Search Results

Roundabouts are one of the most complex traffic environments in urban roads, and a key challenge for intelligent driving decision-making. Deep reinforcement learning, as an emerging solution for intelligent driving decisions, has the advantage of avoiding complex algorithm design and sustainable iteration. For the decision difficulty in roundabout scenarios, this paper proposes an artificial potential field based Soft Actor-Critic (APF-SAC) algorithm. Firstly, based on the Carla simulator and Gym framework, a reinforcement learning simulation system for roundabout driving is built. Secondly, to reduce reinforcement learning exploration difficulty, global path planning and path smoothing algorithms are designed to generate and optimize the path to guide the agent.

Autonomous driving technology is more and more important nowadays, it has been changing the living style of our society. As for autonomous driving planning and control, vehicle dynamics has strong nonlinearity and uncertainty, so vehicle dynamics and control is one of the most challenging parts. At present, many kinds of specific vehicle dynamics models have been proposed, this review attempts to give an overview of the state of the art of vehicle dynamics models for autonomous driving. Firstly, this review starts from the simple geometric model, vehicle kinematics model, dynamic bicycle model, double-track vehicle model and multi degree of freedom (DOF) dynamics model, and discusses the specific use of these classical models for autonomous driving state estimation, trajectory prediction, motion planning, motion control and so on.

Internal combustion engines, as the dominant power source in the transportation sector and the primary contributor to carbon emissions, face both significant challenges and opportunities in the context of achieving carbon neutral goal. Biofuels, such as biodiesel produced from biomass, and zero-carbon fuel ammonia, can serve as alternative fuels for achieving cleaner combustion in internal combustion engines. The dual-fuel combustion of ammonia-biodiesel not only effectively reduces carbon emissions but also exhibits promising combustion performance, offering a favorable avenue for future applications. However, challenges arise in the form of unburned ammonia (NH3) and N2O emissions. This study, based on a ammonia-biodiesel duel-fuel engine modified from a heavy-duty diesel engine, delves into the impact of adjustments in the two-stage injection strategy on the combustion and emission characteristics.

Ammonia is employed as the carbon-free fuel in the future engine, which is consistent with the requirements of the current national dual-carbon policy. However, the great amount of NOx and unburned NH3/H2 in the exhaust emissions is produced from combustion of ammonia and is one kind of the most strictly controlled pollutants in the emission regulation. This paper aims to investigate the NOx and unburned NH3/H2 generative process and emission characteristics by CFD simulation during the engine combustion. The results show that the unburned ammonia and hydrogen emissions increase with an increase of equivalence ratio and hydrogen blending ratio. In contrast, the emission concentrations of NOx, NO, and NO2 decrease with the increasing of equivalence ratio, but increase with hydrogen blending ratio rising. The emission concentration of N2O is highly sensitive to the O/H group and temperature, and it is precisely opposite to that of NO and NO2.

A multiple-injection combustion strategy has been developed for heated gasoline direct injection compression ignition (HGCI). Gasoline was injected into a 0.4L single cylinder engine at a fuel pressure of 300bar. Fuel temperature was increased from 25degC to a temperature of 280degC by means of electric injector heater. This approach has the potential of improving fuel efficiency, reducing harmful CO and UHC as well as particulate emissions, and reducing pressure rise rates. Moreover, the approach has the potential of reducing fuel system cost compared to high pressure (>500bar) gasoline direct injection fuel systems available in the market for GDI SI engines that are used to reduce particulate matter. In this study, a multiple injection strategy was developed using electric heating of the fuel prior to direct fuel injection at engine speed of 1500rpm and load of 12.3bar IMEP.

Driving assistance system is regarded as an effective method to improve driving safety and comfort and is widely used in automobiles. However, due to the different driving styles of different drivers, their acceptance and comfort of driving assistance systems are also different, which greatly affects the driving experience. The key to solving the problem is to let the system understand the driving style and achieve humanization or personalization. This paper focuses on clustering and identification of different driving styles. In this paper, based on the driver's real vehicle experiment, a driving data acquisition platform was built, meanwhile driving conditions were set and drivers were recruited to collect driving information. In order to facilitate the identification of driving style, the correlation analysis of driving features is conducted and the principal component analysis method is used to reduce the dimension of driving features.

In order to improve the ignition capacity and burning rate for spark-ignited engines, pre-chamber jet ignition is a promising technique to achieve fast premixed combustion and low pollutant emissions. However, few studies focus on the interaction between multiple reacting (i.e. flamelet) or reacted (i.e. radical) jets, its effect on ignition, exotherm and flow behaviors also remain to be revealed. This paper investigated two types of jet interaction under different pre-chamber structures, including the jet-crossing and unequal nozzle designs. Optical experiments under different conditions were conducted in a constant volume combustion chamber with CH4 as fuel, using simultaneous high speed schlieren and OH* chemiluminescence method. Meanwhile, computational fluid dynamics (CFD) simulations with CH4 and NH3/CH4 blend fuels were carried out using Converge software to provide further insights of turbulent flow and ignition process.

