Active Learning and Data Driven Control
We work on machine learning techniques that use control authority (inputs to the system) to actively learn. The inputs do not simply contribute to learning through action, the inputs are chosen to maximize the amount of learning that occurs in a given amount of time. Much of our recent work has used ergodicity as a principle of information coverage. Moreover, we have been using active learning with respect to information about unknown Koopman operators (nonparametric descriptions of dynamical systems).
People
Giorgos Mamakoukas (Ph.D. Student)
Collaborators
Brenna Argall, Northwestern University
Mitra Hartmann, Northwestern University
Publications
Active learning of dynamics for data-driven control using Koopman operators
I. Abraham and T. D. Murphey
IEEE Transactions on Robotics, 2019. PDF, Code
CPL-Sync: Efficient and guaranteed planar pose graph optimization using the complex number representation
T. Fan, H. Wang, M. Rubenstein, and T. D. Murphey
IEEE Int. Conf. on Intelligent Robots and Systems (IROS), 2019. Winner of ABB Best Student Paper Award. PDF
Local Koopman operators for data-driven control of robotic systems
G. Mamakoukas, M. Castano, X. Tan, and T. D. Murphey
Robotics: Science and Systems Proceedings, 2019. PDF
Model-based control using Koopman operators
I. Abraham, G. de la Torre, and T. Murphey
Robotics: Science and Systems Proceedings, 2017. PDF, Code
Other Projects
Active Learning and Data-Driven Control
Active Perception in Human-Swarm Collaboration
Algorithmic Matter and Emergent Computation
Control for Nonlinear and Hybrid Systems
Cyber Physical Systems in Uncertain Environments
Harmonious Navigation in Human Crowds
Information Maximizing Clinical Diagnostics
Reactive Learning in Underwater Exploration
Robot-Assisted Rehabilitation
Software-Enabled Biomedical Devices