Human-like decision making for autonomous lane change driving: a hybrid inverse reinforcement learning with game-theoretical vehicle interaction model

The development of automated driving vehicles aims to provide safer, comfortable, and more efficient mobility options. However, the decision-making control of autonomous vehicles still faces limitations of human performance mimicry. These limitations become particularly evident in complex and unfamiliar driving scenarios, where weak decision-making abilities and poor adaptation of vehicle behaviour are prominent issues. This paper proposes a game-theoretic decision-making algorithm for human-like driving in the vehicle lane change scenario. Firstly, an inverse reinforcement learning (IRL) model is used to quantitatively analyze the lane change trajectories of the natural driving dataset, establishing the human-like human cost function. Subsequently, joint safety, and comfort to build the comprehensive decision cost function. The combined decision cost function is used to conduct a noncooperative game of vehicle lane changing decisions to solve the optimal decision of host vehicle lane changing. The host vehicle lane-changing decision problem is formulated as a Stackelberg game optimization problem. To verify the feasibility and effectiveness of the algorithm proposed in this study, a lane change test scenario was established. Firstly, we analyze the human-like decision-making model derived from the maximum entropy inverse reinforcement learning algorithm to verify the effectiveness and robustness of the IRL algorithm. Secondly, the human-like game decision-making algorithm in this paper is validated by conducting an interactive lane-changing experiment with obstacle vehicles of different driving styles. The experimental results prove that the human-like driving decision-making model proposed in this study can make lane-changing behaviours in line with human driving patterns in lane-changing scenarios of the expressway.

---

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).