Journal on Autonomous Transportation Systems最新文献

Backdozer: A Backdoor Detection Methodology for DRL-based Traffic Controllers Backdozer：基于 DRL 的交通控制器的后门检测方法

Journal on Autonomous Transportation Systems Pub Date : 2024-01-08 DOI: 10.1145/3639828

Yue Wang, Wenqing Li, Manaar Alam, M. Maniatakos, S. Jabari

{"title":"Backdozer: A Backdoor Detection Methodology for DRL-based Traffic Controllers","authors":"Yue Wang, Wenqing Li, Manaar Alam, M. Maniatakos, S. Jabari","doi":"10.1145/3639828","DOIUrl":"https://doi.org/10.1145/3639828","url":null,"abstract":"While the advent of Deep Reinforcement Learning (DRL) has substantially improved the efficiency of Autonomous Vehicles (AVs), it makes them vulnerable to backdoor attacks that can potentially cause traffic congestion or even collisions. Backdoor functionality is typically implanted by poisoning training datasets with stealthy malicious data, designed to preserve high accuracy on legitimate inputs while inducing desired misclassifications for specific adversary-selected inputs. Existing countermeasures against backdoors predominantly concentrate on image classification, utilizing image-based properties, rendering these methods inapplicable to the regression tasks of DRL-based AV controllers that rely on continuous sensor data as inputs. In this paper, we introduce the first-ever defense against backdoors on regression tasks of DRL-based models, called Backdozer. Our method systematically extracts more abstract features from representations of training data by projecting them into a specific latent subspace and segregating them into several disjoint groups based on the distribution of legitimate outputs. The key observation of Backdozer is that authentic representations for each group reside in one latent subspace, whereas the incorporation of malicious data impacts that subspace. Backdozer optimizes a sample-wise weight vector for the representations capturing the disparities in projections originating from different groups. We experimentally demonstrate that Backdozer can attain (100% ) accuracy in detecting backdoors. We also evaluate its effectiveness against three closely related state-of-the-art defenses.","PeriodicalId":388333,"journal":{"name":"Journal on Autonomous Transportation Systems","volume":"35 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139446455","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}

引用次数: 0

Effect of Wind on Electric Vehicle Energy Consumption: Sensitivity Analyses and Implications for Range Estimation and Optimal Routing 风对电动汽车能源消耗的影响：敏感性分析及其对范围估计和最佳路线选择的影响

Journal on Autonomous Transportation Systems Pub Date : 2023-11-20 DOI: 10.1145/3633460

T. B. Tran, Ilya Kolmanovsky, Erik Biberstein, Omar Makke, Marina Tharayil, Oleg Gusikhin

{"title":"Effect of Wind on Electric Vehicle Energy Consumption: Sensitivity Analyses and Implications for Range Estimation and Optimal Routing","authors":"T. B. Tran, Ilya Kolmanovsky, Erik Biberstein, Omar Makke, Marina Tharayil, Oleg Gusikhin","doi":"10.1145/3633460","DOIUrl":"https://doi.org/10.1145/3633460","url":null,"abstract":"The energy consumption of electric vehicles (EVs) depends on multiple factors. As it affects vehicle range, energy consumption must be accurately predicted. After a summary of the relevant literature, this paper focuses on two sensitivity studies: one on the impact of wind on energy consumption, and the other on the identifiability of wind in the absence of vehicles’ speed and acceleration profiles. The studies show that wind has a significant impact on the energy consumption for a trip, and without high-resolution knowledge of the acceleration and instantaneous velocity, minor variations in the wind condition do not drastically alter the energy consumption distribution. After that, data sources for the information on the wind velocity and direction are discussed. A data-driven approach based on fuzzy set theory is proposed to incorporate wind into the energy prediction; the best model from this approach shows a notable improvement (3.62%) over the currently implemented production-level predictive model for energy consumption on a data set of 35,139 real-world trips; the improvement is even more pronounced (∼ 7%) for trips with more substantial headwind or tailwind level. Recognizing the interplay between range prediction and route selection, we consider a Markov Decision Process (MDP) framework for battery-charge- and travel-time-aware optimal route planning that accounts for the impact of the wind and includes stops at the charging stations. Finally, we propose a framework that includes wind in the operation of EVs, which consists of learning the impact of wind, incorporating wind forecasting into range and energy prediction, and using that prediction to perform optimal routing.","PeriodicalId":388333,"journal":{"name":"Journal on Autonomous Transportation Systems","volume":"37 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139257824","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}

引用次数: 0

Autonomous Vehicles for All? 无人驾驶汽车?

