Homogeneous charge compression ignition (HCCI) combustion, also known as controlled autoignition (CAI) combustion, has been realized over a range of engine speed and load conditions in a single cylinder four-stroke gasoline engine equipped with a 4VVAS mechanical variable intake and exhaust valve lift and timing devices system. The engine has the capability to operate either in the spark ignition (SI) or HCCI combustion in order to cover the complete engine operational range. Therefore, smooth switching between SI and HCCI modes is required. In this work, a systematic investigation has been carried out to study the transition between the conventional spark ignition combustion and HCCI combustion and develop the control strategies for optimized mode switch. Results show that dynamic transitions between HCCI and SI can be stably achieved around the boundaries of HCCI operation region through the rapid and effective control of the in-cylinder residual gas concentration by a Four Variable Valve Actuation System (4VVAS). It is found that switching from HCCI to SI operation is less problematic than that from SI to HCCI combustion operation, and certain regions of residual concentrations should be avoided. During the switching process, the spark timing and exhaust valve closing timing have the largest effect and can be optimized for mode switching. Two major approaches have been developed and applied to controlling the HCCI-SI transitions, through the dynamic management of residual gas and the management of hybrid heat release processes.

The path tracking control system is a crucial component for autonomous vehicles; it is challenging to realize accurate tracking control when approaching a wide range of uncertain situations and dynamic environments, particularly when such control must perform as well as, or better than, human drivers. While many methods provide state-of-the-art tracking performance, they tend to emphasize constant PID control parameters, calibrated by human experience, to improve tracking accuracy. A detailed analysis shows that PID controllers inefficiently reduce the lateral error under various conditions, such as complex trajectories and variable speed. In addition, intelligent driving vehicles are highly non-linear objects, and high-fidelity models are unavailable in most autonomous systems. As for the model-based controller (MPC or LQR), the complex modeling process may increase the computational burden. With that in mind, a self-optimizing, path tracking controller structure, based on reinforcement learning, is proposed. For the lateral control of the vehicle, a steering method based on the fusion of the reinforcement learning and traditional PID controllers is designed to adapt to various tracking scenarios. According to the pre-defined path geometry and the real-time status of the vehicle, the interactive learning mechanism, based on an RL framework (actor–critic—a symmetric network structure), can realize the online optimization of PID control parameters in order to better deal with the tracking error under complex trajectories and dynamic changes of vehicle model parameters. The adaptive performance of velocity changes was also considered in the tracking process. The proposed controlling approach was tested in different path tracking scenarios, both the driving simulator platforms and on-site vehicle experiments have verified the effects of our proposed self-optimizing controller. The results show that the approach can adaptively change the weights of PID to maintain a tracking error (simulation: within ±0.071 m; realistic vehicle: within ±0.272 m) and steering wheel vibration standard deviations (simulation: within ±0.04°; realistic vehicle: within ±80.69°); additionally, it can adapt to high-speed simulation scenarios (the maximum speed is above 100 km/h and the average speed through curves is 63–76 km/h).

In this brief, a novel decoupling solution is proposed for the variable-geometry turbine (VGT) and exhaust gas recirculation (EGR) system of diesel engines based on the principle of active disturbance rejection control. This complex, double-input, double-output, VGT-EGR system is treated as two ideal, decoupled integrators for the purpose of control design, while all other dynamics that deviate from the ideal model, including cross coupling and dynamic variations due to operating point changes, and all other uncertainties are treated as the total disturbance to be estimated and canceled. Since the estimation of the total disturbance is bandwidth limited in the VGT-EGR system, feedforward controllers, one static and one dynamic, are used to speed up the response. The proposed controller is simple to implement, easy to tune, and able to handle a wide range of uncertainties without retuning or gain-scheduling. Its effectiveness has been validated in simulation, experimental tests, as well as in mathematical analysis, proving the inverse relationship between the tracking error and the controller bandwidth.

Driving assistance systems (DAS) is a key technology to improve fuel economy for in-use vehicles. This also reduces the operational cost of running a fleet of these vehicles, such as city buses. In this paper, we develop a novel white-box evaluation model using machine learning for a manual transmission bus based on previous research about fuel consumption sensitivity to driving style. Using the proposed evaluation model, an algorithm for learning path planning (LPP) for a driving style is also proposed. The LPP method plans a step-by-step shortest learning path for different driving styles to achieve eco-driving, while increasing the driver's acceptance and adaptation of DAS. Simulation results based on vehicle and engine physical models show that the proposed evaluation model, a pure data model, can be used as an alternative to physical model for the eco-driving prompt strategy. The results of the verification show that the proposed strategy can progressively guide the driver to improve the fuel consumption by 6.25% with minimal changes to driver's driving task and driving style.

A key research area in autonomous driving is how to model the driver’s decision-making behavior, due to the fact it is significant for a self-driving vehicles considering their traffic safety and efficiency. However, the uncertain characteristics of vehicle and pedestrian trajectories affect urban roads, which poses severe challenges to the cognitive understanding and decision-making of autonomous vehicle systems in terms of accuracy and robustness. To overcome the abovementioned problems, this paper proposes a Bayesian driver agent (BDA) model which is a vision-based autonomous vehicle system with learning and inference methods inspired by human driver’s cognitive psychology. Different from the end-to-end learning method and traditional rule-based methods, our approach breaks the driving system up into a scene recognition module and a decision inference module. The perception module, which is based on a multi-task learning neural network (CNN), takes a driver’s-view image as its input and predicts the traffic scene’s feature values. The decision module based on dynamic Bayesian network (DBN) then makes an inferred decision using the traffic scene’s feature values. To explore the validity of the Bayesian driver agent model, we performed experiments on a driving simulation platform. The BDA model can extract the scene feature values effectively and predict the probability distribution of the human driver’s decision-making process accurately based on inference. We take the lane changing scenario as an example to verify the model, the intraclass correlation coefficient (ICC) correlation between the BDA model and human driver’s decision process reached 0.984. This work suggests a research in scene perception and autonomous decision-making that may apply to autonomous vehicle system.