Search Results

Lane detection is one of the most important part in ADAS because various modules (i.e., LKAS, LDWS, etc.) need robust and precise lane position for ego vehicle and traffic participants localization to plan an optimal routine or make proper driving decisions. While most of the lane detection approaches heavily depend on tedious pre-processing and great amount of assumptions to get reasonable result, the robustness and efficiency are deteriorated. To address this problem, a novel framework is proposed in this paper to realize robust and real-time lane detection. This framework consists of two branches, where canny edge detection and Progressive Probabilistic Hough Transform (PPHT) are introduced in the first branch for efficient detection.

Intelligent driving, aimed for collision avoidance and self-navigation, is mainly based on environmental sensing via radar, lidar and/or camera. While each of the sensors has its own unique pros and cons, camera is especially good at object detection, recognition and tracking. However, unpredictable environmental illumination can potentially cause misdetection or false detection. To investigate the influence of illumination conditions on detection algorithms, we reproduced various illumination intensities in a photo-realistic virtual world, which leverages recent progress in computer graphics, and verified vehicle detection effect there. In the virtual world, the environmental illumination is controlled precisely from low to high to simulate different illumination conditions in the driving scenarios (with relative luminous intensity from 0.01 to 400). Sedan cars with different colors are modelled in the virtual world and used for detection task.

Ambient temperature is a very sensitive use condition for electric vehicles (EVs), so it is imperative to ensure the maintenance of suitable temperature. This is particularly important in regions characterized by prolonged exposure to unfavorable temperature conditions. In such cases, it becomes necessary to implement insulation measures within parking facilities and allocate energy resources to sustain a desired temperature level. Solar energy is a renewable and environmentally friendly source of energy that is widely available. However, the effectiveness of utilizing solar energy is influenced by various factors, such as the time of day and weather conditions. The use of phase change material (PCM) in a latent heat energy storage (LHES) system has gained significant attention in this field. In contrast to single-phase energy storage materials, PCM offer a more effective heat storage capacity.

The automotive industry is aggressively pursuing fuel efficiency improvements through hybridization of production vehicles, and there are an increasing number of racing series adopting similar architectures to maintain relevance with current passenger car trends. Hybrid powertrains offer both performance and fuel economy benefits in a motorsport setting, but they greatly increase control complexity and add additional degrees of freedom to the design optimization process. The increased complexity creates opportunity for performance gains, but simulation based tools are necessary since hybrid powertrain design and control strategies are closely coupled and their optimal interactions are not straightforward to predict. One optimization-related advantage that motorsports applications have over production vehicles is that the power demand of circuit racing has strong repeatability due to the nature of the track and the professional skill-level of the driver.

Hybrid Electric Vehicles with a power split system provide a variety of possibilities to promote the fuel economy of vehicles and better adapt to various driving conditions. In this paper, a new power split system of a hybrid electric bus which consists of double planetary gear sets and a clutch is introduced. The system is able to decouple both the torque and speed of the engine from the road load, which makes it possible for the engine to operate on its optimal operation line (OOL). Considering the features of the system configuration and bus driving cycle, the driving mode of the bus is divided into Electric Vehicle (EV) mode, Electric Variable Transmission (EVT) mode and Parallel mode. By controlling the engagement of the clutch at high vehicle speed (after the mechanical point), the system operates in the parallel mode rather than EVT mode. This avoids the problem that the system efficiency sharply declines in high speed region which EVT configurations are generally faced with.

The platooning of connected automated vehicles (CAV) possesses the significant potential of reducing energy consumption in the Intelligent Transportation System (ITS). Moreover, with the rapid development of eco-driving technology, vehicle platooning can further enhance the fuel efficiency by optimizing the efficiency of the powertrain. Since road grade is a main factor that affects the energy consumption of a vehicle, the estimation of the road grade with high accuracy is the key factor for a connected vehicle platoon to optimize energy consumption using vehicle-to-vehicle (V2V) communication. Commonly, the road grade is quantified by single consumer grade global positioning system (GPS) with the geodetic height data which is rough and in the meter-level, increasing the difficulty of precisely estimating the road grade.

