navigation capabilities of automated vehicles in the presence of non-detailed, open-source maps. The system involves dynamically obtaining road corridors from map information and utilizing a camera-based lane detection system to update and enhance the navigable space in order to address the issues of intrinsic uncertainty and low-fidelity. An efficient and human-like local planner then determines, within a probabilistic framework, a safe motion trajectory, ensuring the continuity of the path curvature and limiting longitudinal and lateral accelerations. LiDAR-based perception is then used to identify the driving scenario, and subsequently re-plan the trajectory, leading in some cases to adjustment of the high-level route to reach the given destination. The method has been validated through extensive theoretical and experimental analyses, which are reported here in detail.
By the dawn of the new millennium, robotics has undergone a major transformation in scope and dimensions. This expansion has been brought about by the maturity of the field and the advances in its related technologies. From a largely dominant industrial focus, robotics has been rapidly expanding into the challenges of the human world. The new generation of robots is expected to safely and dependably co-habitat with humans in homes, workplaces, and communities, providing support in services, entertainment, education, healthcare, manufacturing, and assistance. Beyond its impact on physical robots, the body of knowledge robotics has produced is revealing a much wider range of applications reaching across diverse research areas and scientific disciplines, such as: biomechanics, haptics, neurosciences, virtual simulation, animation, surgery, and sensor networks among others. In return, the challenges of the new emerging areas are proving an abundant source of stimulation and insights for the field of robotics. It is indeed at the intersection of disciplines that the most striking advances happen. The goal of the series of Springer Tracts in Advanced Robotics (STAR) is to bring, in a timely fashion, the latest advances and developments in robotics on the basis of their significance and quality. It is our hope that the wider dissemination of research developments will stimulate more exchanges and collaborations among the research community and contribute to further advancement of this rapidly growing field.
This book describes how robots can make sense of motion in their surroundings and use the patterns they observe to blend in better in dynamic environments shared with humans.The world around us is constantly changing. Nonetheless, we can find our way and aren’t overwhelmed by all the buzz, since motion often follows discernible patterns. Just like humans, robots need to understand the patterns behind the dynamics in their surroundings to be able to efficiently operate e.g. in a busy airport. Yet robotic mapping has traditionally been based on the static world assumption, which disregards motion altogether. In this book, the authors describe how robots can instead explicitly learn patterns of dynamic change from observations, store those patterns in Maps of Dynamics (MoDs), and use MoDs to plan less intrusive, safer and more efficient paths. The authors discuss the pros and cons of recently introduced MoDs and approaches to MoD-informed motion planning, and provide an outlook on future work in this emerging, fascinating field.
Going beyond the traditional field of robotics to include other mobile vehicles, this reference and "recipe book" describes important theoretical concepts, techniques, and applications that can be used to build truly mobile intelligent autonomous systems (MIAS). With the infusion of neural networks, fuzzy logic, and genetic algorithm paradigms for MIAS, it blends modeling, sensors, control, estimation, optimization, signal processing, and heuristic methods in MIAS and robotics, and includes examples and applications throughout. Offering a comprehensive view of important topics, it helps readers understand the subject from a system-theoretic and practical point of view.
