2022 IEEE 1st International Conference on Cognitive Mobility (CogMob)最新文献

{"title":"Traffic Sign Detection and Recognition Using YOLOv5 and Its Versions","authors":"Aaron Joaquin Lebumfacil, P. Abu","doi":"10.1109/CogMob55547.2022.10118112","DOIUrl":"https://doi.org/10.1109/CogMob55547.2022.10118112","url":null,"abstract":"A Traffic Sign Detection and Recognition (TSDR) System, which helps navigate vehicles through computer vision and human-machine communication, has to perform quickly as vehicles using them travel at high speeds. During this study, a speedy one-stage detector such as YOLOv5, a deep learning model, was chosen to dive into. This study explores creating a TSDR model by comparing four different versions of YOLOv5, namely YOLOv5 Nano, Small, Medium, and Large. This study was accomplished by first creating a new traffic sign dataset. The four versions of the YOLOv5 algorithm were then trained with a 75–25 train validation split, and 24 models were created. Afterwards, the models were tested on a test set, and their metrics were tallied. Results showed that YOLOv5 Medium and Large offer a 10% increase in accuracy performance when compared to YOLOv5 Small, but due to the slower detection speed of YOLOv5 Large, the YOLOv5 Medium models are a better fit when it comes to the detection of traffic signs when prepared by a relatively small dataset. This study provides an overview of the performance of the different YOLOv5 versions in traffic sign detection and recognition that aims to contribute to the improvement of traffic sign detectors.","PeriodicalId":430975,"journal":{"name":"2022 IEEE 1st International Conference on Cognitive Mobility (CogMob)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134618465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Noise and vibration test of electric drive cars","authors":"Márton Zöldy, F. Dömötör","doi":"10.1109/CogMob55547.2022.10118037","DOIUrl":"https://doi.org/10.1109/CogMob55547.2022.10118037","url":null,"abstract":"Electric drive vehicles play a growing role in today's society. More and more people are aware of their environmental advantages and drive them day by day. However, electric vehicles might have disadvantages, too. The authors of this paper have the goal to study the noise, vibration and harshness (NVH) features. For this purpose two electric drive cars have been tested running on a test pad. During the test vibration and noise were measured at various speeds at several locations both on the drive chain and inside the passenger cabin. Results are shown on individual vibration spectra and waterfall diagrams. It was found, that both the vibration severity and the noise depend very much on the speed.","PeriodicalId":430975,"journal":{"name":"2022 IEEE 1st International Conference on Cognitive Mobility (CogMob)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127054993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial Neural Network Based Prediction of Engine Combustion and Emissions from a High Resolution Dataset","authors":"Márton Virt, M. Zöldy","doi":"10.1109/CogMob55547.2022.10118200","DOIUrl":"https://doi.org/10.1109/CogMob55547.2022.10118200","url":null,"abstract":"Development of new advanced fuels require more efficient methods to reduce costs. Artificial neural networks can be used in the fuel designing process, but the dataset creation can be expensive. This paper aims to create highly accurate multilayer perceptron type artificial neural network models to predict a medium duty commercial diesel engine's combustion and emission properties. A high-resolution dataset with 6277 samples was used for the training, and the resulted models will be used for future researches on cost optimization. The NOx and PM emission, peak combustion temperature, peak pressure rise rate, indicated mean effective pressure, start of combustion, duration of combustion, ignition delay, brake specific fuel consumption and brake thermal efficiency was predicted from the engine speed, torque and high-pressure exhaust gas recirculation valve position. First, the cost-efficient method of high resolution dataset creation is described, then the results of the predictive models are presented. The mean squared error for the scaled dataset, and the root-mean-square error, mean average percentage error, correlation coefficient and determination coefficient for the unscaled dataset was used to evaluate the performance of the resulted models. In addition the most informative prediction error plots are also presented. It was found that the high-resolution dataset resulted really accurate models that can be used for continuing the cost optimization research.","PeriodicalId":430975,"journal":{"name":"2022 IEEE 1st International Conference on Cognitive Mobility (CogMob)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130893596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Defining metrics for scenario-based evaluation of autonomous vehicle models","authors":"Peter Farkaš, Lászlo Szőke, S. Aradi","doi":"10.1109/CogMob55547.2022.10117768","DOIUrl":"https://doi.org/10.1109/CogMob55547.2022.10117768","url":null,"abstract":"The paper deals with the evaluation of autonomous vehicles along with the quantification of their behavior and maneuvers. The article outlines the positive aspects of autonomy and lists several arguments in their favor, e.g. convenience and efficiency considerations. Furthermore, it also addresses the associated difficulties including the feasibility of road testing and the establishment of appropriate simulations. The current work aims to define methods providing objective indicators to compare algorithms solving the complex tasks of road