The new control algorithm for parallel hybrid electric vehicle is presented systematically, in which engine operation points are limited within higher efficient area by the control algorithm and the state of charge (SOC) is limited in a range in order to enhance the batteries' charging and discharging efficiency. In order to determine the ideal operating point of the vehicle's engine, the control strategy uses a lookup table to determine the torque output of the engine. The off-line simulation model of parallel HEV power train is developed which includes the control system and controlled objective (such as engine, electric motor, battery pack and so on). The results show that the control algorithm can effectively limite engine and battery operation points and much more fuel economy can be achieved than that of conventional one.

Since road electric vehicles typically require a significantly variable and random load power demand in response to traffic conditions, such as frequent sequences of acceleration and deceleration and uphill followed by downhill runs. In this context, the energy management system of electric vehicle must ensure an effective power distribution between battery and supercapacitor to satisfy load demand. In this paper, the power management control strategy of hybrid energy storage system is developed by introducing terrain information to optimize system efficiency and battery lifetime. In this presented research, we aim at developing a power management control strategy considering the influence of the terrain information on system efficiency and battery lifetime.

The poor low-temperature behavior of Li-ion batteries has limited its application in the field of electric vehicles and hybrid electric vehicles. Many previous studies concentrate on developing new type of electrolyte to solve this problem. However, according to recent research, the key limitation at low temperature is the low diffusivity of lithium ion in the anode electrodes. Hence, it is potential to study anode materials to improve low-temperature behavior of LIBs. ZnFe2O4 with higher theoretical capacity is low toxicity and abundance, contributing to its commercial application. Different ZnFe2O4 crystalline shapes have different particle sizes. Among them, the cubic ZnFe2O4 with smaller particle size will increase its own electronic and ionic conductance at lower temperature. In this regard, we evaluated low-temperature performance of LIBs with ZnFe2O4 cubes as anode materials at -25°C.

This paper describes a novel power management control strategy of battery and supercapacitor hybrid energy storage system to improve system efficiency and battery lifetime. In the presented research, the high and low frequency power demand in the load is separated by a Haar wavelet transform algorithm to overcome the problem of battery overload work and associated degeneration in battery lifetime resulting from an ineffective distribution between battery and supercapacitor. The purpose of frequency distribution is that the supercapacitor is used to share high frequency power components of load power demand to smooth the power demand applied to battery. However, the sole frequency control often fails to realize the optimal utilization of supercapacitor because of the uncertain variation in the driving cycle.

Adaptive cruise control (ACC), as one of the advanced driver assistance systems (ADAS), has become increasingly popular in improving both driving safety and comfort. Since the objectives of ACC can be multi-dimensional, and often conflict with each other, it is a challenging task in its control design. The research presented in this paper takes ACC control design as a constrained optimization problem with multiple objectives. A hierarchical framework for ACC control is introduced, aimed to achieve optimal performance on driving safety and comfort, speed and/or distance tracking, and fuel economy whenever possible. Under the hierarchical framework, the operational mode is determined in the upper layer, in which a model predictive control (MPC) based spacing controller is employed to deal with the multiple control objectives. On the other hand, the lower layer is for actuator control, such as braking and driving control for vehicle longitudinal dynamics.

This paper addresses the issues of long-term signal loss in localization and cumulative drift in SLAM-based online mapping and localization in autonomous valet parking scenarios. A GPS, INS, and SLAM fusion localization framework is proposed, enabling centimeter-level localization with wide scene adaptability at multiple scales. The framework leverages the coupling of LiDAR and Inertial Measurement Unit (IMU) to create a point cloud map within the parking environment. The IMU pre-integration information is used to provide rough pose estimation for point cloud frames, and distortion correction, line and plane feature extraction are performed for pose estimation. The map is optimized and aligned with a global coordinate system during the mapping process, while a visual Bag-of-Words model is built to remove dynamic features.

High-precision and real-time ego-motion estimation is vital for autonomous vehicle. There is a lot GPS-denied maneuver such as underground parking lot in urban areas. Therefore, the localization system relying solely on GPS cannot meets the requirements. Recently, lidar odometry and visual odometry have been introduced into localization systems to overcome the problem of missing GPS signals. Compared with visual odometry, lidar odometry is not susceptible to light, which is widely applied in weak-light environments. Besides, the autonomous parking is highly dependent on the geometric information around the vehicle, which makes building map of surroundings essential for autonomous vehicle. We propose a lidar inertial odometry and mapping. By sensor fusion, we compensate for the drawback of applying a single sensor, allowing the system to provide a more accurate estimate.

