top of page

Systems Engineering

Autonomous Systems

Online Machine Learning and Resilience of Autonomous Systems

  • Develop online machine learning techniques for enhanced intelligence, anomaly mitigation, and resilience of autonomous systems

  • Challenges:

    • Mining PNT information from images
      (visual-servoing)

    • Real-time edge computing (computer 
      visualization & control reconfiguration)

OMLC.png
turtlebot1.png
turtlebot2.jpg
turtlebot3.jpg
robot_on_track.gif
robot_positioning.gif

Cyber-security of Manufacturing Systems

  • Develop a unified framework based on the deep learning for real-time health and security monitoring and diagnosis of manufacturing systems

  • Challenges:

    • Limited data of cyber-attack

    • Minimal data labelling/annotation

    • “Around-the-clock” monitoring

dae_energy_auditing.png
manufacturing_all_stations.png
all_sensor_readings.png
energy_auditing_detection_results.png

Leader-Follower Formation Control

  • Develop robust autonomous systems based on
    visual-servoing and intelligent control for
    leader-follower formation control

  • Challenges:

    • Mining PNT information from images
      (visual-servoing)

    • Real-time edge computing

    • Obstacle learning, avoidance, path planning
      and control

leader-follower_overall.png

Publications:

Hong, S. H., Cornelius, J., Wang, Y., & Pant, K. (2019). Fault compensation by online updating of genetic algorithm-selected neural network model for model predictive control. SN Applied Sciences, 1(11), 1488.

Hong, S. H., Cornelius, J., Wang, Y., & Pant, K. (2020). Online Machine Learning Model Compensator for Model Predictive Control and Anomaly Mitigation of Mechanical Systems. In AIAA Scitech 2020 Forum (p. 2251).

S.H. Hong, J. Cornelius, Y. Wang*, K. Pant, "Optimized Artificial Neural Network Model and Compensator in Model Predictive Control for Anomaly Mitigation", Journal of Dynamic Systems, Measurement and Control, https://doi.org/10.1115/1.4049130​

bottom of page