Neural Network-based Control for Multi-Agent Systems from Spatio-Temporal Specifications
This work addresses real-time control challenges for multi-agent systems like robotic teams, but it is incremental as it builds on existing logic and optimization methods.
The paper tackles control synthesis for multi-agent systems to satisfy spatio-temporal specifications by proposing a framework that maps specifications to optimization problems and trains a neural network for real-time control, demonstrating effectiveness on a robotic team model with communication constraints.
We propose a framework for solving control synthesis problems for multi-agent networked systems required to satisfy spatio-temporal specifications. We use Spatio-Temporal Reach and Escape Logic (STREL) as a specification language. For this logic, we define smooth quantitative semantics, which captures the degree of satisfaction of a formula by a multi-agent team. We use the novel quantitative semantics to map control synthesis problems with STREL specifications to optimization problems and propose a combination of heuristic and gradient-based methods to solve such problems. As this method might not meet the requirements of a real-time implementation, we develop a machine learning technique that uses the results of the off-line optimizations to train a neural network that gives the control inputs at current states. We illustrate the effectiveness of the proposed framework by applying it to a model of a robotic team required to satisfy a spatial-temporal specification under communication constraints.