Non-zero-sum Game Control for Multi-vehicle Driving via Reinforcement Learning
This addresses interactive decision-making in autonomous driving for vehicles at non-signalized intersections, representing an incremental improvement by applying game theory to a known bottleneck.
The paper tackled multi-vehicle driving by modeling it as a non-zero-sum game, integrating prediction, decision, and control into a single framework, and achieved perfect driving performance with direct control of acceleration and steering in experiments.
When a vehicle drives on the road, its behaviors will be affected by surrounding vehicles. Prediction and decision should not be considered as two separate stages because all vehicles make decisions interactively. This paper constructs the multi-vehicle driving scenario as a non-zero-sum game and proposes a novel game control framework, which consider prediction, decision and control as a whole. The mutual influence of interactions between vehicles is considered in this framework because decisions are made by Nash equilibrium strategy. To efficiently obtain the strategy, ADP, a model-based reinforcement learning method, is used to solve coupled Hamilton-Jacobi-Bellman equations. Driving performance is evaluated by tracking, efficiency, safety and comfort indices. Experiments show that our algorithm could drive perfectly by directly controlling acceleration and steering angle. Vehicles could learn interactive behaviors such as overtaking and pass. In summary, we propose a non-zero-sum game framework for modeling multi-vehicle driving, provide an effective way to solve the Nash equilibrium driving strategy, and validate at non-signalized intersections.