transport. Rule-based, supervised and reinforcement learning control models, test environments, accelerated test methods and assessment indicators of the corresponding literature are reviewed and evaluated. After investigating the different metrics, we formulate an evaluation framework that can be applied in the development and assessment process of new artificial intelligence controlled models. As an outcome of this work, we aim to aid a missing sector in the field of autonomous driving function development by collecting and defining metrics that intend to help qualitatively evaluate and compare algorithms. The key aspect during the definition of the suggested method was to ensure its extensive applicability by selecting only metrics that can be obtained from the already installed sensors of the vehicles. Additionally, we also assess multiple agents to observe how their behavior compares and whether the proposed metrics reflect the expected behavior.","PeriodicalId":430975,"journal":{"name":"2022 IEEE 1st International Conference on Cognitive Mobility (CogMob)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133037276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Overview of the Relationship between Human Spatial Abilities and GPS Usage","authors":"Borbóla Berki","doi":"10.1109/CogMob55547.2022.10117612","DOIUrl":"https://doi.org/10.1109/CogMob55547.2022.10117612","url":null,"abstract":"GPS-based (Global Positioning System) navigation is a great help when traveling to new places. Although, many of us have experienced the feeling that after driving across town with a GPS device, that we cannot retrieve the road and we feel that without the GPS we will not be able to find our way back. This paper presents human spatial abilities and spatial orientation. Then shows the state of the art in the empirical research regarding the effects of using GPS. Then presents some methods and design principles that aim to overcome this detrimental effect. For example, raising the awareness of the drivers and users, to be more conscious when they decide whether they need navigational aid or not. Furthermore, the interaction design of these devices could also initiate actively dealing with the information to enhance active encoding. In addition, by integrating landmarks as reference points in the GPS aids, the users are also encouraged to pay more attention to the environment.","PeriodicalId":430975,"journal":{"name":"2022 IEEE 1st International Conference on Cognitive Mobility (CogMob)","volume":"710 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132982251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Motorcycle rider posture measurement for on-road experiments on rider intention detection","authors":"Karl Ludwig Stolle, A. Wahl, Stephan Schmidt","doi":"10.1109/CogMob55547.2022.10118004","DOIUrl":"https://doi.org/10.1109/CogMob55547.2022.10118004","url":null,"abstract":"Motorcycle riders represent a highly vulnerable group of road users with high risk of heavy injuries and fatalities per distance traveled. Hence there is an ongoing demand for the development of assistance systems to improve riding safety. Collecting information about a rider's intention – the desired maneuver to carry out or trajectory to travel through – is considered as an enabler for new systems that can warn or intervene before or assist in dangerous driving situations. The observation of the rider's posture is necessary for a holistic understanding of the human-machine interface as riders typically move their body during riding for various reasons. The authors develop and test an on-road capable measurement system of high accuracy and robustness for the detection of rider upper body posture in riding experiments as off-the-shelf systems are not existent. AprilTag optical markers applied to the back of the rider that are filmed by a camera from behind prove to be superior to other concepts tested. Two new methods named subarea and dynamic frame rate evaluation are introduced to reduce computational effort from raw video data to rider posture information. First measurement results from on-road riding are presented and reveal positional errors below 1 cm or 3 deg rider lean angle. Based on the data that is collected in an ongoing riding study, the meaning of posture information for the identification of rider behavior and intention will be further investigated.","PeriodicalId":430975,"journal":{"name":"2022 IEEE 1st International Conference on Cognitive Mobility (CogMob)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124905125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Closer-to-reality artificial ageing of engine oils with implemented nitration","authors":"A. Agocs, C. Besser, M. Frauscher","doi":"10.1109/CogMob55547.2022.10117853","DOIUrl":"https://doi.org/10.1109/CogMob55547.2022.10117853","url":null,"abstract":"Internal combustion engine development is predominantly focusing on emission aspects, where improvements are often achieved by turbocharged engines and higher compression ratios. These trends combined with increasingly higher oil change intervals require increasing stability of engine oils, especially since lubricant condition and tribological performance are strongly interrelated. Various artificial alteration methods have been developed to simulate lubricant degradation in the laboratory, however, nitration as a degradation mechanism is often not considered in standardized tests. Nitration is especially relevant, as it might be tied to emission values and petrol and diesel passenger vehicles show significant differences in this regard. Furthermore, the provision of close-to-reality, defined and reproducible test oils in large quantities