Journal on Autonomous Transportation Systems Pub Date : 2023-07-03 DOI: 10.1145/3611017

S. Khan, M. Salek, Vareva Harris, G. Comert, Eric Morris, M. Chowdhury

{"title":"Autonomous Vehicles for All?","authors":"S. Khan, M. Salek, Vareva Harris, G. Comert, Eric Morris, M. Chowdhury","doi":"10.1145/3611017","DOIUrl":"https://doi.org/10.1145/3611017","url":null,"abstract":"The traditional build-and-expand approach is not a viable solution to keep roadway traffic rolling safely, so technological solutions, such as Autonomous Vehicles (AVs), are favored. AVs have considerable potential to increase the carrying capacity of roads, ameliorate the chore of driving, improve safety, provide mobility for those who cannot drive, and help the environment. However, they also raise concerns over whether they are socially responsible, accounting for issues such as fairness, equity, and transparency. Regulatory bodies have focused on AV safety, cybersecurity, privacy, and legal liability issues, but have failed to adequately address social responsibility. Thus, existing AV developers do not have to embed social responsibility factors in their proprietary technology. Adverse bias may therefore occur in the development and deployment of AV technology. For instance, an artificial intelligence-based pedestrian detection application used in an AV may, in limited lighting conditions, be biased to detect pedestrians who belong to a particular racial demographic more efficiently compared to pedestrians from other racial demographics. Also, AV technologies tend to be costly, with a unique hardware and software setup which may be beyond the reach of lower-income people. In addition, data generated by AVs about their users may be misused by third parties such as corporations, criminals, or even foreign governments. AVs promise to dramatically impact labor markets, as many jobs that involve driving will be made redundant. We argue that the academic institutions, industry, and government agencies overseeing AV development and deployment must act proactively to ensure that AVs serve all and do not increase the digital divide in our society.","PeriodicalId":388333,"journal":{"name":"Journal on Autonomous Transportation Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122899168","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}

引用次数: 0

CAV Traffic Control to Mitigate the Impact of Congestion from Bottlenecks: A Linear Quadratic Regulator Approach and Microsimulation Study 缓解瓶颈拥堵影响的 CAV 交通控制：线性二次调节器方法与微观模拟研究

Journal on Autonomous Transportation Systems Pub Date : 2023-06-17 DOI: 10.1145/3636464

Suyash C. Vishnoi, Junyi Ji, MirSaleh Bahavarnia, Yuhang Zhang, A. Taha, C. Claudel, D. Work

{"title":"CAV Traffic Control to Mitigate the Impact of Congestion from Bottlenecks: A Linear Quadratic Regulator Approach and Microsimulation Study","authors":"Suyash C. Vishnoi, Junyi Ji, MirSaleh Bahavarnia, Yuhang Zhang, A. Taha, C. Claudel, D. Work","doi":"10.1145/3636464","DOIUrl":"https://doi.org/10.1145/3636464","url":null,"abstract":"This work investigates traffic control via controlled connected and automated vehicles (CAVs) using novel controllers derived from the linear-quadratic regulator (LQR) theory. CAV-platoons are modeled as moving bottlenecks impacting the surrounding traffic with their speeds as control inputs. An iterative controller algorithm based on the LQR theory is proposed along with a variant that allows for penalizing abrupt changes in platoon speeds. The controllers use the Lighthill-Whitham-Richards (LWR) model implemented using an extended cell transmission model (CTM) which considers the capacity drop phenomenon for a realistic representation of traffic in congestion. The impact of various parameters of the proposed controller on the control performance is analyzed. The effectiveness of the proposed traffic control algorithms is tested using a traffic control example and compared with existing proportional-integral (PI) and model predictive control (MPC) controllers from the literature. A case study using the TransModeler traffic microsimulation software is conducted to test the usability of the proposed controller as well as existing controllers in a realistic setting and derive qualitative insights. It is observed that the proposed controller works well in both settings to mitigate the impact of the jam caused by a fixed bottleneck. The computation time required by the controller is also small making it suitable for real-time control.","PeriodicalId":388333,"journal":{"name":"Journal on Autonomous Transportation Systems","volume":"31 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139369559","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}

引用次数: 0

Car-following-response Based Vehicle Classification via Deep Learning 基于深度学习的车辆跟随响应分类

Journal on Autonomous Transportation Systems Pub Date : 2023-06-10 DOI: 10.1145/3603369

Tianyi Li, Raphael E. Stern

{"title":"Car-following-response Based Vehicle Classification via Deep Learning","authors":"Tianyi Li, Raphael E. Stern","doi":"10.1145/3603369","DOIUrl":"https://doi.org/10.1145/3603369","url":null,"abstract":"The driving characteristics of individual vehicles in the flow have been shown to influence the aggregate traffic flow characteristics. This is true both for individual human drivers as well as vehicles with some level of automation, such as adaptive cruise control (ACC). Knowledge of the individual constituents of the traffic flow will allow for more advanced traffic control strategies that are tailored to the individual vehicles and their respective driving characteristics. Therefore, there is a need to rapidly assess the car-following dynamics of individual vehicles and identify their level of automation based on their car-following trajectory. This study proposed a time-series based deep learning classification method to classify and identify human-driven and driver-assist vehicles in real-time from driving data. Powered by the recent advances in deep learning, we are able to identify individual vehicles in the flow using only car-following trajectory data and identify both ACC vehicles and human drivers. This paper represents the first step toward assessing vehicle characteristics in real-time. Furthermore, the proposed method can classify vehicles within a couple of seconds with high accuracy. Comparison with existing state-of-the-art methods shows the superior performance of the proposed method.","PeriodicalId":388333,"journal":{"name":"Journal on Autonomous Transportation Systems","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125021256","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}

