ACM Journal on Autonomous Transportation Systems最新文献

{"title":"D4: Dynamic, Decentralized, Distributed, Delegation-Based Network Control and Its Applications to Autonomous Vehicles","authors":"Anuj Kaul, Katia Obraczka, Ramon Fontes, Thierry Turletti","doi":"10.1145/3644079","DOIUrl":"https://doi.org/10.1145/3644079","url":null,"abstract":"Connected autonomous vehicles technology are expected to be an important component of Intelligent Transportation Systems (ITS). Several relevant industry standards are being created to prepare for the maturity of connected vehicles with the help of artificial intelligence, cognitive methods, software-hardware and sensor platforms. One of the significant challenges raised by connected vehicles is how the underlying communication infrastructure will be able to efficiently support them. In this paper, we propose the Dynamic, Decentralized, Distributed, Delegation-based (D4) network control plane architecture which aims at providing adequate communication support for connected vehicles. To our knowledge, D4 is the first framework to support on-demand network control decentralization. At its core, D4’s flexible network control delegation framework allows network control to be dynamically distributed on demand to address quality-of-service requirements of different connected vehicle services and applications. We demonstrate the benefits of D4 through a proof-of-concept prototype running on a fully reproducible emulation platform. Experimental results using a variety of real-world scenarios demonstrate that D4 delivers lower latency with minimal additional overhead. We also showcase the benefits of D4 when compared to traditional vehicular ad-hoc network (VANET) approaches.","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"61 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139843414","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":"D4: Dynamic, Decentralized, Distributed, Delegation-Based Network Control and Its Applications to Autonomous Vehicles","authors":"Anuj Kaul, Katia Obraczka, Ramon Fontes, Thierry Turletti","doi":"10.1145/3644079","DOIUrl":"https://doi.org/10.1145/3644079","url":null,"abstract":"Connected autonomous vehicles technology are expected to be an important component of Intelligent Transportation Systems (ITS). Several relevant industry standards are being created to prepare for the maturity of connected vehicles with the help of artificial intelligence, cognitive methods, software-hardware and sensor platforms. One of the significant challenges raised by connected vehicles is how the underlying communication infrastructure will be able to efficiently support them. In this paper, we propose the Dynamic, Decentralized, Distributed, Delegation-based (D4) network control plane architecture which aims at providing adequate communication support for connected vehicles. To our knowledge, D4 is the first framework to support on-demand network control decentralization. At its core, D4’s flexible network control delegation framework allows network control to be dynamically distributed on demand to address quality-of-service requirements of different connected vehicle services and applications. We demonstrate the benefits of D4 through a proof-of-concept prototype running on a fully reproducible emulation platform. Experimental results using a variety of real-world scenarios demonstrate that D4 delivers lower latency with minimal additional overhead. We also showcase the benefits of D4 when compared to traditional vehicular ad-hoc network (VANET) approaches.","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"83 15","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139783599","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":"Basic Safety Message Generation Through a Video-Based Analytics for Potential Safety Applications","authors":"Abyad Enan, Abdullah Al Mamun, Jean Michel Tine, Judith Mwakalonge, Debbie Aisiana Indah, G. Comert, Mashrur Chowdhury","doi":"10.1145/3643823","DOIUrl":"https://doi.org/10.1145/3643823","url":null,"abstract":"With the advancement of modern artificial intelligence techniques, computer vision can play a vital role in enhancing roadway safety by reducing the risk of imminent collisions. To do so, a vision-based safety application is required, where a roadside camera can monitor the traffic and predict potential risks of crashes in real-time. If any risky behavior is observed, then the safety application can send warnings to the vehicles with risky behavior. For vision-based safety applications on a roadway section, it is important to accurately monitor each vehicle's location, speed, acceleration, heading direction, etc., in that section. In this study, we develop a video analytics-based basic safety message (BSM) generation method in accordance with the Society of Automotive Engineers standards (SAE J2945 and SAE J2735). Our developed BSM is further evaluated by conducting a field test where the results are compared with the ground truth results and cellular vehicle-to-everything (C-V2X) communication device-generated results. Our results demonstrate that our proposed video-based BSM generation method outperforms the C-V2X generated results, and our method's errors are less than the maximum acceptable errors set by SAE J2945. Additionally, we conduct tests to assess the end-to-end latency of our developed method and found that the end-to-end latency is within the maximum allowable range for potential safety applications. We further propose use case scenarios, illustrating how our developed BSM generation method can be utilized for potential safety applications.","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"15 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140477273","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":"RAMPART: Reinforcing Autonomous Multi-agent Protection through Adversarial Resistance in Transportation","authors":"Md Tamjid Hossain, Hung La, S. Badsha","doi":"10.1145/3643137","DOIUrl":"https://doi.org/10.1145/3643137","url":null,"abstract":"\u0000 In the field of multi-agent autonomous transportation, such as automated payload delivery or highway on-ramp merging, agents routinely exchange knowledge to optimize their shared objective and adapt to environmental novelties through Cooperative Multi-Agent Reinforcement Learning (CMARL) algorithms. This knowledge exchange between agents allows these systems to operate efficiently and adapt to dynamic environments. However, this cooperative learning process is susceptible to adversarial poisoning attacks, as highlighted by contemporary research. Particularly, the poisoning attacks where malicious agents inject deceptive information camouflaged within the differential noise, a pivotal element for differential privacy (DP)-based CMARL algorithms, pose formidable challenges to identify and overcome. The consequences of not addressing this issue are far-reaching, potentially jeopardizing safety-critical operations and the integrity of data privacy in these applications. Existing