Learning Spatiotemporal Tubes for Full Class of Signal Temporal Logic Tasks for Control of Unknown Systems under Input Constraints

2026-07-08

AI Summary

This work addresses the challenge of enforcing general Signal Temporal Logic (STL) specifications on unknown nonlinear Euler-Lagrange systems subject to input constraints. The authors propose a spatio-temporal tube (STT)-based control framework that leverages Physics-Informed Neural Networks (PINNs) to parameterize time-varying spherical tubes. The STL robustness degree is explicitly embedded into the training loss, and a closed-form control law is designed to guarantee that system trajectories remain within the tube while respecting input constraints. By innovatively integrating PINNs with STTs, the approach enables formal STL control for unknown dynamical systems and introduces a global robustness metric to prevent spatio-temporal tube conflicts in multi-agent settings. Experimental results demonstrate the method’s high-precision satisfaction of complex STL specifications in both single- and multi-agent scenarios.

Abstract

This paper presents a Spatiotemporal Tube (STT)-based control framework for general unknown nonlinear Euler-Lagrange (EL) systems subject to input constraints, with the objective of satisfying Signal Temporal Logic (STL) specifications, where confinement of the system trajectory within the STT guarantees the satisfaction of the corresponding STL task. For both single and multi-agent scenarios, the STT corresponding to each agent is modeled as a time-varying ball, whose center and radius are jointly parameterized using a physics-informed neural network (PINN). The robustness metric associated with the STL specification corresponding to the agents is incorporated into the training process as a loss function, enabling the learned tube to encode task-level temporal requirements. For a multi-agent scenario, we introduce an additional robustness metric corresponding to the global task, which, when satisfied, ensures the tubes do not collide with each other. To ensure that the system trajectory remains within the learned STT and thereby satisfies the local and global STL specifications, we propose a control strategy that explicitly accounts for input constraints. In particular, a closed-form control law is developed to keep the trajectory inside the tube while regulating the motion of the tube by enforcing bounds on its evolution depending on the input constraints of the system. The proposed approach has been validated over several case studies.

Problem

• Signal Temporal Logic
• Input Constraints
• Unknown Nonlinear Systems
• Spatiotemporal Tubes
• Multi-agent Control

Innovation

• Spatiotemporal Tube
• Signal Temporal Logic
• Physics-Informed Neural Network
• Input Constraints
• Multi-Agent Control