Disturbance Observer Based Compliant Environment Estimator For Torque Controlled Systems

Disturbance Observer-based Compliant Environment Es[t]imator for Torque Controlled Systems

Automation and Control Trends

This book is an overview of the different paths automation and control engineering have taken lately, from a modern point of view. Built up with example chapters, this book provides some insight into the use of artificial intelligence and control theory on manufacturing, comfort analysis, reliability of modern digital systems, and the use of unusual reference and feedback signals as those coming from the brain. Nonetheless, some chapters are also devoted to a more traditional point of view of control theory, addressing complex problems where human intervention must be limited. Overall, this book is an effort to show that modern automation and control engineering are comprised by many diverse areas, which should interact in order to provide a complete result. In this way, as the systems become more complex and the control objectives more subjective, both, formal analytic and intelligent approaches, should be seen as complementary tools, not unrelated competitors. This books aim is precisely that of showing how broad and diverse the control objectives have become and how the abilities of the control engineer should be extended.

Reinforcement Learning of Bimanual Robot Skills

This book tackles all the stages and mechanisms involved in the learning of manipulation tasks by bimanual robots in unstructured settings, as it can be the task of folding clothes. The first part describes how to build an integrated system, capable of properly handling the kinematics and dynamics of the robot along the learning process. It proposes practical enhancements to closed-loop inverse kinematics for redundant robots, a procedure to position the two arms to maximize workspace manipulability, and a dynamic model together with a disturbance observer to achieve compliant control and safe robot behavior. In the second part, methods for robot motion learning based on movement primitives and direct policy search algorithms are presented. To improve sampling efficiency and accelerate learning without deteriorating solution quality, techniques for dimensionality reduction, for exploiting low-performing samples, and for contextualization and adaptability to changing situations are proposed. In sum, the reader will find in this comprehensive exposition the relevant knowledge in different areas required to build a complete framework for model-free, compliant, coordinated robot motion learning.