Pub Date : 2020-02-01DOI: 10.1109/metrocad48866.2020.00004
{"title":"MetroCAD 2020 TOC","authors":"","doi":"10.1109/metrocad48866.2020.00004","DOIUrl":"https://doi.org/10.1109/metrocad48866.2020.00004","url":null,"abstract":"","PeriodicalId":117440,"journal":{"name":"2020 International Conference on Connected and Autonomous Driving (MetroCAD)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124981953","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}
Pub Date : 2020-02-01DOI: 10.1109/MetroCAD48866.2020.00016
Tian Wu, Yifan Wang, Weisong Shi, Joshua Lu
Autonomous driving has been a hot topic recently, so many industrial and academic groups are putting much engineering and research efforts into this topic. However, it is difficult for most researchers or students to afford a car as a research platform to conduct experiments for autonomous driving. Further, we believe that only when more people have the chance to make contributions will this area be more prosperous. Therefore, in this paper, we present HydraMini, an affordable experimental research and education platform supporting the experiments from hardware systems to vision algorithms, and its high flexibility makes it easily extended and modified. It is equipped with the Xilinx PYNQ-Z2 board as the computing platform, which deploys the Deep Learning Processing Unit (DPU) in FPGA to accelerate the deep learning inference. It also provides useful tools like a simulator for model training and testing in a virtual environment to facilitate the use of HydraMini. Our platform will help researchers and students build and test their own solutions for autonomous driving algorithms and systems easily and efficiently.
自动驾驶是近年来的一个热门话题，许多行业和学术团体都在这一领域投入了大量的工程和研究努力。然而，对于大多数研究人员或学生来说，很难负担得起一辆汽车作为进行自动驾驶实验的研究平台。此外，我们认为只有更多的人有机会做出贡献，这个地区才会更加繁荣。因此，在本文中，我们提出了HydraMini，一个经济实惠的实验研究和教育平台，支持从硬件系统到视觉算法的实验，其高灵活性使其易于扩展和修改。采用Xilinx PYNQ-Z2板作为计算平台，在FPGA中部署深度学习处理单元(Deep Learning Processing Unit, DPU)，加速深度学习推理。它还提供了有用的工具，如模拟器，用于在虚拟环境中进行模型训练和测试，以促进HydraMini的使用。我们的平台将帮助研究人员和学生轻松高效地构建和测试他们自己的自动驾驶算法和系统解决方案。
{"title":"HydraMini: An FPGA-based Affordable Research and Education Platform for Autonomous Driving","authors":"Tian Wu, Yifan Wang, Weisong Shi, Joshua Lu","doi":"10.1109/MetroCAD48866.2020.00016","DOIUrl":"https://doi.org/10.1109/MetroCAD48866.2020.00016","url":null,"abstract":"Autonomous driving has been a hot topic recently, so many industrial and academic groups are putting much engineering and research efforts into this topic. However, it is difficult for most researchers or students to afford a car as a research platform to conduct experiments for autonomous driving. Further, we believe that only when more people have the chance to make contributions will this area be more prosperous. Therefore, in this paper, we present HydraMini, an affordable experimental research and education platform supporting the experiments from hardware systems to vision algorithms, and its high flexibility makes it easily extended and modified. It is equipped with the Xilinx PYNQ-Z2 board as the computing platform, which deploys the Deep Learning Processing Unit (DPU) in FPGA to accelerate the deep learning inference. It also provides useful tools like a simulator for model training and testing in a virtual environment to facilitate the use of HydraMini. Our platform will help researchers and students build and test their own solutions for autonomous driving algorithms and systems easily and efficiently.","PeriodicalId":117440,"journal":{"name":"2020 International Conference on Connected and Autonomous Driving (MetroCAD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124674031","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}
Pub Date : 2020-02-01DOI: 10.1109/MetroCAD48866.2020.00013
Jade Zsiros, Brian Blalock, D. Craig, Sudharsan Vaidhun, Alexander Wang, Zhishan Guo
In this demonstration, we present a generalized platform customized to suit the needs of a fast power-efficient and autonomous delivery system. As an application demonstration, we deployed a mapping and localization system based on a combination of sensor sources. An online navigation algorithm utilizes the map information to deliver to a destination in the mapped area.
