Chance-Constrained Iterative Linear-Quadratic Stochastic Games

Dynamic game arises as a powerful paradigm for multi-robot planning, for which safety constraint satisfaction is crucial. Constrained stochastic games are of particular interest, as real-world robots need to operate and satisfy constraints under uncertainty. Existing methods for solving stochastic games handle chance constraints using exponential penalties with hand- tuned weights. However, finding a suitable penalty weight is nontrivial and requires trial and error. In this letter, we pro- pose the chance-constrained iterative linear-quadratic stochastic games (CCILQGames) algorithm. CCILQGames solves chance- constrained stochastic games using the augmented Lagrangian method. We evaluate our algorithm in three autonomous driving scenarios, including merge, intersection, and roundabout. Exper- imental results and Monte Carlo tests show that CCILQGames can generate safe and interactive strategies in stochastic environ- ments.