The research in this Ph.D. thesis is a step towards creating intelligent autonomous mobile robots with abstract reasoning capabilities using a limited number of very simple raw noisy sensory signals, such as distance sensors. The basic assumption is that the low-dimensional sensory signal can be projected into a high-dimensional dynamic space where learning and computation is performed by linear methods (such as linear regression), overcoming sensor aliasing problems commonly found in robot navigation tasks. This form of computation is known in the literature as Reservoir Computing (RC). The Echo State Network is a particular RC model used in this work, which is characterized by having the high-dimensional space implemented by a discrete analog recurrent neural network with fading memory properties.
This thesis proposes a number of Reservoir Computing architectures which can be used in a variety of autonomous navigation tasks, by modeling implicit abstract representations of an environment and navigation behaviors which can be sequentially executed in the physical environment or simulated as a plan in deliberative goal-directed tasks.