引用次数: 1

Bridging the Domain Gap between Synthetic and Real-World Data for Autonomous Driving 缩小自动驾驶合成数据与真实世界数据之间的领域差距

Journal on Autonomous Transportation Systems Pub Date : 2023-06-05 DOI: 10.1145/3633463

Xiangyu Bai, Yedi Luo, Le Jiang, Aniket Gupta, Pushyami Kaveti, H. Singh, S. Ostadabbas

{"title":"Bridging the Domain Gap between Synthetic and Real-World Data for Autonomous Driving","authors":"Xiangyu Bai, Yedi Luo, Le Jiang, Aniket Gupta, Pushyami Kaveti, H. Singh, S. Ostadabbas","doi":"10.1145/3633463","DOIUrl":"https://doi.org/10.1145/3633463","url":null,"abstract":"Modern autonomous systems require extensive testing to ensure reliability and build trust in ground vehicles. However, testing these systems in the real-world is challenging due to the lack of large and diverse datasets, especially in edge cases. Therefore, simulations are necessary for their development and evaluation. However, existing open-source simulators often exhibit a significant gap between synthetic and real-world domains, leading to deteriorated mobility performance and reduced platform reliability when using simulation data. To address this issue, our Scoping Autonomous Vehicle Simulation (SAVeS) platform benchmarks the performance of simulated environments for autonomous ground vehicle testing between synthetic and real-world domains. Our platform aims to quantify the domain gap and enable researchers to develop and test autonomous systems in a controlled environment. Additionally, we propose using domain adaptation technologies to address the domain gap between synthetic and real-world data with our SAVeS+ extension. Our results demonstrate that SAVeS+ is effective in helping to close the gap between synthetic and real-world domains and yields comparable performance for models trained with processed synthetic datasets to those trained on real-world datasets of same scale. Finally, we introduce two new autonomy driving datasets with complex scenes, essential sensor data, ground truth and improved imagery. The data is generated using both open-source and commercial simulators and processed through our SAVeS+ domain adaptation pipeline. This paper highlights our efforts to quantify and address the domain gap between synthetic and real-world data for autonomy simulation. By enabling researchers to develop and test autonomous systems in a controlled environment, we hope to bring autonomy simulation one step closer to realization.","PeriodicalId":388333,"journal":{"name":"Journal on Autonomous Transportation Systems","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139370827","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}

引用次数: 0

Theoretical Development and Numerical Validation of an Asymmetric Linear Bilateral Control Model- Case Study for an Automated Truck Platoon 非对称线性双边控制模型的理论发展与数值验证——以自动化卡车排为例

Journal on Autonomous Transportation Systems Pub Date : 2021-12-29 DOI: 10.1145/3592619

M. Salek, M. Chowdhury, Mizanur Rahman, Kakan C. Dey, Md Rafiul Islam

{"title":"Theoretical Development and Numerical Validation of an Asymmetric Linear Bilateral Control Model- Case Study for an Automated Truck Platoon","authors":"M. Salek, M. Chowdhury, Mizanur Rahman, Kakan C. Dey, Md Rafiul Islam","doi":"10.1145/3592619","DOIUrl":"https://doi.org/10.1145/3592619","url":null,"abstract":"In this paper, we theoretically develop and numerically validate an asymmetric linear bilateral control model (LBCM), in which the motion information (e.g., position and speed) from the immediate leading and following vehicles are weighted differently. The novelty of the asymmetric LBCM is that using this model all the follower vehicles in a platoon can adjust their acceleration and deceleration to closely follow a constant desired time gap to improve platoon operational efficiency while maintaining local and string stability. We theoretically analyze the local stability of the asymmetric LBCM using the condition for asymptotic stability of a linear time-invariant system and prove the string stability of the asymmetric LBCM using a space gap error attenuation approach. Then, we evaluate the efficacy of the asymmetric LBCM by simulating a closely coupled cooperative adaptive cruise control (CACC) platoon of fully automated trucks in various non-linear acceleration and deceleration states. We choose automated truck platooning as a case study since heavy-duty trucks experience higher delays and lags in the powertrain system, and limited acceleration and deceleration capabilities than passenger cars. To evaluate the platoon operational efficiency of the asymmetric LBCM, we compare the performance of the asymmetric LBCM to a baseline model, i.e., the symmetric LBCM, for different powertrain delays and lags. Our analyses found that the asymmetric LBCM can handle any combined powertrain delays and lags up to 0.6 sec while maintaining a constant desired time gap during a stable platoon operation, whereas the symmetric LBCM fails to ensure stable platoon operation as well as maintain a constant desired time gap for any combined powertrain delays and lags over 0.2 sec. These findings demonstrate the potential of the asymmetric LBCM in improving platoon operational efficiency and stability of an automated truck platoon.","PeriodicalId":388333,"journal":{"name":"Journal on Autonomous Transportation Systems","volume":"335 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123315310","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}

引用次数: 1