This work presents a multi-objective adaptive cruise control (ACC) system via deep reinforcement learning (DRL). During the control period, it quantitatively considers three indexes: tracking accuracy, riding comfort, and fuel economy. The system balances contradictions between different indexes to achieve the best overall control results. First, a hierarchical control architecture is utilized, where the upper level controller is synthesized under DRL framework to give out the vehicle desired acceleration. The lower level controller executes the command and compensates vehicle dynamics. Then, four state variables that can comprehensively determine the car-following states are selected for better convergence. Multi-objective reward function is quantitatively designed referring to the evaluation indexes, in which safety constraints are considered by adding violation penalty. Thereafter, the training environment which excludes the disturbance of preceding car acceleration is built.

High speed on-off valves (HSVs) are widely used in advanced hydraulic braking actuators, including regenerative braking systems and active safety systems, which take crucial part in improving the energy efficiency and safety performance of vehicles. As a component involving multiple physical fields, the HSV is affected by the interaction of the fields-fluid, electromagnetic, and mechanical. Since the opening of the HSV is small and the flow speed is high, cavitation and vortex are inevitably brought out so that increase the valve’s noise and instability. However, it is costly and complex to observe the flow status by visual fluid experiments. Hence, in this article a visual multi-physics system simulation model of the HSV is explored, in which the flow field model of the HSV built by computational fluid dynamic (CFD) is co-simulated with the model of hydraulic actuator established by AMESim.

According to the statistics of National Highway Traffic Safety Administration, driver’s cognitive distraction, which is usually caused by drivers using mobile phones, has become one of the main causes of traffic accidents. To solve this problem and guarantee the safety of man-vehicle-road system, the most critical work is to improve the accuracy of driver’s cognitive state detection. In this paper, a novel driver’s cognitive state detecting method based on LightGBM (Light Gradient Boosting Machine) is proposed. Firstly, cognitive distraction experiments of making calls are carried out on a driving simulator to collect vehicle states, eye tracking and EEG (electron encephalogram) data simultaneously and feature extraction is conducted. Then a classifier considering road and individual characteristics used for detecting cognitive states is trained based on LightGBM algorithm, with 3 predefined cognitive states including concentration, ordinary distraction and extreme distraction.

It’s hard to achieve complete self-driving using hand-crafting generalized decision-making rules, while the end-to-end self-driving system is low in complexity, does not require hand-crafting rules, and can deal with complex situations. Modular-based self-driving systems require multi-task fusion and high-precision maps, resulting in high system complexity and increased costs. In end-to-end self-driving, we usually only use camera to obtain scene status information, so image processing is very important. Numerous deep learning applications benefit from multi-task learning, as the multi-task learning can accelerate model training and improve accuracy with combine all tasks into one model, which reduces the amount of calculation and allows these systems to run in real-time. Therefore, the approach of obtaining rich scene state information based on multi-task learning is very attractive. In this paper, we propose an approach to multi-task learning for semantics, geometry and motion.

Active control of low-frequency engine order noise helps to improve the passenger’s sense of hearing, so it has become one of the hot topics in the automotive field. Depth improvement of active noise control (ANC) performance from the perspective of novel algorithms has attracted the attention of researchers. The conventional notch dual-channel filtered-x least mean square (NDFxLMS) algorithm shows acceptable noise reduction for the elimination of engine order noise. To further enhance the steady-state ANC effect, this paper proposed two new notch algorithms: the notch dual-channel filtered-x recursive least square (NDFxRLS) algorithm and the notch dual-channel affine projection (NDAP) algorithm. Vehicle simulation tests show that both the proposed algorithms, especially the NDFxRLS algorithm, have a satisfying performance for the cancellation of interior noise from the engine.

Due to the rapid development of road infrastructure and vehicle population in China, the fuel consumption and emission of on-road vehicles tested in China World Transient Vehicle Cycle (C-WTVC) cannot indicate the real driving results. But the test results in China Heavy-duty Commercial Vehicle Test Cycle-Coach (CHTC-C) based on the road driving conditions in China are closer to the actual driving data. In this paper, the model for predicting the performance of heavy-duty vehicles is established and validated. The fuel consumption and NOx emission of a Euro VI heavy-duty coach under C-WTVC and CHTC-C tests are calculated by employing the developed model. Furthermore, the fuel consumption of the test coach is optimized and its sensitivity to the driving factors is analyzed.