{"title":"GARDS: Generalized Autonomous Robotic Delivery System","authors":"Jade Zsiros, Brian Blalock, D. Craig, Sudharsan Vaidhun, Alexander Wang, Zhishan Guo","doi":"10.1109/MetroCAD48866.2020.00013","DOIUrl":"https://doi.org/10.1109/MetroCAD48866.2020.00013","url":null,"abstract":"In this demonstration, we present a generalized platform customized to suit the needs of a fast power-efficient and autonomous delivery system. As an application demonstration, we deployed a mapping and localization system based on a combination of sensor sources. An online navigation algorithm utilizes the map information to deliver to a destination in the mapped area.","PeriodicalId":117440,"journal":{"name":"2020 International Conference on Connected and Autonomous Driving (MetroCAD)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124783658","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}
Pub Date : 2020-02-01DOI: 10.1109/MetroCAD48866.2020.00012
Jeonghui Yeom, Sukhyun Seo
In-vehicle communication uses CAN Bus, and for this, communication speed and security are important. Since the current CAN communication is used without encryption, many cases have been reported of vehicle hacking over time. With the advent of autonomous driving and connected cars, vehicles no longer remain independent; they can be invaded from the outside and personal information such as vehicle location and driving habits can be accessed through the vehicle, which poses a serious threat to personal privacy and life. Therefore, communication data must be encrypted in order to increase the security of the communication. In this paper, data frames are encrypted using a shuffling algorithm in the CAN communication system environment. To put it more precisely, the data frame is divided into bits and structured into blocks, which are then shuffled for data hiding. This method determines the level of obfuscation based on blockage and shuffle criteria. The encryption time was measured by changing both. This suggest ways to increase the security and communication speed in the vehicle.
{"title":"A Methodology of CAN Communication Encryption Using a shuffling algorithm","authors":"Jeonghui Yeom, Sukhyun Seo","doi":"10.1109/MetroCAD48866.2020.00012","DOIUrl":"https://doi.org/10.1109/MetroCAD48866.2020.00012","url":null,"abstract":"In-vehicle communication uses CAN Bus, and for this, communication speed and security are important. Since the current CAN communication is used without encryption, many cases have been reported of vehicle hacking over time. With the advent of autonomous driving and connected cars, vehicles no longer remain independent; they can be invaded from the outside and personal information such as vehicle location and driving habits can be accessed through the vehicle, which poses a serious threat to personal privacy and life. Therefore, communication data must be encrypted in order to increase the security of the communication. In this paper, data frames are encrypted using a shuffling algorithm in the CAN communication system environment. To put it more precisely, the data frame is divided into bits and structured into blocks, which are then shuffled for data hiding. This method determines the level of obfuscation based on blockage and shuffle criteria. The encryption time was measured by changing both. This suggest ways to increase the security and communication speed in the vehicle.","PeriodicalId":117440,"journal":{"name":"2020 International Conference on Connected and Autonomous Driving (MetroCAD)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126474500","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}
Pub Date : 2020-02-01DOI: 10.1109/metrocad48866.2020.00007
{"title":"Sponsors: MetroCAD 2020","authors":"","doi":"10.1109/metrocad48866.2020.00007","DOIUrl":"https://doi.org/10.1109/metrocad48866.2020.00007","url":null,"abstract":"","PeriodicalId":117440,"journal":{"name":"2020 International Conference on Connected and Autonomous Driving (MetroCAD)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116738320","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}
Pub Date : 2020-02-01DOI: 10.1109/MetroCAD48866.2020.00017
Luodai Yang, Qian Jia, Ruijun Wang, Jie Cao, Weisong Shi
Today’s autonomous vehicles will deploy multiple sensors to achieve safe and reliable navigation and precise perception of the environment. Although multiple sensors can be advantageous in terms of providing a robust and complete description of the surrounding area, the synchronization of multi-sensors in real-time processing is extremely important. When data is synchronized, primary functional systems such as localization, perception, planning, and control, will all benefit. In this paper, we proposed a synchronized data illustration and collection method to assist the data processing applications for autonomous driving. Our proposed solution among different sensors can be directly deployed on autonomous vehicles for data integration and environment analysis to support the driving model construction. The experimental results validate that our proposed method can present a 360◦ synchronized view while providing the capability of real-time scanning with up to 80% reduced latency.
