| 1. |
- Berger, Christian, 1980, et al.
(författare)
-
Simulations on Consumer Tests: A Systematic Evaluation Approach in an Industrial Case Study
- 2015
-
Ingår i: Ieee Intelligent Transportation Systems Magazine. - : Institute of Electrical and Electronics Engineers (IEEE). - 1939-1390 .- 1941-1197. ; 7:4, s. 24-36
-
Tidskriftsartikel (refereegranskat)abstract
- Context: Consumer tests which assess safety features of modern vehicles have a tradition in Europe. Recently, such test protocols have been substantially extended to also cover active safety systems like Volkswagen's Front Assist. Objective: Simulations for passive safety systems are already a widely adopted approach during vehicle development and internal assessments. As active safety systems are becoming an increasingly important element in a vehicle's safety concept and a differentiating feature, a systematic validation and assessment of such systems is necessary to successfully pass consumer tests and complimentarily identified, relevant traffic scenarios. Method: With this work, we extend our previous conference publication about EuroNCAP CCRs tests by additionally investigating US NCAP scenarios for an AEB system. Therefore, we systematically modeled the allowed variations with a graph where the paths represent concrete test scenarios. These paths are used in a virtual test environment to assess the AEB system. In our previous publication, we illustrated our method of test case generation and simulating consumer test scenarios by showing results of 27 specific test cases. In this work, we focused on integrating a test automatization routine as well as evaluating a set of test cases with a factor of 100 compared to our previous paper. Results: We demonstrate the approach for both EuroNCAP's and US NCAP's CCRs scenarios with a total quantity of more than 2,700 test cases including re-runs to systematically evaluate an AEB algorithm. Our results unveiled varying action points in time for the same initial values for a given consumer test scenario while applying different allowed variations. Conclusion: We foresee the importance of complementary virtual testing for real-world tests on proving grounds especially during the design phase. Our study shows that already small variations that yet accord with the test procedure specification influence the behavior of an active safety system and need to be investigated during development and vehicle testing.
|
|
| 2. |
- Fang, Shan, et al.
(författare)
-
A Dynamic Transformation Car-Following Model for the Prediction of the Traffic Flow Oscillation
- 2024
-
Ingår i: IEEE Intelligent Transportation Systems Magazine. - 1939-1390 .- 1941-1197. ; 16:1, s. 174-198
-
Tidskriftsartikel (refereegranskat)abstract
- Car-following (CF) behavior is a fundamental of traffic flow modeling; it can be used for the virtual testing of connected and automated vehicles and the simulation of various types of traffic flow, such as free flow and traffic oscillation. Although existing CF models can replicate the free flow well, they are incapable of simulating complicated traffic oscillation, and it is difficult to strike a balance between accuracy and efficiency. This article investigates the error variation when the traffic oscillation is simulated by the intelligent driver model (IDM). Then, it divides the traffic oscillation into four phases (coasting, deceleration, acceleration, and stationary) by using the space headway of multiple steps. To simulate traffic oscillation between multiple human-driven vehicles, a dynamic transformation CF model is proposed, which includes the long-time prediction submodel [modified sequence-to-sequence (Seq2seq)] model, short-time prediction submodel (Transformer), and their dynamic transformation strategy]. The first submodel is utilized to simulate the coasting and stationary phases, while the second submodel is utilized to simulate the acceleration and deceleration phases. The results of experiments indicated that compared to K-nearest neighbors, IDM, and Seq2seq CF models, the dynamic transformation CF model reduces the trajectory error by 60.79–66.69% in microscopic traffic flow simulations, 7.71–29.91% in mesoscopic traffic flow simulations, and 1.59–18.26% in macroscopic traffic flow simulations. Moreover, the runtime of the dynamic transformation CF model (Inference) decreased by 14.43–66.17% when simulating the large-scale traffic flow.
|
|
| 3. |
- Gelso, Esteban, 1977, et al.
