Detection and tracking of on-road moving objects are crucial for vehicle perception. Data Fusion of perception sensors like cameras, lidar, and radar, allows the automotive perception to achieve a certain level of robustness and performance. The efficiency of vehicle perception determines its accuracy to take better decisions related to road safety. In this article, we propose two approaches for the detection and tracking of on-road moving objects by combining information from lidar and radar sensors. In this work, we propose to use a probabilistic occupancy grid for sensor fusion of radar and lidar point cloud, and a modified YOLO DeepSORT approach to detect, classify, and track the moving objects. Using both traditional and deep learning approaches, data fusion allows us to improve the robustness of the automotive perception pipeline. We finally used the nuScenes dataset to evaluate and compare the accuracy of our approaches with state-of-the-art trackers and detectors. We achieved an AMOTA score of 68.3% and a mAP score of 68.7% for the tracking and detection tasks respectively.

<div class="section abstract"><div class="htmlview paragraph">Vehicle electrification is one of the biggest trends in the automotive industry. Without the presence of combustion engine, which is the main noise source on conventional vehicles, noise from other components becomes more perceivable; among these components, the cooling fan is one of the major noise sources, especially during battery charging. The design of cooling fan modules is usually carried out in the early stage before building prototype vehicles. Therefore, understanding the installation effects of the cooling fan on the radiated sound is essential to secure good customer satisfaction. In this study, three different measurement setups of cooling fans are carried out: free field, wall mounted, and in-vehicle measurement. Four cooling fan prototypes with different fan blade designs are used in each measurement. Correlations of these measurements are investigated through comparisons of the measurement results. The installation effects are identified through spectrum difference between free field and in-vehicle measurement. A spectral decomposition method is implemented to enable the separation of source strength and propagation effect in the results. One variable is introduced to represent the installation effects of vehicles tested in the present study.</div></div>

It is agreed upon that labor’s health conditions, as well as environmental pollutions, are broadly influenced by cutting fluids used in machining operations. In order to secure cleaner work parts and environment as well as reduced machining expenses, less fuel consumption is highly recommended. However, the quality of machined parts in the absence of fluid is considered a delicate subject. Under such conditions, the quality of machining process, as well as productivity, could be evaluated by different parameters and criteria including edge and surface quality, chip thickness, cutting force, and tool wear and life, which all seem to be highly influenced by many factors, including lubrication mode (dry and wet) and chip evacuation process. In order to take the benefits while avoiding the disadvantages of lubricated machining, novel lubrication method the so-called minimum quantity lubrication (MQL), which is micro lubrication near dry machining, is proposed. Review of literature denotes that under MQL condition, a low volume of information is available on the effects of mineral and bio-lubricants and various levels of flow rate on machining attributes, in principle average surface roughness (Ra) and chip thickness (hc) when machining aluminum alloys (AAs). To remedy the lack of knowledge determined, the effects of cutting conditions, in principle cutting speed, feed rate, lubricant, and various levels of flow rate on Ra and hc in MQL turning of AA 6061-T6 and AA 7076-T6, are presented. Therefore, three different experimental models, including multiplicative, 2-factor interactions (2FI), and linear models, were used in this study to assess the effects of cutting parameters on the machining outputs. According to experimental observations and despite the design models used, both Ra and hc are statistically significant responses and could be controlled by variation of the cutting parameters used. A strong relationship can be formulated between both responses and experimental parameters used. Although negligible, however, biodegradable cutting fluid with higher viscosity denoted better capability to improve the surface finish. The use of a higher flow rate also led to improved surface finish (up to 50%). It was observed that despite the material used, both flow rate and cutting fluid have insignificant effects on hc.

Within the framework of an integrated product development, the main objective of this study is to assess the influence of shock absorber damping rates on the fatigue of anti-roll bars of a commercial vehicle. In this regard, force and displacement data have been collected in a durability test track with an instrumented bus on curb weight (CW) and gross axle weight rating (GAWR). Based on the theory of fatigue damage accumulation, the durability of each anti-roll bar of a bus (front and rear suspension) was assessed for three different shock absorber damping rates. Statistical significance between different shock absorbers has been identified for both bars on both loading conditions. The results pointed out that, in some cases, a softer damper could reduce by almost half the fatigue life of an anti-roll bar when compared to the same bar with stiffer dampers.

Within the framework of an integrated product development, the main objective of this study is to assess the influence of shock absorber damping rates on the fatigue of anti-roll bars of a commercial vehicle. In this regard, force and displacement data have been collected in a durability test track with an instrumented bus on curb weight (CW) and gross axle weight rating (GAWR). Based on the theory of fatigue damage accumulation, the durability of each anti-roll bar of a bus (front and rear suspension) was assessed for three different shock absorber damping rates. Statistical significance between different shock absorbers has been identified for both bars on both loading conditions. The results pointed out that, in some cases, a softer damper could reduce by almost half the fatigue life of an anti-roll bar when compared to the same bar with stiffer dampers.

