[Back]


Talks and Poster Presentations (with Proceedings-Entry):

U. Mehmood, S. Roy, R. Grosu, S. Smolka, S. Stoller, A. Tiwari:
"Neural Flocking: MPC-based Supervised Learning of Flocking Controllers";
Talk: FoSSaCS: International Conference on Foundations of Software Science and Computation Structures, virtuell; 2020-04-25 - 2020-04-30; in: "Neural Flocking: MPC-based Supervised Learning of Flocking Controllers", Springer, . (2020), ISBN: 978-3-030-45231-5; 1 - 16.



English abstract:
We show how a symmetric and fully distributed flocking controller
can be synthesized using Deep Learning from a centralized flocking
controller. Our approach is based on Supervised Learning, with the centralized
controller providing the training data, in the form of trajectories
of state-action pairs. We use Model Predictive Control (MPC) for the centralized
controller, an approach that we have successfully demonstrated
on flocking problems. MPC-based flocking controllers are high-performing
but also computationally expensive. By learning a symmetric and distributed
neural flocking controller from a centralized MPC-based one,
we achieve the best of both worlds: the neural controllers have high
performance (on par with the MPC controllers) and high efficiency. Our
experimental results demonstrate the sophisticated nature of the distributed
controllers we learn. In particular, the neural controllers are
capable of achieving myriad flocking-oriented control objectives, including
flocking formation, collision avoidance, obstacle avoidance, predator
avoidance, and target seeking. Moreover, they generalize the behavior
seen in the training data to achieve these objectives in a significantly
broader range of scenarios. In terms of verification of our neural flocking
controller, we use a form of statistical model checking to compute
confidence intervals for its convergence rate and time to convergence.

Keywords:
Flocking · Model Predictive Control · Distributed Neural Controller · Deep Neural Network · Supervised Learning


Electronic version of the publication:
https://publik.tuwien.ac.at/files/publik_293058.pdf


Created from the Publication Database of the Vienna University of Technology.