Training a Network of Electronic Neurons for Control of a Mobile Robot

Abstract

An adaptive training procedure is developed for a network of electronic neurons, which controls a mobile robot driving around in an unknown environment while avoiding obstacles. The neuronal network controls the angular velocity of the wheels of the robot based on the sensor readings. The nodes in the neuronal network controller are clusters of neurons rather than single neurons. The adaptive training procedure ensures that the input–output behavior of the clusters is identical, even though the constituting neurons are nonidentical and have, in isolation, nonidentical responses to the same input. In particular, we let the neurons interact via a diffusive coupling, and the proposed training procedure modifies the diffusion interaction weights such that the neurons behave synchronously with a predefined response. The working principle of the training procedure is experimentally validated and results of an experiment with a mobile robot that is completely autonomously driving in an unknown environment with obstacles are presented.

Robust partial synchronization of delay-coupled networks

“…, where P is a n × n diagonal matrix and ω is a real positive scalar; see DeLellis et al, 2011) for each system, conditions on the interconnection structure of networks of perturbed nonlinear systems with undelayed di usive couplings are derived to achieve practical synchronization. The bene t of the results in Panteley and Loria (2017), Vromen et al (2016), Steur et al (2015), and Montenbruck et al (2015) is that they provide conceptual insights into the collective behavior of network-interconnected systems with model heterogeneity. However, few work has been done on the quantitative analysis of practical partial synchronization of interconnected systems, in particular, in the presence of delayed couplings.…”