Workshop on Machine Learning for Automation

This workshop on Machine Learning for Automation (MLA) provides a unique opportunity to explore the cutting edge research and practice on how machine learning is transforming automation, and vice versa. How is ML transforming semiconductor manufacturing? Accelerating the design of next-generation batteries? Making buildings smarter? Achieving safe, green, and inclusive mobility in cities? Evolving automatic virtual metrology? And how to advance fundamental theories and algorithms in MLA practice, such as solving mixed-binary linear programming problems, combining constrained programming and satisfiability solvers, improving data efficiency and robustness, and making AI models explainable? What are the options in commercial software such as Matlab and Simulink for MLA? We provide 10 exciting talks from leading experts to address these questions. Beyond that, a poster session, a demo session, and a panel session would provide great hands-on experience and opportunities to interact with the experts in MLA. This will be a memorable full day workshop for the participants. This workshop is organized by the IEEE RAS TC on MLA, with support from TC on Logistics, TC on Semiconductor Manufacturing, TC on Smart Buildings, and TC on Digital Manufacturing and Human Machine Interaction.

Program

  • 08:30 Arrival and registration
  • 09:00 Introduction
  • 09:10 Mengchu Zhou (New Jersey Institute of Technology) “Machine Learning Approaches to Transforming Semiconductor Manufacturing Industry from Automation to Intelligenization”
  • 09:40 Benben Jiang (Tsinghua University) “Computational Energy: How Machine Learning Accelerates the Design of Lithium-ion Battery”
  • 10:10 Yu Yang (Xi’an Jiaotong University) “Distributed Nonconvex Optimization with Guaranteed Convergence for Smart and Automated Buildings”
  • 10:40 Bing Yan (Rochester Institute of Technology) “A Systematic Formulation Tightening Approach for Mixed-Binary Linear Programming Problems”
  • 11:10 Maria Pia Fanti (Polytechnic University of Bari) “Machine learning and deep reinforcement learning applied to cooperative, connected and automated vehicles”
  • 11:40 Poster session
  • 12:10 Lunch
  • 13:00 Bengt Lennartson (Chalmers University of Technology) “A New Data-Efficient and Robust Reinforcement Learning Strategy Applied to Eco-Driving”
  • 13:30 Aparna Varde (Montclair State University) “Deep Learning with Explainable AI Models in Robot Training, Autonomous Driving & Drone Data Analytics”
  • 14:00 Fan-Tien Cheng (National Cheng Kung University) “Evolution of Automatic Virtual Metrology (AVM) Generations”
  • 14:30 Afternoon tea [to be determined according to the conference arrangement]
  • 15:00 Roberto G. Valenti (MathWorks) “Machine learning with MATLAB and Simulink for next generation manufacturing automation”
  • 15:30 Michel A. Reniers (Eindhoven University of Technology) “Simulation-Based Optimization of A Production System Topology – A Neural Network-Assisted Genetic Algorithm”
  • 16:00 Demon Session by Yuqian Lu (University of Auckland), “Human-centric Assembly Quality Tracking and Assistance System”
  • 16:30 Panel discussion 
  • 17:30 Closing time

Organizers

  • (Samuel) Qing-Shan Jia | Professor, Tsinghua University, Beijing (China) | Email: jiaqs@tsinghua.edu.cn
  • Bing Yan | Assistant Professor, Rochester Institute of Technology (USA) | Email: bxyeee@rit.edu
  • Aparna Varde | Associate Professor, Montclair State University (USA) | Email: vardea@montclair.edu
  • Bengt Lennartson | Professor, Chalmers University of Technology (Sweden) | Email: bengt.lennartson@chalmers.se
  • Maria Pia Fanti | Professor, Polytechnic of Bari (Italy) | Email: mariapia.fanti@poliba.it
Scroll to Top