A Multidisciplinary Framework for using emerging Computing Systems in Engineering Education

Abstract

This Innovative Practice Full Paper presents a multidisciplinary framework for using emerging computing systems in engineering education. The computing landscape is in the midst of significant changes. Hardware and software systems are becoming highly data intensive, specialized, parallel, and heterogeneous. With these developments, new applications across a wide range of disciplines are being enabled, from agriculture, mechanical and control systems, and many other physical sciences. For this reason, new approaches for teaching, via hands-on experiences, with these systems is needed. In this paper, we propose a novel framework that can be used to support learning objectives for these systems, at the intersection of multiple disciplines (e.g. computer science, data science, mechanical/aerospace/industrial/computer engineering). Specifically, we describe a flexible computing platform, that supports the exploration of custom hardware and software, interfaces, communications, and integrated system design. The RISC-V based system-on-chip architecture and supporting software and programming tools provide a unique opportunity for students to quickly learn advanced computing concepts critical to future computing systems. An implementation of the framework is described in the context of an important class of control applications, system identification and motion control. As these systems scale, analyzing non-linear system dynamics requires non-traditional approaches, e.g. using modern learning-based models and tools. The proposed approach allows for students to explore the impact of computing abstractions, data-intensive system design, and the potential for cross layer optimizations, while also learning key concepts related to parallel programming models and architectures. Based on this case study, we also provide an analysis and discussion of potential curricular activities that could leverage the framework. A key obstacle for such engineering education research, is the lack of familiarity that students in different disciplines have for the other fields of study, making a complete understanding of overall system design principles difficult. This paper presents a framework for multidisciplinary synergy that alleviates this problem and elevates computing systems to a potentially critical position in engineering education.