are necessary to be able to perform component bench tests or engine dynamometer tests which can reliably predict on performance and lifetime of engine components. This study presents a novel artificial alteration method, where test oils can be produced for engine dynamometer testing or component testing during the development phase. This method is capable of close-to-reality simulation of additive degradation, nitration, oxidation, and various further degradation steps of engine oils in batches up to 200 l. Comparability of various chemical parameters of used oils from a modern turbocharged gasoline passenger car with the artificially altered oils is demonstrated","PeriodicalId":430975,"journal":{"name":"2022 IEEE 1st International Conference on Cognitive Mobility (CogMob)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115428141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Long term utilisation effect on vehicle battery performance","authors":"Dávid Tollner, M. Zöldy","doi":"10.1109/CogMob55547.2022.10118087","DOIUrl":"https://doi.org/10.1109/CogMob55547.2022.10118087","url":null,"abstract":"E-mobility is and will be part of the mobility in the third millennium. As the other potential solutions it has several advantages and critical areas. Our research is focusing one of the critical dimensions: the battery and its degradation during the utilization. Based on considering the typical utilisation of electric vehicles a test route was designed. Theoretical calculations were validated in a real word test of a vehicle fleet. The results showed that batteries lose 4% of their capacity in 10,000 km and almost 14% in 45,000 km.","PeriodicalId":430975,"journal":{"name":"2022 IEEE 1st International Conference on Cognitive Mobility (CogMob)","volume":"177 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116531804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Examination of hydraulic hybrid drive unit for PHHV","authors":"P. Harth","doi":"10.1109/CogMob55547.2022.10118100","DOIUrl":"https://doi.org/10.1109/CogMob55547.2022.10118100","url":null,"abstract":"Nowadays, hybrid drive technology is one of the most significant research fields that has attracted much attention in the last decades. Hydraulic hybrid technologies can improve the fuel (electric) economy by recovering energy. In this paper, a design of a test bench for a hybrid drive unit is presented. This hybrid unit makes the improvement of its efficiency possible, approaching the total efficiency of the vehicle from drive unit to wheel. The presented development contains an e-motors and hydraulic pump/motor (HPM) unit. The experimental hybrid drive unit is designed to reach the highest efficiency during vehicle launching, acceleration and regenerative braking.","PeriodicalId":430975,"journal":{"name":"2022 IEEE 1st International Conference on Cognitive Mobility (CogMob)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129313569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Toward a Resilient Automotive Service-Oriented Architecture by using Dynamic Orchestration","authors":"Marc Schindewolf, D. Grimm, Christian Lingor, E. Sax","doi":"10.1109/CogMob55547.2022.10118016","DOIUrl":"https://doi.org/10.1109/CogMob55547.2022.10118016","url":null,"abstract":"Modern software development in vehicles is focusing on a service-oriented approach. Structuring software systems into self-sufficient software components that provide specific capabilities to the overall system allow software engineers to make changes to vehicle functions more granularly. The decentralized SOA approach offers advantages, as it enables loose coupling between components instead of statically implementing their relationships. But with the increasing degree of autonomy and dynamism of the vehicle's software, the system's safety and security requirements are also growing. Preventive measures will no longer suffice here; instead, resilient systems are required that provide a minimum level of safety even in the event of an unexpected problem. Today, a SOA's services are assigned to a hardware platform during development and executed there, which lacks being able to react to problems or changing requirements. One possibility for being more flexible at runtime, is the use of an orchestrator, which dynamically allocates resources to services while retaining the advantages of a loosely coupled architecture. This paper proposes a methodology for implementing a resilient vehicular electronic architecture based on orchestrating containerized software. To avoid a single point of failure, a distributed approach for a dynamic orchestrator that deploys the software to appropriate execution platforms is proposed. The orchestrator makes its deployment decisions based on specifiable parameters (e.g., required RAM, GPU) and dependencies between services. The decision process adapts to changes in these factors dynamically, making the system able to react to external influences. The concept differentiates itself from other approaches by tracking dynamic changes to specified parameters and easily extensible interfaces for new parameters or requirements. In addition, the concept introduces a priority metric to describe the impact of services in the system and models how this metric is inherited through dependencies. The concept is evaluated qualitatively by three exemplary use cases, demonstrating the effect of dynamic orchestration on the resilience of the vehicle.","PeriodicalId":430975,"journal":{"name":"2022 IEEE 1st International Conference on Cognitive Mobility (CogMob)","volume":"19 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133017136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}