Search Results

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.

Ammonia shows promise as an alternative fuel for internal combustion engines (ICEs) in reducing CO2 emissions due to its carbon-free nature and well-established infrastructure. However, certain drawbacks, such as the high ignition energy, the narrow flammability range, and the extremely low laminar flame speed, limit its widespread application. The dual fuel (DF) mode is an appealing approach to enhance ammonia combustion. The combustion characteristics of ammonia-diesel dual fuel mode and ammonia-PODE3 dual fuel mode were experimentally studied using a full-view optical engine and the high-speed photography method. The ammonia energy ratio (ERa) was varied from 40% to 60%, and the main injection energy ratio (ERInj1) and the main injection time (SOI1) were also varied in ammonia-PODE3 mode.

Accurate sensing of road conditions is one of the necessary technologies for safe driving of intelligent vehicles. Compared with the structured road, the unstructured road has complex road conditions, and the response characteristics of vehicles under different road conditions are also different. Therefore, accurately identifying the road categories in front of the vehicle in advance can effectively help the intelligent vehicle timely adjust relevant control strategies for different road conditions and improve the driving comfort and safety of the vehicle. However, traditional road identification methods based on vehicle kinematics or dynamics are difficult to accurately identify the road conditions ahead of the vehicle in advance. Therefore, this paper proposes an unstructured road region detection and road classification algorithm based on machine vision to obtain the road conditions ahead.

The driving power system can be combined with lasers, lights, etc., and applied to automobiles to achieve various functions. Under the general trend of the development of intelligent vehicles, people have higher and higher requirements for the accuracy and power of various equipment. However, as power increases, how to ensure the stability of factors such as current is a challenging problem. Therefore, it is extremely important to study and design a high-power drive system in this paper, so as to ensure a stable output of the current. The system is composed of power supply, load, secondary power supply and control chip. The choice of power supply and load is conventional model. The secondary power supply adopts step-down circuit, with synchronous rectifier chip, which can effectively reduce energy consumption, and with temperature protection device, which can ensure the safe and reliable operation of equipment.

A feasible method was developed to reconstruct the three-dimensional flame surface of SI combustion based on 2D images. A double-window constant volume vessel was designed to simultaneously obtain the side and bottom images of the flame. The flame front was reconstructed based on 2D images with a slicing model, in which the flame characteristics were derived by slicing flame contour modeling and flame-piston collision area analysis. The flame irregularity and anisotropy were also analyzed. Two different principles were used to build the slicing model, the ellipse hypothesis modeling and deep learning modeling, in which the ellipse hypothesis modeling was applied to reconstruct the flame in the optical SI engine. And the reconstruction results were analyzed and discussed. The reconstruction results show that part of the wrinkled and folded structure of the flame front in SI engines can be revealed based on the bottom view image.

Highly autonomous vehicles have drawn the interests of many researchers in recent years. For highly autonomous vehicles, a high-definition (HD) map is crucial since it provides accurate information for autonomous driving. However, due to the possible fast-changing environment, the performance of HD maps will deteriorate over time if timely updates are not ensured. Therefore, this paper studies the updating of lightweight HD maps in closed areas. Firstly, a novel two-layer map model called a lightweight HD map is introduced to support autonomous driving in a flexible and efficient way. Secondly, typical updating of scenarios in closed areas with non-paved roads is abstracted into operations including area border expansion, road addition, and road deletion. Meanwhile, a map updating framework is proposed to address the issue of map updating in closed areas. Finally, an experiment is conducted to demonstrate the feasibility and effectiveness of the proposed map updating approach.

In the field of automatic driving, the combination of 3D LIDAR and inertial measurement unit (IMU) is a common sensor configuration scheme in laser point-cloud localization, high-precision map making and point-cloud target detection. So it is critical to calibrate LIDAR and IMU accurately. At present, due to the large volume and high cost of 3D LIDAR with high-line-number(Such as 64 lines or 128 lines), the configuration scheme of using multiple low-line-number 3D LIDARs appears in the automatic driving vehicle sensing system. However, the common calibration methods are not suitable for multi 3D LIDARs and IMU parameters calibration on autonomous vehicle, which have the disadvantages of cumbersome implementation and low accuracy. In this paper, a joint calibration test platform composed of dual LIDARs and IMU is assembled, and a method of precise automatic calibration based on GPS/RTK data is proposed.

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.

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.

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.

Polyoxymethylene dimethyl ethers (PODEn) have high cetane number, high oxygen content and high volatility, therefore can be added to gasoline to optimize the performance and soot emission of Gasoline Compression Ignition (GCI) combustion. High speed imaging was used to investigate the spray and combustion process of gasoline/PODEn blends (PODEn volume fraction 0%-30%) under various ambient conditions and injection strategies in a constant volume vessel. Results showed that with an increase of PODEn proportion from 10% to 30%, liquid-phase penetration of the spray increased slightly, ignition delay decreased from 3.8 ms to 2.0 ms and flame lift off length decreased 29.4%, causing a significant increase of the flame luminance. For blends with 20% PODEn, when ambient temperature decreased from 893 K to 823 K, the ignition delay increased 1.3 ms and the flame luminance got lower.

