Distributed Machine Learning in Materials that Couple Sensing, Actuation, Computation and Communication

Abstract

This paper reviews machine learning applications and approaches to detection, classification and control of intelligent materials and structures with embedded distributed computation elements. The purpose of this survey is to identify desired tasks to be performed in each type of material or structure (e.g., damage detection in composites), identify and compare common approaches to learning such tasks, and investigate models and training paradigms used. Machine learning approaches and common temporal features used in the domains of structural health monitoring, morphable aircraft, wearable computing and robotic skins are explored. As the ultimate goal of this research is to incorporate the approaches described in this survey into a robotic material paradigm, the potential for adapting the computational models used in these applications, and corresponding training algorithms, to an amorphous network of computing nodes is considered. Distributed versions of support vector machines, graphical models and mixture models developed in the field of wireless sensor networks are reviewed. Potential areas of investigation, including possible architectures for incorporating machine learning into robotic nodes, training approaches, and the possibility of using deep learning approaches for automatic feature extraction, are discussed.

From Natural to Artificial Camouflage: Components and Systems

“…Recent advances in machine learning might also help with addressing trade-offs in computation and communication by integrating the communication structure into the learning problem. For example, [80] proposes to integrate computational synapsis with bandwidth and time constraints into a CNN framework to find appropriate tradeoffs between computation and communication given specific available communication channels.…”

New Directions: Wireless Robotic Materials

“…In addition to build upon and validate hypotheses from biological systems, wireless robotic materials might become part of large-scale distributed neural networks [19]. Wireless channels can be modeled as synapses with bandwidth constraints and delay, and implement distributed pa ern generation and formation algorithms that can adapt to and learn from their environment.…”