Traditional robotic systems rely on extensive feature engineering for sensor data and environment state representation, followed by data analysis steps that are usually disconnected from the data representation. Deep Learning-based methodologies, however, combine all these steps in an end-to-end learning based process which is optimized through experience, enabling the identification and exploitation of complex patterns in sensory data, leading to higher performance levels and robust solutions in real-time. Deep Learning for Robot Perception and Cognition introduces a broad range of topics and methods in deep learning for robot perception and cognition together with end-to-end methodologies. It provides the conceptual and mathematical background needed for approaching a large number of robot perception and cognition tasks from an end-to-end learning point of view. Deep Learning for Robot Perception and Cognition is a textbook and reference suitable for students, university and industry researchers and practitioners in Robotic Vision, Intelligent Control, Mechatronics and Deep Learning focusing on Robotic perception and cognition tasks. Presents deep learning principles and methodologiesExplains the principles of applying end-to-end learning in Robotics applicationsPresents how to design and train deep learning modelsShows how to apply Deep Learning in robot vision tasks such as, object recognition, image classification, video analysisUses robotic simulation environments for training deep learning modelsApplies deep learning methods for different tasks ranging from planning and navigation to biosignal analysis | Deep Learning For Robot Perception And Cognition by Alexandros Iosifidis, Paperback | Indigo Chapters