(författare)
-
Consistent Threat Assessment in Rear-End Near-Crashes Using BTN and TTB Metrics, Road Information and Naturalistic Traffic Data
- 2017
-
Ingår i: IEEE Intelligent Transportation Systems Magazine. - : Institute of Electrical and Electronics Engineers (IEEE). - 1939-1390 .- 1941-1197. ; 9:1, s. 74-89
-
Tidskriftsartikel (refereegranskat)abstract
- Rear-end crashes are one of the most frequent types of traffic accidents. As a response, in order to assist the drivers, Advanced Driver Assistance Systems (ADAS) are being developed; particularly, Collision Avoidance Systems (CAS). Current CAS algorithms are commonly based on very simplified models of the preceding vehicle motion, under the assumptions of constant velocity or con-stant acceleration. This leads to several issues in the pre-diction of the lead vehicle behavior, and at the end, in the evaluation of the potential collision hazard. This paper identifies and addresses a hazard overestimation issue occurring in events related to rear-end (near) crashes that take place at traffic junctions. The issue was identified by analyzing 121 events found within data of 14640 driving hours collected in the framework of the Eu-ropean Field Operational Test on Active Safety Systems (euroFOT) project. Aiming to solve this issue, in this work it is proposed an enhanced model including road information to predict the lead vehicle braking behavior (deceleration pattern) of the CAS algorithms. Then, the hazard estimation is han-dled by a consistent event detection strategy, which uses simultaneously two metrics: the Time-to-Brake (TTB), and the Brake-Threat-Number (BTN). The result is the Consistent Threat Assessment for Longitudinal Motion Al-gorithm (CTALMA). The applicability of this algorithm is illustrated by an in-depth analysis of three test examples. Obtained results show a better assessment of the collision potential hazard and consistent event detection avoiding false alarms in all the cases.
|
|
| 4. |
|
|
| 5. |
- Jiau, Mingkai, et al.
(författare)
-
Multimedia Services in Cloud-Based Vehicular Networks
- 2015
-
Ingår i: IEEE Intelligent Transportation Systems Magazine (ITSM). - 1939-1390 .- 1941-1197. ; 7:3, s. 62-79
-
Tidskriftsartikel (refereegranskat)abstract
- Research into the requirements for mobile services has seen a growing interest in the fields of cloud technology and vehicular applications. Integrating cloud computing and storage with vehicles is a way to increase accessibility to multimedia services, and inspire myriad potential applications and research topics. This paper presents an overview of the characteristics of cloud computing, and introduces the basic concepts of vehicular networks. An architecture for multimedia cloud computing is proposed to suit subscription service mechanisms. The tendency to equip vehicles with advanced and embedded devices such as diverse sensors increases the capabilities of vehicles to provide computation and collection of multimedia content in the form of the vehicular network. Then, the taxonomy of cloud-based vehicular networks is addressed from the standpoint of the service relationship between the cloud computing and vehicular networks. In this paper, we identify the main considerations and challenges for cloud based vehicular networks regarding multimedia services, and propose potential research directions to make multimedia services achievable. More specifically, we quantitatively evaluate the performance metrics of these researches. For example, in the proposed broadcast storm mitigation scheme for vehicular networks, the packet delivery ratio and the normalized throughput can both achieve about 90%, making the proposed scheme a useful candidate for multimedia data exchange. Moreover, in the video uplinking scenarios, the proposed scheme is favorably compared with two well-known schedulers, M-LWDF and EXP, with the performance much closer to the optimum
|
|
| 6. |
- Johansson, Alexander, et al.
(författare)
-
Platoon Cooperation Across Carriers: From System Architecture to Coordination
- 2023
-
Ingår i: IEEE Intelligent Transportation Systems Magazine. - : Institute of Electrical and Electronics Engineers (IEEE). - 1939-1390 .- 1941-1197. ; 15:3, s. 132-144
-
Tidskriftsartikel (refereegranskat)abstract
- Truck platooning is a well-studied technology that has the potential to reduce both the environmental impact and operational costs of trucks. The technology has matured over the last 20 years, and the commercial rollout of platooning is approaching. Cooperation across carriers is essential for the viability of platooning; otherwise, many platooning opportunities are lost. We first present a cross-carrier platooning system architecture in which many carriers cooperate in forming platoons through a platoon-hailing service. Then, we present a cross-carrier platoon coordination approach in which each carrier optimizes its platooning plans according to the predicted plans of other carriers. A profit-sharing mechanism to even out the platooning profit in each platoon is embedded in the platoon coordination approach. Finally, a simulation study over the Swedish road network is performed to evaluate the potential of platooning under realistic conditions. The simulation study shows that the energy consumption of trucks in Sweden can be reduced by 5.4% due to platooning and that cooperation across carriers is essential to achieve significant platooning benefits.
|
|
| 7. |
- Kianfar, Roozbeh, 1984, et al.
