Search Results

Computational models directly derived from data gained increased interest in recent years. Data-driven approaches have brought breakthroughs in different research areas such as image-, video- and audio-processing. Often denoted as Machine Learning (ML), today these approaches are not widely applied in the field of vehicle Noise, Vibration and Harshness (NVH). Works combining ML and NVH mainly discuss the topic with respect to psychoacoustics, traffic noise, structural health monitoring and as improvement to existing numerical simulation methods. Vehicle interior noise is a major quality criterion for today’s automotive customers. To estimate noise levels early in the development process, deterministic system descriptions are created by utilizing time-consuming measurement techniques. This paper examines whether pattern-recognizing algorithms are suitable to conduct the prediction process for a steering system.

Existing electronic combustion engine control systems only guarantee a desired air-to-fuel-ratio λ in stationary operation. In order to achieve the desired λ also in in-stationary use of the engine, it is necessary to use new-technology-based control systems. Artificial Intelligence provides methods to cope with difficulties like wide operation range, unknown nonlinearities and time delay. We will propose a strategy for control of a Spark Ignition Engine to determine the mass of air inside the combustion chambers with the highest accuracy. Since Neural Networks are universal approximators for multidimensional nonlinear static functions they can be used effectively for identification and compensation purposes of unknown nonlinearities in closed control loops.

In order to reduce emissions of spare ignition engines using a three way catalyst, a stoichiometric air-fuel ratio must be guaranteed in stationary and transient operation of the engine. This aim can be reached by using a specific feed-forward structure for the control of the paths of air and fuel based on identification abilities of Artificial Intelligence. As approximators for multidimensional nonlinear static functions we will use specific Neural Networks (NN) together with sophisticated stability-proven learning structures. The acquired knowledge within the NN determines our control action mainly through using feed-forward structures. Our investigations are based on the so-called mean-value-modelling approach of SI engines; it is our aim to present this strategy.

For high levels autonomous driving functions, the Decision Layer often takes on more responsibility due to the requirement of facing more diverse and even rare conditions. It is very difficult to accurately find a safe and efficient lane change timing when autonomous vehicles encounter complex traffic flow and need to change lanes. The traditional method based on rules and experiences has the limitation that it is difficult to be taken into account all possible conditions. Therefore, this paper designs a lane-changing decision algorithm based on data-driven and machine learning, and uses the DQN (Deep Q Network) algorithm in Reinforcement Learning to determine the appropriate lane-changing timing and target lane. Firstly, the scene characteristics of the highway are analyzed, the input and output of the decision-making model are designated and the data from the Perception Layer are processed.

Based on the sample data obtained from the bench test of a four-cylinder naturally aspirated CNG engine, three different machine learning models, BP, SVM and GRNN, were used to develop the intake charge prediction model for the intake system of this engine, in which engine speed, intake manifold pressure and intake temperature, VVT angle and gas injection time were taken as input parameters and intake charge was used as output parameter. The comparative analysis of the experimental data and model prediction data showed that the mean absolute error (MAE) of BP model, GRNN model, and SVM model were 2.69, 8.11and 5.13, and the root mean square error (MSE) were 3.53, 9.29, and 7.17, respectively. BP model has smaller prediction error and higher accuracy than SVM and GRNN models, which is more suitable for the prediction of the intake charge of this type of four-cylinder naturally aspirated CNG engine.

As turbulence modeling has become an indispensable approach to perform flow simulation in a wide range of industrial applications, how to enhance the prediction accuracy has gained increasing attention during the past years. Of all the turbulence models, RANS is the most common choice for many OEMs due to its short turn-around time and strong robustness. However, the default setting of RANS is usually benchmarked through classical and well-studied engineering examples, not always suitable for resolving complex flows in specific circumstances. Many previous researches have suggested a small tuning in turbulence model coefficients could achieve higher accuracy on a variety of flow scenarios. Instead of adjusting parameters by trial and error from experience, this paper introduced a new data-driven method of turbulence model recalibration using adjoint solver, based on Generalized k-ω (GEKO) model, one variant of RANS.

To improve the durability of Proton-exchange membrane fuel cell (PEMFC) in actual transportation application scenario, the research on fault diagnosis of PEMFC is receiving extensive attention. With the development of artificial intelligence, performing fault diagnosis with the massive sampling data of the fuel cell system has become a popular research topic. But few people have successfully verified the diagnosis performance of these artificial intelligence algorithms on a real high power on-board PEMFC system. Therefore, we intend to make a step forward with these data-driven artificial intelligence algorithms. We applied four data-driven artificial intelligence algorithms to diagnose three common faults of PEMFC (each fault type has two severity levels, slight and severe). AVL CRUISE M was firstly applied for generation of simulation fault dataset to speed up the algorithm screening process. Based on the dataset, these algorithms are trained and optimized.

