Factorization of Dynamic Games over Spatio-Temporal Resources

Abstract

Dynamic games feature a state-space complexity that scales superlinearly with the number of players. This makes this class of games often intractable even for a handful of players. We introduce the factorization process of dynamic games as a transformation leveraging the independence of players at equilibrium to build a leaner game graph. When applicable, it yields fewer nodes, fewer players per game node, hence much faster solutions. While for the general case checking for independence of players requires to solve the game itself, we observe that for dynamic games in the robotic domain there exist exact heuristics based on the spatio-temporal occupancy of the individual players. We validate our findings in realistic autonomous driving scenarios showing that already for a 4player intersection we have a reduction of game nodes and solving time close to 99%.

Automatic Traffic Scenario Conversion from OpenSCENARIO to CommonRoad

“…For instance, safe, ethical, and robust motion planning algorithms are benchmarked using CommonRoad scenarios in [21]- [24]. The authors in [25]- [27] utilize CommonRoad tools to demonstrate the game-theoretic aspects of autonomous vehicles. Furthermore, CommonRoad paves the way to use advanced algorithms to facilitate motion planning, such as reinforcement learning [28], [29] and geometric deep learning [30].…”

Hierarchical and Game-Theoretic Decision-Making for Connected and Automated Vehicles in Overtaking Scenarios

“…In decision-making for autonomous mobile robots in environments consisting of many agents, modeling the interactions between the ego agent and surrounding agents is one of the most fundamental while challenging problems [1]- [3]. In such a case, the reward (as a measure of performance) received by each agent depends not only on the agent's own actions but also on the actions of others nearby [4].…”

“…(sbae@honda-ri.com) 3 Nan Li is with the Department of Aerospace Engineering, Auburn University, AL, USA (nzl0058@auburn.edu) aggressive chaser who has been dedicated to an overtaking maneuver and coming up from behind fast, an overtakingblocking behavior can be dangerous and result in a collision. Therefore, a prediction of the opponent's future trajectory is useful in order to react optimally [9].…”