The role of adaptation, learning and optimization are becoming increasingly essential and intertwined. The capability of a system to adapt either through modification of its physiological structure or via some revalidation process of internal mechanisms that directly dictate the response or behavior is crucial in many real world applications. Optimization lies at the heart of most machine learning approaches while learning and optimization are two primary means to effect adaptation in various forms. They usually involve computational processes incorporated within the system that trigger parametric updating and knowledge or model enhancement, giving rise to progressive improvement. This book series serves as a channel to consolidate work related to topics linked to adaptation, learning and optimization in systems and structures. Topics covered under this series include:• complex adaptive systems including evolutionary computation, memetic computing, swarm intelligence, neural networks, fuzzy systems, tabu search, simulated annealing, etc.

No abstract

This chapter briefly reviews the background and the related work in swarm robotics from the perspective of self-sufficiency. It starts with swarm intelligence and provides few examples of swarm behaviors found in nature that serve as the source of inspiration for the advances in swarm robotics. In this regard, it presents the salient properties of robotic modules in a robot swarm and reviews the design of existing state-of-the-art re-configurable robotic platforms that support power sharing. It then introduces the design features of heterogenous REPLICATOR re-configurable robotic modules. The chapter then covers some of the bio-inspired techniques applied in swarm robotics to gain energy autonomy and briefly introduces the fault tolerance, in the context. And lastly, it briefly describes the simulation tools used in this research work.

No abstract

No abstract