Context-Triggered Contingency Games for Strategic Multi-Agent Interaction
Kilian Schweppe, Anne-Kathrin Schmuck
TL;DR
The paper tackles reliable multi-agent interaction by integrating high-level strategic planning with low-level dynamic contingency reasoning in a context-triggered framework. It introduces strategy templates to capture reusable, winning strategies from LTL-based strategic games and pairs them with context-dependent contingency games solved in real time via a novel Dynamic Game Factor Graph (DG-FG) solver, enabling real-time MPC. The approach is validated in autonomous driving and robot navigation scenarios, showing safe, proactive, and efficient behavior with significant improvements in solving speed and scalability over existing solvers. This work provides a practical, real-time framework for combining long-horizon strategic objectives with short-horizon reactive adaptation in uncertain, interactive environments.
Abstract
We address the challenge of reliable and efficient interaction in autonomous multi-agent systems, where agents must balance long-term strategic objectives with short-term dynamic adaptation. We propose context-triggered contingency games, a novel integration of strategic games derived from temporal logic specifications with dynamic contingency games solved in real time. Our two-layered architecture leverages strategy templates to guarantee satisfaction of high-level objectives, while a new factor-graph-based solver enables scalable, real-time model predictive control of dynamic interactions. The resulting framework ensures both safety and progress in uncertain, interactive environments. We validate our approach through simulations and hardware experiments in autonomous driving and robotic navigation, demonstrating efficient, reliable, and adaptive multi-agent interaction.