Search Results

SLAM (Simultaneous Localization and Mapping) plays a key role in autonomous driving. Recently, 4D Radar has attracted widespread attention because it breaks through the limitations of 3D millimeter wave radar and can simultaneously detect the distance, velocity, horizontal azimuth and elevation azimuth of the target with high resolution. However, there are few studies on 4D Radar in SLAM. In this paper, RI-FGO, a 4D Radar-Inertial SLAM method based on Factor Graph Optimization, is proposed. The RANSAC (Random Sample Consensus) method is used to eliminate the dynamic obstacle points from a single scan, and the ego-motion velocity is estimated from the static point cloud. A 4D Radar velocity factor is constructed in GTSAM to receive the estimated velocity in a single scan as a measurement and directly integrated into the factor graph. The 4D Radar point clouds of consecutive frames are matched as the odometry factor.

In recent years, with the development of computing infrastructure and methods, the potential of numerical methods to reasonably predict aerodynamic noise in turbocharger compressors of heavy-duty diesel engines has increased. However, aerodynamic acoustic modeling of complex geometries and flow systems is currently immature, mainly due to the greater challenges in accurately characterizing turbulent viscous flows. Therefore, recent advances in aerodynamic noise calculations for automotive turbocharger compressors were reviewed and a quantitative study of the effects for turbulence models (Shear-Stress Transport (SST) and Detached Eddy Simulation (DES)) and time-steps (2° and 4°) in numerical simulations on the performance and acoustic prediction of a compressor under various conditions were investigated.

As a key component of in-vehicle intelligent voice technology, speech enhancement can extract clean speech signals contaminated by environmental noise to improve the perceptual quality and intelligibility of speech. It has extensive applications in the field of intelligent car cabins. Although some end-to-end speech enhancement methods based on time domain have been proposed, there is often limited consideration given to designing model architectures based on the characteristics of the speech signal. In this paper, we propose a new U-Net based speech enhancement framework that utilizes the temporal correlation of speech signals to reconstruct higher-quality and more intelligible clean speech.

Accurate and reliable localization in GNSS-denied environments is critical for autonomous driving. Nevertheless, LiDAR-based and camera-based methods are easily affected by adverse weather conditions such as rain, snow, and fog. The 4D Radar with all-weather performance and high resolution has attracted more interest. Currently, there are few localization algorithms based on 4D Radar, so there is an urgent need to develop reliable and accurate positioning solutions. This paper introduces RIO-Vehicle, a novel tightly coupled 4D Radar/IMU/vehicle dynamics within the factor graph framework. RIO-Vehicle aims to achieve reliable and accurate vehicle state estimation, encompassing position, velocity, and attitude. To enhance the accuracy of relative constraints, we introduce a new integrated IMU/Dynamics pre-integration model that combines a 2D vehicle dynamics model with a 3D kinematics model.

Radar is playing more and important role in multiple object detection and tracking system due to the fact that Radar can not only determine the velocity instantly but also it is less influenced by environment conditions. However, Radar faces the problem that it has many detection clutter，false alarms and detection results are easily affected by the reflected echoes of road boundary in traffic scenes. Besides this, With the increase of the number of targets and the number of effective echoes, the number of interconnection matrices increases exponentially in joint probability data association, which will seriously affect the real-time and accuracy of high-speed scene algorithms.in the tracking system. So, A method of using millimeter wave radar to detect and fit the boundary guardrail of high-speed road is proposed, and the fitting results are applied to the vehicle detection and tracking system to improve the tracking accuracy.

SEAT Department of SAIC Motor Vehicle Company starts innovatively applying the single motor and P2.5 configuration scheme from EDU G2(Electric Drive Unit Generation 2), which consists of six engine gears and four motor gears. EDU G2 is very compact and adaptable through the coupling design. Gear coupling make the engine and motor coordination limited, so as to the high efficiency zone of the engine and the high efficiency zone of the motor cannot match in some working conditions, which affect the performance of the vehicle. Therefore, SEAT developed the second generation of single-motor plug-in hybrid system EDU G2 Plus EDU G2(Electric Drive Unit Generation 2 Plus), which realized the decoupling design of 5 engine gears and 2 motor gears, so that the power output of engine and motor is freely. With excellent power and economic performance, the vehicle has been well received by customers.