An experiment was carried out to investigate the effect of single and double-deck pre-chamber on the combustion characteristics of premixed CH4/air in a constant volume vessel using schlieren method. A special design was proposed for the visualization of the pre-chamber. Combustion with different initial temperatures (300 K, 400 K, 500 K) were observed at stoichiometric ratio to lean-burn limit. Although single-deck pre-chamber has advantages over double-deck pre-chamber in both initial flame development duration and main combustion duration, the latter could extend the lean-burn limit by up to 0.3 and promote the stability of ignition. It is also found that extensive distribution of active species in main chamber before ignition can accelerate speed of flame propagation enormously.

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.

Small closely-coupled post injections of fuel in diesel engines are known to reduce engine-out soot emissions, but the relative roles of various underlying in-cylinder mechanisms have not been established. Furthermore, the efficacy of soot reduction is not universal, and depends in unclear ways on operating conditions and injection schedule, among other factors. Consequently, designing engine hardware and operating strategies to fully realize the potential of post-injections is limited by this lack of understanding. Following previous work, several different post-injection schedules are investigated using a single-cylinder 2.34 L heavy-duty optical engine equipped with a Delphi DFI 1.5 light-duty injector. In this configuration, adding a closely-coupled post injection with sufficiently short injection duration can increase the load without increasing soot emissions.

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.

Three jet fuel surrogates were compared against their target fuels in a compression ignited optical engine under a range of start-of-injection temperatures and densities. The jet fuel surrogates are representative of petroleum-based Jet-A POSF-4658, natural gas-derived S-8 POSF-4734 and coal-derived Sasol IPK POSF-5642, and were prepared from a palette of n-dodecane, n-decane, decalin, toluene, iso-octane and iso-cetane. Optical chemiluminescence and liquid penetration length measurements as well as cylinder pressure-based combustion analyses were applied to examine fuel behavior during the injection and combustion process. HCHO* emissions obtained from broadband UV imaging were used as a marker for low temperature reactivity, while 309 nm narrow band filtered imaging was applied to identify the occurrence of OH*, autoignition and high temperature reactivity.

Additive manufacturing (AM) of metals is finding numerous applications in automotive industry. In 21st century, aluminum is second to steel in automotive sector, because of its high strength to weight ratio. Hence developing AM for aluminum alloys become necessary to make sure industry gains maximum benefit from AM. This study specifically deals with the manufacturing of Al 7050 alloy, which is quite hardest alloy to manufacture using AM. The ultimate goal is to optimize the laser deposition parameters to deposit defect free Al 7050 alloy on rolled aluminum alloy substrate. Parameter optimization (laser power, powder flow rate, and scanning speed) gets difficult with the presence of various low melting and boiling point alloying elements such as Zn, Mg etc. Numerous other challenges faced while depositing Al 7050 alloy, are also briefly discussed in this article. Microstructural investigation using optical and scanning electron microscopy confirms greater than 99% component density.

Atomization of fuel sprays is a key factor in controlling the combustion quality in the direct-injection engines. In this present work, the effect of saturation ratio (Rs) on the near nozzle spray patterns of ethanol was investigated using an ultra-high speed imaging technique. The Rs range covered both flash-boiling and non-flash boiling regions. Ethanol was injected from a single-hole injector into an optically accessible constant volume chamber at a fixed injection pressure of 40 MPa with different fuel temperatures and back pressures. High-speed imaging was performed using an ultrahigh speed camera (1 million fps) coupled with a long-distance microscope. Under non-flash boiling conditions, the effect of Rs on fuel development was small but observable. Clear fuel collision can be observed at Rs=1.5 and 1.0. Under the flash boiling conditions, near-nozzle spray patterns were significant different from the non-flash boiling ones.

This study investigated driver glances while engaging in infotainment tasks in a stationary vehicle while surrogate driving: watching a driving video recorded from a driver’s viewpoint and projected on a large screen, performing a lane-tracking task, and performing the Tactile Detection Response Task (TDRT) to measure attentional effects of secondary tasks on event detection and response. Twenty-four participants were seated in a 2014 Toyota Corolla production vehicle with the navigation system option. They performed the lane-tracking task using the vehicle’s steering wheel, fitted with a laser pointer to indicate wheel movement on the driving video. Participants simultaneously performed the TDRT and a variety of infotainment tasks, including Manual and Mixed-Mode versions of Destination Entry and Cancel, Contact Dialing, Radio Tuning, Radio Preset selection, and other Manual tasks. Participants also completed the 0-and 1-Back pure auditory-vocal tasks.

A collaborative robot or cobot is a robot that can safely and effectively interact with human workers while performing industrial tasks. The ability to work alongside humans has increased the importance of collaborative robots in the automation industry, as this unique feature is a much needed property among robots nowadays. Rethink Robotics has pioneered this unique discipline by building many robots including the Baxter Robot which is exclusive not only because it has collaborative properties, but because it has two arms working together, each with 7 Degrees Of Freedom. The main goal of this research is to validate the kinematic equations for the Baxter collaborative robot and develop a unified reconfigurable kinematic model for the Left and Right arms so that the calculations can be simplified.