The intersection is recognized as the most dangerous area because of the restricted road structures and indeterminate traffic regulations. Therefore, according to the Vehicle-to-everything (V2X) communication, Intelligent Transportation Systems (ITS), and Digital Twin data, we present a potential energy field method to establish the general characteristics of intersection traffic safety, evaluate the safety situation of intersection and assist intersection traffic participants in passing through the intersection safer and more efficient. The resulting potential energy field method is established by the contour line of traffic participants' potential energy, which is constructed as a superposition of disparate energies, such as boundary potential energy, body potential energy, and velocity potential energy. The intersection traffic safety is evaluated by the potential energy field characteristic of simultaneous intersection traffic participants.

With the popularity of automated vehicles, the future mixed traffic flow contains automated vehicles with different degrees of intelligence developed by other manufacturers. Therefore, simulating the interaction behavior of automated vehicles with varying levels of intelligence is crucial for testing and evaluating autonomous driving systems. Since the algorithm of traffic vehicles with various intelligence levels is difficult to obtain, it leads to hardships in quantitatively characterizing their interaction behaviors. Therefore, this paper designs a new automated vehicle test platform to solve the problem. The intelligent vehicle testbed with multiple personalized in-vehicle control units in the loop consists of three parts: 1. Multiple controllers in the loop to simulate the behavior of traffic vehicles；2. The central console applies digital twin technology to share the same traffic scenario between the tested vehicle and the traffic vehicle, creating a mixed traffic flow. 3.

High-speed vehicles in low illumination environments severely blur the images used in object detectors, which poses a potential threat to object detector-based advanced driver assistance systems (ADAS) and autonomous driving systems. Augmenting the training images for object detectors is an efficient way to mitigate the threat from motion blur. However, little attention has been paid to the motion of the vehicle and the position of objects in the traffic scene, which limits the consistence between the resulting augmented images and traffic scenes. In this paper, we present a vehicle kinematics-based image augmentation algorithm by modeling and analyzing the traffic scenes to generate more realistic augmented images and achieve higher robustness improvement on object detectors against motion blur. Firstly, we propose a traffic scene model considering vehicle motion and the relationship between the vehicle and the object in the traffic scene.

In motorsports, aerodynamic development processes target to achieve gains in performance. This requires a comprehensive understanding of the prevailing aerodynamics and the capability of analysing large quantities of numerical data. However, manual analysis of a significant amount of Computational Fluid Dynamics (CFD) data is time consuming and complex. The motivation is to optimize the aerodynamic analysis workflow with the use of deep learning architectures. In this research, variants of 3D deep learning models (3D-DL) such as Convolutional Autoencoder (CAE) and U-Net frameworks are applied to flow fields obtained from Reynolds Averaged Navier Stokes (RANS) simulations to transform the high-dimensional CFD domain into a low-dimensional embedding. Consequently, model order reduction enables the identification of inherent flow structures represented by the latent space of the models.

Cut-in scenarios are common and of potential risk in China but Advanced Driver Assistant System (ADAS) doesn’t work well under such scenarios. In order to improve the acceptance of ADAS, its reactions to Cut-in scenarios should meet driver’s driving habits and expectancy. Brake is considered as an express of risk and brake tendency in normal Cut-in situations needs more investigation. Under critical Cut-in scenarios, driver tends to brake hard to eliminate collision risk when cutting in vehicle right crossing lane. However, under less critical Cut-in scenarios, namely normal Cut-in scenarios, driver brakes in some cases and takes no brake maneuver in others. The time when driver initiated to brake was defined as key time. If driver had no brake maneuver, the time when cutting-in vehicle right crossed lane was defined as key time. This paper focuses on driver’s brake tendency at key time under normal Cut-in situations.

In the autonomous driving perception task, the accuracy of target detection is an essential evaluation, especially for small targets. In this work, we propose a multi-sensor fusion neural network that combines radar and image data to improve the confidence level of the camera when detecting targets and the accuracy of the prediction box regression. The fusion network is based on the basic structure of single-shot multi-box detection (SSD). Inspired by the attention mechanism in image processing, our work incorporates the a priori knowledge of radar detection in the convolutional block attention module (CBAM), which forms a new attention mechanism module called radar convolutional block attention module (RCBAM). We add the RCBAM into the SSD target detection network to build a deep neural network fusing millimeter-wave radar and camera.

