Special Issue on the 2020 International Conference on Automation Science and Engineering

Mariagrazia Dotoli, Weiming Shen, Qing-Shan Jia, Ray Y. ZhongIEEE Trans Autom. Sci. Eng 2022 · OpenReview

Introduction

This special issue of the IEEE Transactions on Automation Science and Engineering (TASE) features 12 standout research papers originally presented at the 2020 International Conference on Automation Science and Engineering (CASE2020). Although the conference was transitioned to a virtual format due to the COVID-19 pandemic, it remained the flagship forum for the IEEE Robotics and Automation Society. The central theme, "Automation Analytics," highlights a global challenge: the integration of data-driven modeling with traditional control systems to manage the complexity of modern industrial and biological systems.

Guest Editor Maria Pia Fanti

The Paradigm of Automation Analytics

The guest editorial frames a significant evolution in the field. Automation is no longer confined to repetitive, deterministic tasks in controlled environments. Instead, it is increasingly tasked with managing highly complex, uncertain, and interconnected systems. The "Automation Analytics" framework addresses this by extracting actionable intelligence from vast datasets to improve decision-making. This approach acts as a crucial bridge between classical control theory and modern data science, allowing for more nuanced responses to real-world volatility.

Guest Editor MengChu Zhou

Core Research Domains

The selected articles span four critical domains, demonstrating the versatility of automation analytics in solving diverse technical challenges.

1. Smart Energy and Infrastructure

A major focus of this issue is the stability and economic efficiency of energy grids. As power systems become more decentralized and integrate multiple energy sources, they face increased risks of cascading failures.

  • Failure Prevention: Researchers utilize event-triggered hybrid system models to identify and halt the propagation of failures in real-time.
  • Microgrid Management: The issue explores robust model predictive control (MPC) strategies that balance the economic costs of energy procurement with the comfort requirements of end-users, particularly in integrated gas and electricity microgrids.
  • Market Intelligence: To protect industrial consumers, new models use historical market data to generate "rolling price spike warnings," allowing for proactive energy management.

2. Precision Farming and Sustainability

Automation is playing a key role in the "greening" of agriculture. The research presented here emphasizes sustainability through better modeling and monitoring.

  • Polyculture Simulation: The introduction of first-order, open-access simulators for polyculture farming allows for the optimization of irrigation and growth strategies for multiple crops simultaneously, a significant step up from traditional monoculture models.
  • Livestock Health: Wearable technology is making its way into the barn. By analyzing inertial sensor data with machine learning, researchers can now detect subtle signs of limb lameness in horses, enabling earlier intervention and better animal welfare.

3. Advanced Manufacturing and Logistics

In the manufacturing sector, the focus is on enhancing quality control and optimizing complex logistics.

  • Defect Recognition: Moving beyond standard computer vision, the issue presents graph-guided convolutional neural networks (CNNs). These models leverage the structural relationships within manufacturing data to achieve superior accuracy in identifying surface defects.
  • Electric Vehicle Routing: As factories adopt electric vehicle fleets, routing becomes more complex due to charging constraints. New compositional algorithms provide efficient solutions for these large-scale coordination problems.

4. Autonomous Navigation and Robotics

Operating in "unknown" or GPS-denied environments remains a frontier for robotics.

  • Safe Learning: Hierarchical learning architectures are proposed to ensure safe control policies even when the robot's environment or internal dynamics are not fully characterized beforehand.
  • Bio-Inspired Swarms: Drawing inspiration from biological processes like chemotaxis (the movement of cells in response to chemical signals), researchers have developed algorithms to coordinate robot swarms without centralized control.
  • Confined Space Mapping: For robots operating in tunnels or indoor environments where GPS and compasses fail, a new LiDAR-based SLAM (Simultaneous Localization and Mapping) framework provides high-precision localization.

Conclusion and Future Outlook

The 12 papers in this special issue collectively demonstrate that the future of automation lies in its ability to handle uncertainty through analytics. Key takeaways include the importance of bio-inspired design, the necessity of robust control in unknown environments, and the growing role of open-access simulators in accelerating research.

As the field moves forward, the guest editors emphasize the need for scalable multi-agent systems and the deeper integration of real-time analytics into industrial applications. The success of the virtual CASE2020 conference also points toward a future where remote collaboration and digital validation tools are central to the automation research community.

Summary updated

Abstract

We are pleased to present this Special Issue of TASE, including 12 extended articles selected from the technical program of the 2020 International Conference on Automation Science and Engineering (CASE2020). CASE2020 was held virtually due to the COVID19 pandemics, August 20–21, 2020, and was originally scheduled in Hong Kong, China. CASE is an offspring of TASE and is the flagship automation conference of the IEEE Robotics and Automation Society, constituting the primary forum for cross-industry and multidisciplinary research in automation. The 2020 CASE theme was Automation Analytics, a global challenge emphasized at the conference by several invited and regular sessions, as well as specific workshops.
BibTeX
@inproceedings{dotoli2022special,
  author = {Mariagrazia Dotoli and Weiming Shen and Qing-Shan Jia and Ray Y. Zhong},
  title = {{Special Issue on the 2020 International Conference on Automation Science and Engineering}},
  booktitle = {IEEE Trans Autom. Sci. Eng},
  year = {2022},
  url = {https://openreview.net/forum?id=QyCg8a6uxeV},
}
Figure