Neuromodulation Based Control of Autonomous Robots on a Cloud Computing Platform

In recent years, the advancement of neurobiologically plausible models and computer networking has resulted in new ways of implementing control systems on robotic platforms. The work presents a control approach based on vertebrate neuromodulation and its implementation on autonomous robots in the open-source, open-access environment of robot operating system (ROS). A spiking neural network (SNN) is used to model the neuromodulatory function for generating context based behavioral responses of the robots to sensory input signals. The neural network incorporates three types of neurons- cholinergic and noradrenergic (ACh/NE) neurons for attention focusing and action selection, dopaminergic (DA) neurons for rewards- and curiosity-seeking, and serotonergic (5-HT) neurons for risk aversion behaviors. This model depicts neuron activity that is biologically realistic but computationally efficient to allow for large-scale simulation of thousands of neurons. The model is implemented using graphics processing units (GPUs) for parallel computing in real-time using the ROS environment. The model is implemented to study the risk-taking, risk-aversive, and distracted behaviors of the neuromodulated robots in single- and multi-robot configurations. The entire process is implemented in a cloud computing environment using ROS where the robots communicate wirelessly with the computing nodes through the on-board laptops. However, unlike the traditional neural networks, the neuromodulatory models do not need any pre-training. Instead, the robots learn from the sensory inputs and follow the behavioral facets of living organisms. The details of algorithm development, the experimental setup and implementation results under different conditions, in both single- and multi-robot configurations, are presented along with a discussion on the scope of further work