TR2020-116

Data-Driven Optimal Tracking with Constrained Approximate Dynamic Programming for Servomotor Systems


    •  Chakrabarty, A., Danielson, C., Wang, Y., "Data-Driven Optimal Tracking with Constrained Approximate Dynamic Programming for Servomotor Systems", IEEE Conference on Control Technology and Applications, DOI: 10.1109/​CCTA41146.2020.9206315, August 2020, pp. 352-357.
      BibTeX TR2020-116 PDF
      • @inproceedings{Chakrabarty2020aug,
      • author = {Chakrabarty, Ankush and Danielson, Claus and Wang, Yebin},
      • title = {Data-Driven Optimal Tracking with Constrained Approximate Dynamic Programming for Servomotor Systems},
      • booktitle = {IEEE Conference on Control Technology and Applications},
      • year = 2020,
      • pages = {352--357},
      • month = aug,
      • publisher = {IEEE},
      • doi = {10.1109/CCTA41146.2020.9206315},
      • url = {https://www.merl.com/publications/TR2020-116}
      • }
  • MERL Contacts:
  • Research Areas:

    Control, Machine Learning, Optimization

Abstract:

We design real-time optimal tracking controllers for servomotor systems engaged in single-axis point-to-point positioning tasks. The design is challenging due to the presence of unmodeled dynamics, along with speed and acceleration constraints. As model-based optimal control design methods cannot be applied directly to this uncertain system, we propose a data-driven approximate dynamic programming approach to learn an optimal tracking controller that is constraint-enforcing. The potential of our proposed method is illustrated on a servomotor that positions the head of a laser drilling machine.

 

  • Related News & Events