{"title":"HydraView: A Synchronized 360◦-View of Multiple Sensors for Autonomous Vehicles","authors":"Luodai Yang, Qian Jia, Ruijun Wang, Jie Cao, Weisong Shi","doi":"10.1109/MetroCAD48866.2020.00017","DOIUrl":"https://doi.org/10.1109/MetroCAD48866.2020.00017","url":null,"abstract":"Today’s autonomous vehicles will deploy multiple sensors to achieve safe and reliable navigation and precise perception of the environment. Although multiple sensors can be advantageous in terms of providing a robust and complete description of the surrounding area, the synchronization of multi-sensors in real-time processing is extremely important. When data is synchronized, primary functional systems such as localization, perception, planning, and control, will all benefit. In this paper, we proposed a synchronized data illustration and collection method to assist the data processing applications for autonomous driving. Our proposed solution among different sensors can be directly deployed on autonomous vehicles for data integration and environment analysis to support the driving model construction. The experimental results validate that our proposed method can present a 360◦ synchronized view while providing the capability of real-time scanning with up to 80% reduced latency.","PeriodicalId":117440,"journal":{"name":"2020 International Conference on Connected and Autonomous Driving (MetroCAD)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123494848","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}
Pub Date : 2020-02-01DOI: 10.1109/MetroCAD48866.2020.00015
Houchao Gan, Chen Liu
Boosted by the evolution of machine learning technology, large amount of data and advanced computing system, neural networks have achieved state-of-the-art performance that even exceeds human capability in many applications [1] [2] . However, adversarial attacks targeting neural networks have demonstrated detrimental impact in autonomous driving [3] . The adversarial attacks are capable of arbitrarily manipulating the neural network classification results with different input data which is non-perceivable to human.
{"title":"An Autoencoder Based Approach to Defend Against Adversarial Attacks for Autonomous Vehicles","authors":"Houchao Gan, Chen Liu","doi":"10.1109/MetroCAD48866.2020.00015","DOIUrl":"https://doi.org/10.1109/MetroCAD48866.2020.00015","url":null,"abstract":"Boosted by the evolution of machine learning technology, large amount of data and advanced computing system, neural networks have achieved state-of-the-art performance that even exceeds human capability in many applications [1] [2] . However, adversarial attacks targeting neural networks have demonstrated detrimental impact in autonomous driving [3] . The adversarial attacks are capable of arbitrarily manipulating the neural network classification results with different input data which is non-perceivable to human.","PeriodicalId":117440,"journal":{"name":"2020 International Conference on Connected and Autonomous Driving (MetroCAD)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132713375","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}
Pub Date : 2020-02-01DOI: 10.1109/MetroCAD48866.2020.00009
Yunyi Jia, B. Ayalew
Automated vehicles have immense potentials for improving the safety, efficiency and environmental problems in our existing transportation systems. Despite the tremendous ongoing efforts from both industry and academia, fully autonomous vehicles have not yet been widely deployed in public traffic. In the foreseeable future, automated vehicles will very likely be expected to operate in traffic that involve heterogeneous agents including automated vehicles, human-driven vehicles and pedestrians. Such heterogeneity will bring new challenges to the safety of the traffic system. This paper reviews some existing works related to heterogeneous traffic systems and presents a vision of cyber-human-physical heterogeneous traffic systems that can substantially enhance overall safety.
