At any stage of development, any organism is required to go through a learning phase as a way to acquire and enhance certain skills. Similarly, legged robots perform a learning phase to obtain basic skills before implementing them in real specific applications. Walking skills are one of the first capabilities that need to be learned, as this allows the robots to traverse their environment. This work proposes A Directed Evolutionary Algorithm Learning method - which we henceforth refer to as the DEAL method. This method aims to direct the learning process by incorporating the robot learning experience, and hence, to reduce the time period required for the learning process to converge to a framed optimal solution. This will reduce the deployment time of the robot and as a result, the learning process will have a minimal impact on the wear and tear of the robot body and maximise the life of the robot when it is deployed on specific applications.

This invaluable book comprehensively describes evolutionary robotics and computational intelligence, and how different computational intelligence techniques are applied to robotic system design. It embraces the most widely used evolutionary approaches with their merits and drawbacks, presents some related experiments for robotic behavior evolution and the results achieved, and shows promising future research directions. Clarity of explanation is emphasized such that a modest knowledge of basic evolutionary computation, digital circuits and engineering design will suffice for a thorough understanding of the material. The book is ideally suited to computer scientists, practitioners and researchers keen on computational intelligence techniques, especially the evolutionary algorithms in autonomous robotics at both the hardware and software levels. Sample Chapter(s). Chapter 1: Artificial Evolution Based Autonomous Robot Navigation (184 KB). Contents: Artificial Evolution Based Autonomous Robot Navigation; Evolvable Hardware in Evolutionary Robotics; FPGA-Based Autonomous Robot Navigation via Intrinsic Evolution; Intelligent Sensor Fusion and Learning for Autonomous Robot Navigation; Task-Oriented Developmental Learning for Humanoid Robots; Bipedal Walking Through Reinforcement Learning; Swing Time Generation for Bipedal Walking Control Using GA Tuned Fuzzy Logic Controller; Bipedal Walking: Stance Ankle Behavior Optimization Using Genetic Algorithm. Readership: Researchers in evolutionary robotics, and graduate and advanced undergraduate students in computational intelligence.

The development of legged robots capable of navigating in and interacting with the world is quickly advancing as new methods and techniques for sensing, decision-making, and controls expand the capabilities of state-of-the-art systems. Model-based methods, empowered by greater computing capacity and clever formulations, are imbuing systems with further physics-based understanding. While machine learning techniques, enabled by parallelized data generation and more efficient training, are imparting greater robustness to noise and abilities to handle poorly defined world features. Together these tools constitute the two major paradigms of legged robot research and while both have their shortcomings, they have complementary limitations that can be reinforced by the other's strengths. We propose MIMOC: Motion Imitation from Model-Based Optimal Control. MIMOC is a Reinforcement Learning (RL) locomotion controller that learns agile locomotion by imitating reference trajectories from model-based optimal control. MIMOC mitigates challenges faced by other motion imitation-based RL approaches because the generated reference trajectories are dynamically consistent, require no motion retargeting, and include torque references that are essential to learn dynamic locomotion. As a result, MIMOC does not require any fine-tuning to transfer the policy to the real robots. MIMOC also overcomes key issues with model-based optimal controllers. Since it is trained with simulated sensor noise and domain randomization, MIMOC is less sensitive to modeling and state estimation inaccuracies. We validate MIMOC on the Mini-Cheetah in outdoor environments over a wide variety of challenging terrain and on the MIT Humanoid in simulation. We show that MIMOC can transfer to the real-world and to different legged platforms. We also show cases where MIMOC outperforms model-based optimal controllers, and demonstrate the value of imitating torque references.

