Handling Uncertainty and Networked Structure in Robot Control [Paperback]

Thisbook focuses on two challenges posed in robot control by the increasingadoption of robots in the everyday human environment: uncertainty and networkedcommunication. PartI of the book describes learning control to address environmental uncertainty.Part II discusses state estimation, active sensing, and complex scenarioperception to tackle sensing uncertainty. Part IIIcompletes the book with control of networked robots and multi-robot teams.

Each chapter features in-depth technical coverage and case studieshighlighting the applicability of the techniques, with real robots or insimulation. Platforms include mobile ground, aerial, and underwater robots, aswell as humanoid robots and robot arms. Source code and experimental data areavailable at http://extras.springer.com.

The text gathers contributions from academic and industry experts,and offers a valuable resource for researchers or graduate students in robotcontrol and perception. It also benefits researchers in related areas, such ascomputer vision, nonlinear and learning control, and multi-agent systems.

Part I Learning Control in Unknown Environments.- Robot Learning for Persistent Autonomy.- The Explore-Exploit Dilemma in Nonstationary Decision Making under Uncertainty.- Learning Complex Behaviors via Sequential Composition and Passivity-based Control.- Visuospatial Skill Learning.- Part II Dealing with Sensing Uncertainty.- Observer Design for Robot Manipulators via Takagi-Sugeno Models and Linear Matrix Inequalities.- Homography Estimation between Omnidirectional Cameras without Point Correspondences.- Dynamic environment perception and 4D reconstruction using a mobile Rotating Multi-beam Lidar sensor.- ROBOSHERLOCK: Unstructured Information Processing for Robot Perception.- Active SLAM : Problem Overview and an Application to Navigation Under Uncertainty.- Interactive Segmentation of Textured and Textureless Objects.- Part III Control of Networked and Ilc¿