{"title":"Cyber-Human-Physical Heterogeneous Traffic Systems for Enhanced Safety","authors":"Yunyi Jia, B. Ayalew","doi":"10.1109/MetroCAD48866.2020.00009","DOIUrl":"https://doi.org/10.1109/MetroCAD48866.2020.00009","url":null,"abstract":"Automated vehicles have immense potentials for improving the safety, efficiency and environmental problems in our existing transportation systems. Despite the tremendous ongoing efforts from both industry and academia, fully autonomous vehicles have not yet been widely deployed in public traffic. In the foreseeable future, automated vehicles will very likely be expected to operate in traffic that involve heterogeneous agents including automated vehicles, human-driven vehicles and pedestrians. Such heterogeneity will bring new challenges to the safety of the traffic system. This paper reviews some existing works related to heterogeneous traffic systems and presents a vision of cyber-human-physical heterogeneous traffic systems that can substantially enhance overall safety.","PeriodicalId":117440,"journal":{"name":"2020 International Conference on Connected and Autonomous Driving (MetroCAD)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128132959","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}
Pub Date : 2020-02-01DOI: 10.1109/MetroCAD48866.2020.00014
Liangkai Liu, Yongtao Yao, Ruijun Wang, Baofu Wu, Weisong Shi
The great success of artificial intelligence and edge computing technology has largely promote the development of connected and autonomous driving. However, owing to the missing of the experiment platform for Road-Side Unit (RSU), majority of research works are either simulation based task offloading or commercial equipment's based scheduling design. The fundamental challenge of how to co-design the communication and computation in a practical system is not tackled.In this paper, we proposed Equinox, which is our design of the rode-side edge computing experimental platform for connected and autonomous vehicles. With communication, data, as well as the computation taken into consideration, Equinox provides stable and sufficient communication based on a combination of WiFi, LTE, and DSRC. Also, Equinox guarantees reliable and flexible data collection, data storage, and efficient data processing.
{"title":"Equinox: A Road-Side Edge Computing Experimental Platform for CAVs","authors":"Liangkai Liu, Yongtao Yao, Ruijun Wang, Baofu Wu, Weisong Shi","doi":"10.1109/MetroCAD48866.2020.00014","DOIUrl":"https://doi.org/10.1109/MetroCAD48866.2020.00014","url":null,"abstract":"The great success of artificial intelligence and edge computing technology has largely promote the development of connected and autonomous driving. However, owing to the missing of the experiment platform for Road-Side Unit (RSU), majority of research works are either simulation based task offloading or commercial equipment's based scheduling design. The fundamental challenge of how to co-design the communication and computation in a practical system is not tackled.In this paper, we proposed Equinox, which is our design of the rode-side edge computing experimental platform for connected and autonomous vehicles. With communication, data, as well as the computation taken into consideration, Equinox provides stable and sufficient communication based on a combination of WiFi, LTE, and DSRC. Also, Equinox guarantees reliable and flexible data collection, data storage, and efficient data processing.","PeriodicalId":117440,"journal":{"name":"2020 International Conference on Connected and Autonomous Driving (MetroCAD)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125083299","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}
Pub Date : 2020-02-01DOI: 10.1109/MetroCAD48866.2020.00018
Shahid Malik, Weiqing Sun
We are expecting to see hundreds of thousands of smart connected cars in a matter of months from now until they replace the legacy vehicles. Connectivity is at the core of every such vehicle, with a large number of computer systems to monitor and control the vehicle. Cyber-security threats are on the rise and manufacturers are facing a unique level of challenge given the increasing complexity of the vehicles. Consumers need to understand the security implications of connected and autonomous vehicles before they can drive them with confidence. This paper reviews most common cyber attacks that hackers use to disrupt and compromise connected and autonomous vehicles. In particular, we use the threat modeling to analyze and identify the most significant threats. Moreover, we simulated the impact of those cyber attacks to demonstrate the significance of the cyber threats against connected and autonomous vehicles.
{"title":"Analysis and Simulation of Cyber Attacks Against Connected and Autonomous Vehicles","authors":"Shahid Malik, Weiqing Sun","doi":"10.1109/MetroCAD48866.2020.00018","DOIUrl":"https://doi.org/10.1109/MetroCAD48866.2020.00018","url":null,"abstract":"We are expecting to see hundreds of thousands of smart connected cars in a matter of months from now until they replace the legacy vehicles. Connectivity is at the core of every such vehicle, with a large number of computer systems to monitor and control the vehicle. Cyber-security threats are on the rise and manufacturers are facing a unique level of challenge given the increasing complexity of the vehicles. Consumers need to understand the security implications of connected and autonomous vehicles before they can drive them with confidence. This paper reviews most common cyber attacks that hackers use to disrupt and compromise connected and autonomous vehicles. In particular, we use the threat modeling to analyze and identify the most significant threats. Moreover, we simulated the impact of those cyber attacks to demonstrate the significance of the cyber threats against connected and autonomous vehicles.","PeriodicalId":117440,"journal":{"name":"2020 International Conference on Connected and Autonomous Driving (MetroCAD)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132314572","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：