The roof sensor system is an indispensable part of intelligent vehicles to observe the environment, however, it deteriorates the aerodynamic and noise performance of the vehicle. In this paper, large eddy simulation and the acoustic perturbation equation are combined to simulate the flow and sound fields of the intelligent vehicle. Firstly, test and simulation differences of aerodynamic drag and pressure coefficients on the roof and rear of the intelligent vehicle without roof sensor system are discussed. It is found that the difference in aerodynamic drag coefficient is 5.5%, and the pressure coefficients’ differences at 21 out of 24 measurement points are less than 0.05. On this basis, under the influence of the sensor system, the aerodynamic drag coefficient of the intelligent vehicle is increased by 23.4%.

A formal gesture recognition based on optics has limitations, but millimeter-wave (MMW) radar has shown significant advantages in gesture recognition. Therefore, the MMW radar has become the most promising human-computer interaction equipment, which can be used for human-computer interaction of vehicle personnel. This paper proposes a multi-branch network based on a residual neural network (ResNet) to solve the problems of insufficient feature extraction and fusion of the MMW radar and immense algorithm complexity. By constructing the gesture sample library of six gestures, the MMW radar signal is processed and coupled to establish the relationship between the motion parameters of the distance, speed, and angle of the gesture information and time, and the depth features are extracted. Then the three depth features are fused. Finally, the classification and recognition of MMW radar gesture signals are realized through the full connection layer.

Multi-Target tracking is a central aspect of modeling the surrounding environment of autonomous vehicles. Automotive millimeter-wave radar is a necessary component in the autonomous driving system. One of the biggest advantages of radar is it measures the velocity directly. Another big advantage is that the radar is less influenced by environmental conditions. It can work day and night, in rainy or snowy conditions. In the expressway scenario, the forward-looking radar can generate multiple objects, to properly track the leading vehicle or neighbor-lane vehicle, a multi-target tracking algorithm is required. How to associate the track and the measurement or data association is an important question in a multi-target tracking system. This paper applies the nearest-neighbor method to solve the data association problem and uses an extended Kalman filter to update the state of the track.

As the electric vehicle market grows rapidly, thermal analysis related to the performance of electric drive motors has gained increasing interest. However, it is hard to obtain rotor temperature for torque correction during operation which leads to unexpected inaccurate control of motors. Rotor temperature monitoring and torque correction for IPMSM (Interior Permanent Magnet Synchronous motor) of new Energy vehicles are discussed in this paper. Considering the practical application, a low-order lumped parameter thermal network (LPTN) composed of three nodes is built for calculating the rotor temperature under different operating conditions on a 160kw IPMSM of a three-in-one electric drive. To identify the parameters of LPTN, the measurements were done on a test bench with a prototype of the three-in-one electric drive. K-type thermocouples were used to directly measure the temperature of each node.

Indirect rotary transducer for an automotive screen interface is an innovative solution for the smart cockpit. The primary objective of this study is to design an indirect rotary transducer system, and study its feasibility in the smart cockpit. The working theory of this designed system is that the magnetic induction hall electronic chip can detect changes in the magnetic field. Several tests have been conducted, which show that the hypothesis of dangling operating system achieves the same effect as a hard-wired operating system. The results of the experiment indicate that the magnetic induction hall sensor can meet the specification of traditional hard-wired operating system. This system is a good concept for intelligent cab driving, which can fully meet the needs of the current market.

As the connectivity of vehicles increases rapidly, more vehicles have the capability to communicate with each other. Because Vehicular Ad-hoc NETworks (VANETs) have the characteristics of solid mobility and decentralization, traditional security strategies such as authentication, firewall, and access control are difficult to play an influential role. As a soft security method, trust management can ensure the security attributes of VANETs. However, the rapid growth of newly encountered nodes of the trust management system also increases the requirements for trust establishing mechanisms. Without a proper trust establishment mechanism, the trust value of the newly encountered nodes will deviate significantly from its actual performance, and the trust management system will suffer from newcomer attacks.

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.