Applications for adaptive (sometimes also called smart) Cyber-Physical Systems are blossoming thanks to the large volumes of data, sensed in a continuous fashion, in large distributed systems. The benefits of these applications come nonetheless with a price: the need for jointly addressing challenges in efficient data communication and analysis (among others). The goal of the DRIVEN framework, presented here, is to address these challenges for a data gathering and distance-based clustering tool in the context of vehicular networks. Because of the limited communication bandwidth (compared to the volume of sensed data) of vehicular networks and the monetary costs of data transmission, the intuition behind DRIVEN is to avoid gathering the data to be clustered in a raw format from each vehicle, but rather to allow for a streaming-based error-bounded approximation, through Piecewise Linear Approximation, to compress the volumes of data to be gathered. At the same time, rather than relying on a batch-based clustering algorithm that requires all the data to be first gathered (and then clustered), DRIVEN relies on and extends a streaming-based clustering algorithm that leverages the inherent ordering of the spatial and temporal data being collected, to perform the clustering in an online fashion, while data is being retrieved. As we show, based on our prototype implementation using Apache Flink and our evaluation with real-world data such as GPS and LiDAR, the accuracy loss for the clustering performed on the reconstructed data can be small, even when the raw data is compressed to 10-35% of its original size, and the transferring of data itself can be completed in up to one-tenth of the duration observed when gathering raw data.

The combustion processes of three injection strategies in a light-duty (LD) diesel engine at a medium load point are captured with a high speed video camera. A double-pilot/main/single-post injection strategy representative of a LD Euro 6 calibration is considered as the reference. There is a modest temporal spacing (dwell) after the first pilot (P1) and second pilot (P2). A second strategy, A, adds a third pilot (P3). The dwell after both P2 and P3 are several times shorter than in the reference strategy. A third strategy, B, further reduces all dwells. Each injection has its own associated local peak in the heat release rate (HRR) following some ignition delay. Between these peaks lie local minima, or dips. In all three cases, the fuel from P1 combusts as a propagating premixed flame. For all strategies, the ignition of P2 primarily occurs at its interface with the existing combustion regions. Extinguishing of the prevailing combustion by the fuel jets of later injections is noted in all strategies. This phenomenon is confirmed by comparing the timing of each fuel injection with the dips in the HRR and spatial luminescence over time. These dips after each injection are larger than would be expected by the cooling effect of the injected fuel alone. Furthermore, not all dips in the HRR are the result of this extinguishing, and it would not have been possible to determine if the dips are due to this extinguishing or a simple exhaustion of available fuel without this optical investigation. Even if the precise hydraulic injection timing can be known, knowledge of the spatial relationship of the injected fuel and prevailing combustion is necessary. (Less)

Given the importance of the road transportation and its correct maintenance, the assessment of the real loads applied to the pavement proved to be a relevant subject. On the basis of an experimental methodology and a statistical analysis, this work quantified and evaluated the vertical loads applied to the pavement by the wheels of a commercial vehicle during pothole events. As a first experimental approach, the main objective of this study is to investigate the isolated influence of the vehicle's speed and the pothole's depth on the vertical load. The results suggested that the pothole's depth is a parameter that directly influences the vertical load, while the vehicle's speed is more likely to impact in the contrasts at low velocities. Although further studies are necessary, the obtained results emphasise the importance of considering the loads imposed by transient events (such as potholes) on the project of pavement roads and heavy vehicles.

The concept of double compression, and double expansion engine (DCEE) for improving the efficiency of piston reciprocating engines was introduced in SAE Paper 2015-01-1260. This engine configuration has separate high, and low pressure units thereby effectively reducing friction losses for high effective compression ratios. The presence of an additional expander stage also theoretically allows an extra degree of freedom to manipulate the combustion heat release rate so as to achieve better optimum between heat transfer, and friction losses. This paper presents a 1-D modeling study of the engine concept in GT-Power for assessing the sensitivity of engine losses to heat release rate. The simulations were constrained by limiting the maximum pressure to 300 bar. The maximum motoring pressure was varied by, (a) constraining the compression ratio of the high pressure unit, and adapting the low pressure unit accordingly, (b) changing the compression ratio of the high pressure unit with a constant geometry for the low pressure unit. The effect of maximum pressure on the brake thermal efficiency was also investigated. A final set of simulations also compared the heat release rate of the model in SAE Paper 2015-01-1260 and two other models with the same start and end of combustion. The simulations were done at engine speed of 1900 rpm, and lambda 3. The results indicate the relative insensitivity of this concept engine's performance to the heat release rate when the maximum pressure constrained to a constant value of 300 bar, or even when lowering peak pressure down to 200 bar due to reduction in heat loss, and friction losses. The major limitations of the present study was the adoption of a constant convection heat loss multiplier for all the cases, and a simplistic friction model. (Less)