Motivated by applying artificial intelligence technology to the automobile industry, reinforcement learning is becoming more and more popular in the community of intelligent driving research. The reward function is one of the critical factors which affecting reinforcement learning. Its design principle is highly dependent on the features of the agent. The agent studied in this paper can do perception, decision-making, and motion-control, which aims to be the assistant or substitute for human driving in the latest future. Therefore, this paper analyzes the characteristics of excellent human driving behavior based on the six-layer model of driving scenarios and constructs it into a human knowledge graph. Furthermore, for highway pilot driving, the expert demo data is created, and the reward function is self-learned via inverse reinforcement learning. The reward function design method proposed in this paper has been verified in the Unity ML-Agent environment.

Object detection is an important visual content of the autonomous vehicle, the traditional detecting methods usually cost a lot of computational memory and elapsed time. This paper proposes to use lightweight deep convolutional neural network (MobilenetV3-SSDLite) to carry out the object detection task of autonomous vehicles. Simulation analysis based on this method is implemented, the feature layer obtained after h-swish activation function in the first Conv of the 13th bottleneck module in MobilenetV3 is taken as the first effective feature layer, and the feature layer before pooling and convolution of the antepenultimate layer in MobilenetV3 is taken as the second effective feature layer, and these two feature layers are extracted from the MobilenetV3 network.

The main challenge for future autonomous vehicles is to identify their location and body pose in real time during driving, that is, “where am I? and how will I go?”. We address the problems of pose estimation and scene perception from continuous visual frames in intelligent vehicle. Recent advanced technology in the domain of deep learning proposes to train some learning models for vehicle’s series detection tasks in a supervised or unsupervised manner, which has numerous advances over traditional approaches, mainly reflected in the absence of manual calibration and synchronization of the camera and IMU. In the paper, we propose a novel approach for pose estimation and scene recognition with a deep fusion of multi-modal neural features in the manner of unsupervised. Firstly, low-cost camera and IMU are used to extract original visual and inertial data, then the visual and inertial encoders are utilized to encoder the feature of the two modes.

The plug-in hybrid electric vehicles with dual-motor and multi-gear structure can realize multiple operation modes such as series, parallel, hybrid, etc. The traditional rule-based energy management strategy mostly selects some of the modes (such as series and parallel) to construct the energy management strategy. Although this method is simple and reliable, it can’t fully exert the full potential of this structure considering both economy and driving performance. Therefore, it is very important to study the algorithm which can exert the maximum potential of the multi-degree-of-freedom structure. In this paper, a new RL-PMP algorithm is proposed, which does not divide the operation modes, and explores the optimal energy allocation strategy to the maximum extent according to the economic and drivability criteria within the allowable range of the characteristics of the power system components.

Since data processing methods could not completely eliminate the uncertainty of signals, it is a key issue for stable and robust decision-making for uncertainty tolerance of intelligent vehicles. In this paper, a decision-making for an Autonomous Emergency Braking (AEB) case considering the uncertainty of road adhesion coefficient estimation (RACE) is proposed. Firstly, the 3σ criterion is employed to classify the confidence in order to establish the decision-making mechanism considering the signal uncertainty of RACE. Secondly, the model for AEB with the uncertainty of the road adhesion coefficient estimated is designed based on the Seungwuk Moon model. Thirdly, a CCRs and CCRm scenario was designed to verify the feasibility in reference to the European New Car Assessment Programme (Euro NCAP) standard. Finally, the results of 10,000 cycles test illustrate that the proposed method is stable and could significantly improve the safety confidence both in the CCRs and CCRm scenarios.

Since situational awareness is crucial for autonomous driving in urban environments, multi-target tracking has become an increasingly popular research topic during the last several years. For autonomous driving in urban environments, cars and pedestrians are the two main types of obstacles, and their motion characteristics are not the same. While in the current related multi-target tracking research, the same motion model (such as Constant Velocity model [CV]) or motion model set (such as CV combined with Constant Acceleration model [CA]) is mostly used to track different types of obstacles simultaneously. Besides, in current research, regular motion models are mostly adopted to track pedestrians, such as CV, CA, and so on, the uncertainty in pedestrian motion is not well considered.

Deep neural network models have been widely used for environment perception of intelligent vehicles. However, due to models’ innate probabilistic property, the lack of transparency, and sensitivity to data, perception results have inevitable uncertainties. To compensate for the weakness of probabilistic models, many pieces of research have been proposed to analyze and quantify such uncertainties. For safety-critical intelligent vehicles, the uncertainty analysis of data and models for environment perception is especially important. Uncertainty estimation can be a way to quantify the risk of environment perception. In this regard, it is essential to deliver a comprehensive survey. This work presents a comprehensive overview of uncertainty estimation in deep neural networks for environment perception of intelligent vehicles.