A physics-informed neural network learns time-varying safe tubes encoding full STL specifications, and a closed-form controller confines unknown Euler-Lagrange systems within them under input constraints.
Lipschitz Continuity of Signal Temporal Logic Robustness Measures: Synthesizing Control Barrier Functions from One Expert Demonstration
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Control Barrier Functions (CBFs) allow for efficient synthesis of controllers to maintain desired invariant properties of safety-critical systems. However, the problem of identifying a CBF remains an open question. As such, this paper provides a constructive method for control barrier function synthesis around one expert demonstration that realizes a desired system specification formalized in Signal Temporal Logic (STL). First, we prove that all STL specifications have Lipschitz-continuous robustness measures. Second, we leverage this Lipschitz continuity to synthesize a time-varying control barrier function. By filtering control inputs to maintain the positivity of this function, we ensure that the system trajectory satisfies the desired STL specification. Finally, we demonstrate the effectiveness of our approach on the Robotarium.
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Spatiotemporal Tubes for Full Class of Signal Temporal Logic Tasks for Control of Unknown Systems under Input Constraints
A physics-informed neural network learns time-varying safe tubes encoding full STL specifications, and a closed-form controller confines unknown Euler-Lagrange systems within them under input constraints.