Bioinspired Legged Locomotion: Models, Concepts, Control and Applications explores the universe of legged robots, bringing in perspectives from engineering, biology, motion science, and medicine to provide a comprehensive overview of the field. With comprehensive coverage, each chapter brings outlines, and an abstract, introduction, new developments, and a summary. Beginning with bio-inspired locomotion concepts, the book's editors present a thorough review of current literature that is followed by a more detailed view of bouncing, swinging, and balancing, the three fundamental sub functions of locomotion. This part is closed with a presentation of conceptual models for locomotion. Next, the book explores bio-inspired body design, discussing the concepts of motion control, stability, efficiency, and robustness. The morphology of legged robots follows this discussion, including biped and quadruped designs. Finally, a section on high-level control and applications discusses neuromuscular models, closing the book with examples of applications and discussions of performance, efficiency, and robustness. At the end, the editors share their perspective on the future directions of each area, presenting state-of-the-art knowledge on the subject using a structured and consistent approach that will help researchers in both academia and industry formulate a better understanding of bioinspired legged robotic locomotion and quickly apply the concepts in research or products. - Presents state-of-the-art control approaches with biological relevance - Provides a thorough understanding of the principles of organization of biological locomotion - Teaches the organization of complex systems based on low-dimensional motion concepts/control - Acts as a guideline reference for future robots/assistive devices with legged architecture - Includes a selective bibliography on the most relevant published articles

A variety of impressive approaches to legged locomotion exist; however, the science of legged robotics is still far from demonstrating a solution which performs with a level of flexibility, reliability and careful foot placement that would enable practical locomotion on the variety of rough and intermittent terrain humans negotiate with ease on a regular basis. In this thesis, we strive toward this particular goal by developing a methodology for designing control algorithms for moving a legged robot across such terrain in a qualitatively satisfying manner, without falling down very often. We feel the definition of a meaningful metric for legged locomotion is a useful goal in and of itself. Specifically, the mean first-passage time (MFPT), also called the mean time to failure (MTTF), is an intuitively practical cost function to optimize for a legged robot, and we present the reader with a systematic, mathematical process for obtaining estimates of this MFPT metric. Of particular significance, our models of walking on stochastically rough terrain generally result in dynamics with a fast mixing time, where initial conditions are largely "forgotten" within 1 to 3 steps. Additionally, we can often find a near-optimal solution for motion planning using only a short time-horizon look-ahead. Although we openly recognize that there are important classes of optimization problems for which long-term planning is required to avoid "running into a dead end" (or off of a cliff!), we demonstrate that many classes of rough terrain can in fact be successfully negotiated with a surprisingly high level of long-term reliability by selecting the short-sighted motion with the greatest probability of success. The methods used throughout have direct relevance to machine learning, providing a physics-based approach to reduce state space dimensionality and mathematical tools to obtain a scalar metric quantifying performance of the resulting reduced-order system.

An overview of the basic concepts and methodologies of evolutionary robotics, which views robots as autonomous artificial organisms that develop their own skills in close interaction with the environment and without human intervention.

Darwin2K: An Evolutionary Approach to Automated Design for Robotics is an essential reference tool for researchers, professionals, and students involved in robot design or in evolutionary synthesis, design, and optimization. It is also necessary for users of Darwin2K. Researchers and hobbyists interested in genetic algorithms and artificial life techniques will find the book interesting. The primary purpose of this book is to describe a methodology for using computers to automatically design robots to meet the specific needs of an application. Details of many novel aspects of the methodology are presented, including an evolutionary algorithm for synthesizing and optimizing multiple objective functions, an algorithm for dynamic simulation of arbitrary robots, an extensible software architecture, and a new representation for robots that is appropriate for robot design. The methodology as a whole is significant in terms of its impact on robot design practices, and as a case study in building evolutionary design systems. Individual parts of the systems are also relevant to other areas. For example, the evolutionary algorithm can be used for design and optimization problems other than robotics, and the dynamic simulation algorithm can be used for analysis and simulation of existing robots or as a part of a manual design tool. The book also gives an overview of previous work in automated design of robots, and of evolutionary design in other engineering disciplines.

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, neuros- ences, 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.

Robot Motion Control 2009 presents very recent results in robot motion and control. Forty short papers have been chosen from those presented at the sixth International Workshop on Robot Motion and Control held in Poland in June 2009. The authors of these papers have been carefully selected and represent leading institutions in this field. The following recent developments are discussed: design of trajectory planning schemes for holonomic and nonholonomic systems with optimization of energy, torque limitations and other factors, new control algorithms for industrial robots, nonholonomic systems and legged robots, different applications of robotic systems in industry and everyday life, like medicine, education, entertainment and others, multiagent systems consisting of mobile and flying robots with their applications. The book is suitable for graduate students of automation and robotics, informatics and management, mechatronics, electronics and production engineering systems as well as scientists and researchers working in these fields.