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.

Improvement of shift quality evaluation has become more prevalent over the past few years in the development of automatic transmission electronic control system. For the problems of the subjective shift quality evaluation that subjectivity is too strong, the standard cannot be unified and the definition of the objective evaluation index is not clear at present, this paper studies on the methods of objective evaluation of shift quality based on the multi-hierarchical grey relational analysis. Firstly, objective evaluation index system is constructed based on physical quantities, such as the engine speed, the longitudinal acceleration of the vehicle and so on, which broadens the scope of the traditional objective evaluation index further.

In this paper, the performance simulation model of a domestic self-dumping truck was established using AVL-Cruise software. Then its accuracy was checked by the power performance and fuel economy tests which were conducted on the proving ground. The power performance of the self-dumping truck was evaluated through standing start acceleration time from 0 to 70km/h, overtaking acceleration time from 60 to 70km/h, maximum speed and maximum gradeability, while the composite fuel consumption per hundred kilometers was taken as an evaluation index of fuel economy. A L9 orthogonal array was applied to investigate the effect of three matching factors including engine, transmission and final drive, which were considered at three levels, on the power performance and fuel economy of the self-dumping truck. Furthermore, the grey relational grade was proposed to assess the multiple performance responses according to the grey relational analysis.

In this study, with the aim of reducing fuel consumption and improving power performance, the optimization for the driveline parameters of a self-dumping truck was performed by using a vehicle performance simulation model. The accuracy of this model was checked by the power performance and fuel economy tests. Then the transmission ratios and final drive ratio were taken as design variables. Meanwhile, the power performance of the self-dumping truck was evaluated through standing start acceleration time from 0 to 70km/h, maximum speed and maximum gradeability, while the combined fuel consumption of C-WTVC drive cycle was taken as an evaluation index of fuel economy. The multi-objective optimization for the power performance and fuel economy was then performed based on particle swarm optimization algorithm, and the Pareto optimal set was obtained. Furthermore, the entropy method was proposed to determine the weight of fuel consumption and acceleration time.

Utilizing the developed off-line simulation model of series hybrid power train the study on the influence of components' parameters on acceleration performance and fuel economy of transit bus is completed. Based on these the guideline strategies of parametric design of series hybrid power train for transit bus are brought forward in this paper. Given the condition of propulsion requirement the parametric design for this transit bus are performed targeting minimizing fuel consumption. It is conclusion that the appropriate components' parameters determined by means of parametric design can make series hybrid transit bus achieve much better acceleration performance and much lower fuel equivalent consumption than that of baseline transit bus.

A novel torque-coupling architecture for hybrid electric vehicles is proposed. The torque-coupling device is based on automated manual transmission (AMT), which is highly efficient and provides six gears for the engine and three gears for each motor to enable the engine and the motors to work at high-efficiency levels in most cases. The proposed power-shift AMT (P-AMT) does not have a hydraulic torque converter and wet clutches, which dampen the driveline shock. Thus, the drivability control of the P-AMT becomes a challenging issue. Accurate engine, motor model and transmission model have been built and the dynamic control of the gear shift process of PAMT in hybrid mode is simulated. The electric motors compensate for the traction loss during the gear shift of the engine.

This paper describes a novel recognition and classification method of vehicle targets in urban road based on a vehicle-mounted Velodyne HDL64E light detection and ranging (LIDAR) system. The autonomous vehicle will choose different driving strategy according to the surrounding traffic environments to guarantee that the driving is safe, stable and efficient. It is helpful for controller to provide the efficient stagey to know the exact type of vehicle around. So this method concentrates on reorganization and classification the type of vehicle targets so that the controller can provide a safe and efficient driving strategy for autonomous ground vehicles. The approach is targeted at high-speed ground vehicle, so real-time performance of the method plays a critical role. In order to improve the real-time performance, some methods of data preprocessing should be taken to simplify the large-size long-range 3D point clouds.