research has strived to develop anomaly detection-based defense models to counteract conventional poisoning methods. Nonetheless, the recurring necessity for model offloading and retraining with labeled anomalous data undermines their practicality, considering the inherently dynamic nature of the safety-critical autonomous transportation applications. Further, it is imperative to maintain data privacy, ensure high performance, and adapt to environmental changes. Motivated by these challenges, this paper introduces a novel defense mechanism against stealthy adversarial poisoning attacks in the autonomous transportation domain, termed Reinforcing Autonomous Multi-agent Protection through Adversarial Resistance in Transportation (RAMPART). Leveraging a GAN model at each local node, RAMPART effectively filters out malicious advice in an unsupervised manner, whilst generating synthetic samples for each state-action pair to accommodate environmental uncertainties and eliminate the need for labeled training data. Our extensive experimental analysis, conducted in a Private Payload Delivery Network (PPDN) —a common application in the autonomous multi-agent transportation domain—demonstrates that\u0000 \u0000 RAMPART successfully defends against a DP-exploited poisoning attack with a\u0000 \u0000 (30% )\u0000 \u0000 attack ratio, achieving an F1 score of 0.852 and accuracy of\u0000 \u0000 (96.3% )\u0000 \u0000 in heavy-traffic environments\u0000 \u0000 .\u0000","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"74 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139593733","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":"Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation","authors":"Yiming Cui, Cheng Han, Dongfang Liu","doi":"10.1145/3632181","DOIUrl":"https://doi.org/10.1145/3632181","url":null,"abstract":"The advancement of computer vision has pushed visual analysis tasks from still images to the video domain. In recent years, video instance segmentation, which aims to track and segment multiple objects in video frames, has drawn much attention for its potential applications in various emerging areas such as autonomous driving, intelligent transportation, and smart retail. In this paper, we propose an effective framework for instance-level visual analysis on video frames, which can simultaneously conduct object detection, instance segmentation, and multi-object tracking. The core idea of our method is collaborative multi-task learning which is achieved by a novel structure, named associative connections among detection, segmentation, and tracking task heads in an end-to-end learnable CNN. These additional connections allow information propagation across multiple related tasks, so as to benefit these tasks simultaneously. We evaluate the proposed method extensively on KITTI MOTS and MOTS Challenge datasets and obtain quite encouraging results.","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"105 24","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135137298","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":"Dynamic Planning of Optimally-safe Lane-change Trajectory for Autonomous Driving on Multi-lane Highways Using a Fuzzy Logic based Collision Estimator","authors":"Omveer Sharma, N. C. Sahoo, Niladri B. Puhan","doi":"10.1145/3632180","DOIUrl":"https://doi.org/10.1145/3632180","url":null,"abstract":"The collision avoidance system in an autonomous vehicle, intended to address traffic safety issues, has a crucial function called collision estimation. It accomplishes this by identifying potential dangers and notifying the drivers in advance or by using autonomous control to navigate safely. In this work, a novel approach is proposed for generating and selecting a lane change trajectory for the vehicle in a driving scenario where two vehicles are simultaneously executing lane change processes on highways and approaching the same target lane. Moreover, a novel fuzzy logic estimator based on time-to-collision (TTC) and time-to-gap (TTG) is designed to estimate the collision risk. In the collision avoidance process, the proposed estimator is utilized to determine the risk of a collision with polynomial function-based generation of possible lane change trajectories. The safest lane change trajectory is then provided to the motion controller so that it can navigate the vehicle safely through such a challenging lane change scenario. This work also investigates Stanley and Pure Pursuit controllers to follow the optimized trajectory. The simulation experiment results demonstrate that the proposed approach for dynamic trajectory generation during the lane change process can successfully handle this type of challenging situation and prevent a potential collision. Experimental results also indicate that monitoring the movement of the nearby lane-changing vehicle is crucial for safe lane change execution and that the proposed approach successfully handles the challenging situation preventing potential collision.","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"5 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135390752","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":"Sniffer Faster R-CNN ++: An Efficient Camera-LiDAR Object Detector with Proposal Refinement on Fused Candidates","authors":"Sudip Dhakal, Dominic Carrillo, Deyuan Qu, Qing Yang, Song Fu","doi":"10.1145/3631138","DOIUrl":"https://doi.org/10.1145/3631138","url":null,"abstract":"In this paper we present Sniffer Faster R-CNN++, an efficient Camera-LiDAR late fusion network for low complexity and accurate object detection in autonomous driving scenarios. The proposed detection network architecture operates on output candidates of any 3D detector and proposals from regional proposal network of any 2D detector to generate final prediction results. In comparison to the single modality object detection approaches, fusion based methods in many instances suffer from dissimilar data integration difficulties. On one hand, fusion based network models are complicated in nature and on the other hand they require large computational overhead and resources, processing pipelines for training and inference specially, the early fusion and deep fusion approaches. As such, we devise a late fusion network that in-cooperates pre-trained, single-modality detectors without change, performing association only at the detection level. In addition to this, lidar based method fail to detect distant object due to its sparse nature so we devise proposal refinement algorithm to jointly optimize detection candidates and assist detection for distant objects. Extensive experiments on both the 3D and 2D detection benchmark of challenging KITTI dataset illustrate that our proposed network architecture significantly improves the detection accuracy, accelerating the detection speed.","PeriodicalId":474318,"journal":{"name":"ACM Journal on Autonomous Transportation Systems","volume":"7 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136158810","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}