(författare)
-
Safety Verification of Automated Driving Systems
- 2013
-
Ingår i: IEEE Intelligent Transportation Systems Magazine. - 1939-1390 .- 1941-1197. ; 5:4, s. 73-86
-
Tidskriftsartikel (refereegranskat)abstract
- n this paper, a set based approach is presented for safety verification and performance analysis of automated driving systems. As an example, reachability analysis technique is used to study the minimum required safe inter-vehicle distance for two given adaptive cruise controllers, a state feedback and a state feedback/feedforward controller designed based on mixed d H2/3 control. Not surprisingly, the results indicate that a shorter inter-vehicle distance can be achieved when a feedforward term used in the controller. In addition, we show how backward reachability analysis and invariant set theory can be used to find the Maximal Admissible Safe Set. This is defined as the set of position error, relative speeds and acceleration, which a given controller is guaranteed to control to the desired speed and inter-vehicle distance, while fulfilling vehicle physical constraints and avoiding rear-end collisions with the preceding vehicle. The calculation of the Maximal Admissible Safe Set is demonstrated for the two aforementioned controllers. Furthermore, the presented verification method is extended to account for the case of vehicle model with polytopic uncertainties and delay. The results on the reachability analysis are verified experimentally using an emergency braking scenario.
|
|
| 8. |
- Li, Guofa, et al.
(författare)
-
Driver Behavior in Intelligent Transportation Systems
- 2022
-
Ingår i: IEEE Intelligent Transportation Systems Magazine. - 1939-1390 .- 1941-1197. ; 14:3, s. 7-9
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- Drivers are the center of road/air/sea transportation systems, and they can be either human beings or artificial beings. Inconsistency between human driver behavior and artificial driver behavior will lead to accidents and congestion in intelligent transportation systems (ITSs) [1] , [2] . To make future ITSs trustworthy for traffic safety and acceptable for travel efficiency, developing industrial ITS applications based on drivers’ reliable behavioral and cognitive intelligence is essential [3] . However, there are many challenges to be addressed, including real-time behavior prediction, reliable decision making, safe interaction among human and artificial drivers, and so on.
|
|
| 9. |
- Li, Xiaopeng (Shaw), et al.
(författare)
-
Emerging Mobility Systems
- 2019
-
Ingår i: IEEE Intelligent Transportation Systems Magazine. - 1939-1390 .- 1941-1197. ; 11:3, s. 8-11
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)
|
|
| 10. |
- Lin, Hongyi, et al.
(författare)
-
Deep Demand Prediction: An Enhanced Conformer Model With Cold-Start Adaptation for Origin–Destination Ride-Hailing Demand Prediction
- 2024
-
Ingår i: IEEE Intelligent Transportation Systems Magazine. - 1939-1390 .- 1941-1197. ; 16:3, s. 111-124
-
Tidskriftsartikel (refereegranskat)abstract
- In intelligent transportation systems, one key challenge for managing ride-hailing services is the balancing of traffic supply and demand while meeting passenger needs within vehicle availability constraints. Accurate origin–destination (OD) demand predictions can empower platforms to execute timely reallocation of cruising vehicles and improve ride-sharing services. Nonetheless, the complexity of OD-based demand prediction arises from intricate spatiotemporal dependencies and a higher need for precision compared to zone-based predictions, which leads to many unprecedented OD pairs. To tackle this issue, we design a comprehensive set of 102 features, including travel demand, passenger count, travel volume, liveliness, weather, and cross features. We also introduce an enhanced conformer model, which is composed of a single conformer block that integrates feedforward layers, multihead self-attention mechanisms, and depth-wise separable convolution layers. To address the cold-start problem and manage large values, we design a specific algorithm for OD pairs lacking training data and apply a technique to handle larger values. Our approach demonstrates a marked improvement in prediction performance, with an 18% decrease in the total travel demand error and up to a 47% reduction for certain larger values in some cases. Through extensive experiments on a dataset collected from a city, provided by a ride-hailing platform, our proposed methods significantly outperform the most advanced models.
|
|
