The combination of Spiking Neural Networks and event-based vision sensors holds the potential of highly efficient and high-bandwidth optical flow estimation. This thesis presents, to the best of the author’s knowledge, the first hierarchical spiking architecture in which motion (direction and speed) selectivity emerges in a biologically plausible unsupervised fashion from the stimuli generated with an event-based camera. A novel adaptive neuron model and Spike-Timing-Dependent Plasticity formulation are at the core of this neural network governing its spike-based processing and learning, respectively. After convergence, the neural architecture exhibits the main properties of biological visual motion systems: feature extraction and local and global motion perception. To assess the outcome of the learning, a shallow conventional Artificial Neural Network is trained to map the activation traces of the penultimate layer to the optical flow visual observables of ventral flows. The proposed solution is validated for simulated event sequences with ground truth measurements. Experimental results show that accurate estimates of these parameters can be obtained over a wide range of speeds.

Robotic behavior policies learned in simulation suffer from a performance degradation once transferred to a real-world robotic platform. This performance degradation originates from discrepancies between the real-world and simulation environment, referred to as the reality gap. To cross the reality gap, this papers presents a simple reinforcement learning algorithm named Directed Increment Policy Search (DIPS). DIPS is a form of episodic model-free policy search which leverages the interpretable structure and the coupling of the Behavior Tree (BT) parameters to reduce the number of required real-world evaluations. Additionally, DIPS does not require a form of reward function crafting and is robust to hyper-parameter settings. DIPS is evaluated on a simulated model of the DelFly Explorer which is tasked to perform a window fly-through maneuver. It is demonstrated that DIPS efficiently and effectively improves the BT behavior policy performance for three simulated environments with increasingly large reality gaps. We believe DIPS can generalize to other behavior representation methods and tasks due to the inherent coupling between behavior and environment experienced by embodied robots.