The inflexible human-autonomy relationship within autonomous driving scenarios still has not realized synergetic intelligence, therefore unable to provide adaptive and context-sensitive decision-making and sometimes leading to violation of human pReferences or even hazards. In this paper, we utilize functional near-infrared spectroscopy (fNIRS) signals as real-time human risk-perception feedback to establish a brain-in-the-loop (BiTL) trained artificial intelligence algorithm for decision-making. The proposed algorithm uses the result of driving risk reasoning as one input of reinforcement learning combining fNIRS-based risk and driving safety field model-based risk, realizing integrating human brain activity into the reinforcement learning scheme, then overcoming the disadvantage of machine-oriented intelligence that could violate human intentions. To achieve policy learning within limited BiTL training periods, we add two modification features to the proposed algorithm based on TD3. The experiment involving twenty participants has been conducted, and the results show that in continuously high-risk driving scenarios, compared to traditional reinforcement learning algorithms without human participation, the proposed algorithm can maintain a cautious driving policy and avoid potential collisions, validated with both proximal surrogate indicators and success rates.

In this paper, a learning based Model Predictive Control (MPC) using a low dimensional residual model is proposed for autonomous driving. One of the critical challenge in autonomous driving is the complexity of vehicle dynamics, which impedes the formulation of accurate vehicle model. Inaccurate vehicle model can significantly impact the performance of MPC controller. To address this issue, this paper decomposes the nominal vehicle model into invariable and variable elements. The accuracy of invariable elements are ensured by calibration, while the deviations in the variable elements are learned by a low-dimensional residual model. The features of residual model are selected as the physical variables most correlated with nominal model errors. Physical constraints among these features are formulated to explicitly define the valid region within the feature space. The formulated model and constraints are incorporated into the MPC framework and validated through both simulation and real vehicle experiments. The results indicate that the proposed method significantly enhances the model accuracy and controller performance.

Path planning and path tracking play an important role in the development of the auto drive system. Based on the advantages of Bezier Curves, such as smoothness and ease of calculation, this paper proposes a path planning method for two segment Bezier Curves, and establishes the relationship between the control points of Bezier Curves and the driving status of vehicles, so as to ensure the feasibility of the planned curves. Based on the planned path and the vehicle’s own state, a model predictive control method is adopted to develop a path tracking control algorithm. In order to fully ensure the driving stability of the vehicle tracking path, this paper developed a vehicle stability control algorithm based on model predictive control to ensure the stability of the vehicle during the path tracking process. Finally, the corresponding verification test is designed, and the test results show that the path planning and path tracking control algorithm considering stability developed in this paper have good control effects. It can not only plan the driving path according to the obstacle information and the current driving state of the vehicle, but also ensure the driving stability of the vehicle in the path tracking process, and improve the driving safety of autonomous vehicle.