Intelligent Product Agents for Multi-Agent Control of Manufacturing Systems

Abstract

The current manufacturing paradigm is shifting toward requiring more flexible and adaptable manufacturing systems. However, to achieve this type of flexibility, new system-level control strategies must be developed to control and coordinate different components on the shop floor. One decentralized control strategy that can enable system flexibility and personalized production is multi-agent control. For this strategy, resource agents, representing handling/processing resources, and product agents, representing parts in the system, work together to drive system behavior. The focus of this talk will be the work for improving the intelligence and capabilities of one of these agents – the product agent. A standardized architecture, models to capture environment dynamics and constraints, and methods to improve decision making will be described. The product agent presented in this talk pushes the fields of manufacturing and system-level control closer to realizing the goals of increased personalized production and improved manufacturing system flexibility.

Bio

Ilya Kovalenko is currently an Assistant Professor in the Department of Mechanical Engineering and the Department of Industrial & Manufacturing Engineering at Penn State University. He received his PhD in Mechanical Engineering from the University of Michigan (2020), his MS degree in Mechanical Engineering from the University of Michigan (2018), and his BS degree in Mechanical Engineering from the Georgia Institute of Technology (2015). He was awarded the NSF Graduate Research Fellowship in 2016 and University of Michigan’s College of Engineering Distinguished Leadership Award in 2020. His current research interests lie in the areas of control theory, artificial intelligence, and smart manufacturing, with a focus on cooperative control, cyber-physical systems, and robotics.