A computational fluid dynamics (CFD) guided design optimization was conducted for the piston bowl geometry for a heavy-duty diesel engine. The optimization goal was to minimize engine-out NOx emissions without sacrificing engine peak power and thermal efficiency. The CFD model was validated with experiments and the combustion system optimization was conducted under three selected operating conditions representing low speed, maximum torque, and rated power. A hundred piston bowl shapes were generated, of which 32 shapes with 3 spray angles for each shape were numerically analyzed and one optimized design of piston bowl geometry with spray angle was selected. On average, the optimized combustion system decreased nitrogen oxide (NOx) emissions by 17% and soot emissions by 41% without compromising maximum engine power and fuel economy.

Use of ethanol as gasoline replacement can contribute to the reduction of nitrogen oxide (NOx) and carbon oxide (CO) emissions. Depending on ethanol production, significant reduction of greenhouse-gas emissions is possible. Concentration of certain species, such as unburned ethanol and acetaldehyde in the engine-out emissions are known to rise when ratio of ethanol to gasoline increases in the fuel. This research explores on hydrous ethanol fueled port-fuel injection (PFI) spark ignition (SI) engine emissions that contribute to photochemical formation of ozone, or so-called ozone precursors and the precursor of peroxyacetyl nitrates (PANs). The results are compared to engine operation on gasoline. Concentration obtained by FTIR gas analyzer, and mass-specific emissions of formaldehyde (HCHO), acetaldehyde (MeCHO) and methane (CH4) under two engine speed, four load and two spark advance settings are analyzed and presented.

The purpose of this study is to evaluate the impact of two-stage pilot injection parameters on the combustion and emissions of pilot diesel compression ignition natural gas (CING) engine at low load. Experiments were performed using a diesel/natural gas dual-fuel engine, which was modified from a six-cylinder diesel engine. The effect of injection timing and injection pressure of two-stage pilot diesel were analyzed in order to reduce both the fuel consumption and total hydrocarbon (HC) and carbon monoxide (CO) emissions under low load conditions. The results indicate that, because injection timing can determine the degree of pilot diesel stratification, in-cylinder thermodynamic state, and the available mixing time prior to the combustion, the combustion process can be controlled and optimized through adjusting injection timing.

Forecasting the motion of the leading vehicle is a critical task for connected autonomous vehicles as it provides an efficient way to model the leading-following vehicle behavior and analyze the interactions. In this study, a personalized time-series modeling approach for leading vehicle trajectory prediction considering different driving styles is proposed. The method enables a precise, personalized trajectory prediction for leading vehicles with limited inter-vehicle communication signals, such as vehicle speed, acceleration, space headway, and time headway of the front vehicles. Based on the learning nature of human beings that a human always tries to solve problems based on grouping and similar experience, three different driving styles are first recognized based on an unsupervised clustering with a Gaussian Mixture Model (GMM).

To meet the new requirements of braking system for modern electrified and intelligent vehicles, various novel electro-mechanical brake boosters (Eboosters) are emerging. This paper is aimed at a new type of the Ebooster, which is mainly consisted of a permanent magnet synchronous motor (PMSM), a two-stage reduction transmission and a servo mechanism. Among them, the PMSM is a vital actuator to realize the functions of the Ebooster. To get fast response of the Ebooster system, a novel control strategy employing a maximum torque per ampere (MTPA) control with current compensation decoupling and current-adjusting adaptive flux-weakening control is proposed, which requires the PMSM can operate in a large speed range and maintain a certain anti-load interference capability. Firstly, the wide speed control strategy for the Ebooster’s PMSM is designed in MATLAB/Simulink.

This paper details the vehicle testing activities performed during the Year 4 of the EcoCAR 3 competition by the Wayne State University team on a Pre-Transmission Parallel PHEV. The paper focuses on two main testing platforms: the chassis dynamometer and the closed-course track (on-road). The focus of the former is to evaluate the emissions and energy consumption associated with different driving scenarios, while the latter has been used to assess the vehicle performance and their impact on the consumer appeal. The paper presents the objectives of each test, the setup accomplished for the different vehicle testing platforms, the results obtained and the comparison with the values expected from simulations. In addition, the impact of the results on the refinement of the control strategies and on the validation of the simulation models are discussed.

The driving behaviors of young drivers under the influence of anger are analyzed by driving simulator in this paper. A total of 12 subjects are enrolled during the experiment. Standardized videos are utilized to induce the driver's anger emotion. And the driver's electrocardiogram (ECG) signal is collected synchronously and compared before and after emotional trigger, which prove the validity of emotional trigger. Based on the result, the driver's driving performance under the straight road and the curve under normal state and angry state are compared and analyzed. The results of independent sample t-test show that there are significant differences in the running time of straight sections and the standard deviation of steering wheel angle in curves between normal and angry states. In conclusion, the longitudinal and lateral operation of drivers is unstable in angry state and the driver will be more destructive to the regular driving behavior.