Dr Paul Anandan

Doctor of Philosophy (PhD)

  • Research Associate in Contextual Robot Programming

Paul achieved his Bachelor of Engineering in Electronics and Instrumentation from Anna University, India in 2008 and was awarded a Master’s degree in Mechanical and Manufacturing Engineering at the University of Greenwich, UK in 2010. He joined Loughborough University to study for his PhD in August 2014. His research was focused on reliability-based reusability of modular assembly equipment while designing new production lines.

Paul has worked as a Research Associate in Artificial Intelligence for Plant-Wide Control in the Department of Chemical Engineering, Loughborough University. He investigated the use of reinforcement learning as an alternative to replace the traditional PID and Model Predictive Controllers (MPC) for controlling crystallisation processes. Additionally, he has investigated the usefulness of combining state estimation techniques (Kalman Filtering) with reinforcement learning to deal with measurement noise and other random model uncertainties. This research work is funded by EPSRC (REF: EP/R032858/1).

In his current research, Paul is focusing on automatic program generation for robotic cells in response to the dynamic changes in the production requirements. The scope of this work includes multi-sensor inputs for perception, and also for automatic constraint generation to ensure safety and efficient process execution. This research work is funded by EPSRC (REF: EP/V051180/1).

Main research areas

  • Robotics
  • Machine Learning
  • Optimisation and Control
  • Cyber Physical Systems
  • Modular Assembly Systems

Current research activity

  • EPSRC R3M: Reconfigurable Robots for Responsive Manufacturing

Past research activity

  • openMOS
  • ReBorn
  • P. Danny, C. D. Rielly, B. Benyahia, “Optimal control policies of a crystallization process using inverse reinforcement learning”, 32nd European Symposium on Computer Aided Process Engineering (ESCAPE) 2022.
  • B. Benyahia, P. Danny, C. D. Rielly, “Robust Model-Based Reinforcement Learning Control of a Batch Crystallization Process”, 9th International Conference on Systems and Control (ICSC) 2021, 89-94.
  • B. Benyahia, P. Danny, C. D. Rielly, “Control of Batch and Continuous Crystallization Processes using Reinforcement Learning”, 31st European Symposium on Computer Aided Process Engineering (ESCAPE) 2021.
  • P. Danny, C. D. Rielly, B. Benyahia, “Optimal trajectory tracking control of batch crystallization process based on reinforcement learning”, The 2nd International Online Conference on Crystals, session – Crystal Engineering 2020.
  • M. Zimmer, P. Ferreira, P. Danny, A. Yacoub, N. Lohse, “Towards a Decision Support Framework for Reducing Ramp-up Effort in Plug-and-Produce Systems,” 3rd IEEE International Conference on Industrial Cyber Physical Systems (ICPS) 2019.
  • P. Ferreira, P. Danny, I. Pereira, V. Hiwarkar, M. Sayed, N. Lohse, S. Aguiar, G. Goncalves, J. Goncalves, F. Bottinger, “Integrated Design Environment for Reusable Modular Assembly Systems (RMAS),” Assembly Automation, 2019.
  • P. Danny, P. Ferreira, k. Dorofeev, N. Lohse, “An Event-Based AutomationML Model for the Process Execution of ‘Plug-and-Produce’ Assembly Systems,” 16th IEEE International Conference on Industrial Informatics (INDIN) 2018.
  • P. Danny, P. Ferreira, M. Guedes, N. Lohse, “An AutomationML Model for Plug-and-Produce Assembly Systems,” 15th IEEE International Conference on Industrial Informatics (INDIN) 2017.
  • P. Danny, V. Hiwarkar, M. Sayed, P. Ferreira, N. Lohse, “Linear Constraint Programming for Cost-Optimised Configuration of Modular Assembly Systems,” 49th CIRP CMS, 2016.

External collaborators 

  • Cranfield University
  • University of Sheffield
  • Advanced Manufacturing Research Centre (AMRC), Sheffield
  • Airbus Group Ltd
  • BAE Systems
  • Cosworth Racing Ltd
  • Loop Technology Ltd