A comfortable thermal environment can alleviate fatigue, reduce irritability, and improve driving safety. However, it is rather a challenge to evaluate thermal comfort inside a vehicle due to multifarious geometric and environmental factors as well as human differences. This study conducted a series of field experiments both in summer and winter conditions, measuring the thermal environment parameters inside the compartment and the skin temperature of experimental personnel, and carrying out subjective thermal sensation and comfort questionnaires. The experimental results showed that head and trunk are the most relevant parts of all human body parts to the overall thermal sensation/comfort. For overall thermal sensation, the value of regression R2 referring to head/trunk is 0.691/0.721, while those corresponding to overall thermal comfort is 0.802/0.773.

Hydrous ethanol not only has the advantages of high-octane number and valuable oxygen content, but also reduce the energy consumption in the production process. However, little literature investigated the internal flow and cavitation of hydrous ethanol-gasoline fuels in the multi-hole direct injector. In this simulation, a two-phase fuel flow model in injector is established based on the multi-fluid model of Euler-Euler method, and the accuracy of model is verified. On the basis of this model, the flow of different hydrous ethanol-gasoline blends is calculated under different injection conditions, and the cavitation, flow rate, and velocity at the outlet of the nozzle are predicted. Meanwhile, the influence of temperature and back pressure on the flow is also analyzed. The results show that the use of hydrous ethanol reduces the flow rate, compared with the velocity of E0, that of E10w, E20w, E50w, E85w, and E100w decreases by 10%, 12.9%, 17.6%, 20%, and 23.5%, respectively.

The efficiency and durability of fuel cells are affected by internal water content. Therefore, the active control of humidity is of great significance for vehicle fuel cells, especially for self-humidifying fuel cell systems. To realize fuel cell internal humidity active control, it is necessary to collect the humidity information of stack in real time, so as to carry out feedback control. However, humidity sensor has the characteristics of high cost and low durability, so it is more practical to get the feedback value of humidity by using state estimation method for high-power commercial fuel cell system such as vehicle fuel cell. However, humidity estimation is often affected by other physical or chemical dynamic processes, such as oxygen transportation and response process of electrical appliances. In order to weaken the influence of other physical or chemical dynamic processes on humidity estimation, this paper proposes an adaptive sliding mode Kalman observer (ASMK) algorithm.

With the strict requirements of harmful emission regulations, carbon peaking and neutralization goal, the internal combustion engine (ICE) industry is facing great challenges. Compared with pure ICE powertrain, hybrid powertrain has the advantages on fuel consumption and harmful emissions, which is more suitable for the market today. In series hybrid powertrain, because of the direct mechanical connection between ICE and motor, the motor can be used as an assistant in optimizing the performance of ICE. In order to realize the cycle-based or crank angle-based control of ICE, a high-frequency motor control system need to be built. Field Programmable Gate Array (FPGA) has the characteristics of high calculation frequency and high reliability to meet the demand. At the same time, the ICE control based on LabVIEW and FPGA has been realized.

Proton exchange membrane fuel cell (PEMFC) has attracted extensive attention in recent years because of its high efficiency and zero emission. Although fuel cell technology has made great progress, durability is still the bottleneck of its large-scale commercialization. In order to systematically study the degradation of fuel cell system for transportation applications, we selected the most severe operating condition - on-off cyclic condition as the research object, and focused on the influence of cell temperature and air relative humidity on the degradation rate of fuel cell by means of polarization curve, reference voltage and CV. The results show that with the same temperature, the fuel cell performance degradation rate first decreases and then increases with the decrease of humidity, which may be due to the increase of platinum ion transfer rate at high relative humidity and the dry membrane at low relative humidity.

A Joint Probabilistic Data Association (JPDA) multi-objective tracking improvement algorithm based on camera-radar fusion is proposed to address the problems of poor single-sensor tracking performance, unknown target detection probability, and missing valid targets in complex traffic scenarios. First, according to the correlation rule between the target track and the measurement, the correlation probability between the target and the measurement is obtained; then the measurement collection is divided into camera-radar measurement matched target, camera-only measurement matched target, radar-only measurement matched target, and no-match target; and the correlation probability is corrected with different confidence levels to avoid the use of unknown detection probability.

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.