This paper derives a class of gradient controllers with conditional robustness guarantees for signal temporal logic tasks, extends them to unicycle dynamics by adding an auxiliary non-degeneracy task, and demonstrates a heuristic controller-combination scheme in simulation.
A policy search method for temp oral logic specified reinforcement learning tasks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.SY 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Gradient-Based STL Control with Application to Nonholonomic Systems
This paper derives a class of gradient controllers with conditional robustness guarantees for signal temporal logic tasks, extends them to unicycle dynamics by adding an auxiliary non-degeneracy task, and demonstrates a heuristic controller-combination scheme in simulation.