| 1. |
- Berger, Christian, 1980, et al.
(författare)
-
Systematic Evaluation of Applying Space-Filling Curves to Automotive Maneuver Detection
- 2023
-
Ingår i: IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC. - 2153-0009 .- 2153-0017. - 9798350399462
-
Konferensbidrag (refereegranskat)abstract
- Identifying driving maneuvers plays an essential role on-board vehicles to monitor driving and driver states, as well as off-board to train and evaluate machine learning algorithms for automated driving for example. Maneuvers can be characterized by vehicle kinematics or data from its surroundings including other traffic participants. Extracting relevant maneuvers therefore requires analyzing time-series of (i) structured, multi-dimensional kinematic data, and (ii) unstructured, large data samples for video, radar, or LiDAR sensors. However, such data analysis requires scalable and computationally efficient approaches, especially for non-annotated data. In this paper, we are presenting a maneuver detection approach based on two variants of space-filling curves (Z-order and Hilbert) to detect maneuvers when passing roundabouts that do not use GPS data. We systematically evaluate their respective performance by including permutations of selections of kinematic signals at varying frequencies and compare them with two alternative baselines: All manually identified roundabouts, and roundabouts that are marked by geofences. We find that encoding just longitudinal and lateral accelerations sampled at 10 Hz using a Hilbert space-filling curve is already successfully identifying roundabout maneuvers, which allows to avoid the use of potentially sensitive signals such as GPS locations to comply with data protection and privacy regulations like GDPR.
|
|
| 2. |
- Chen, Mo, et al.
(författare)
-
Energy-Efficient and Safe-Separation Operation for Successive Trains
- 2023
-
Ingår i: IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC. - 2153-0017 .- 2153-0009. ; , s. 845-851
-
Konferensbidrag (refereegranskat)abstract
- Energy-efficient and safe-separation during train operation is of great significance for urban rail transit systems, particularly on lines with high traffic density. This paper integrates the two issues and proposes a general cooperative operation method for successive trains with no limit on the number of trains. The cooperation problem is formulated as an optimal control problem and then solved as a nonlinear program. By simultaneously optimizing the speed profiles of each train, the total traction energy of the multi-train system can be minimized, ensuring safety by imposing dynamic time headway constraints among adjacent trains throughout the entire distance horizon. Moreover, a dynamic programming method is developed for comparative study, to verify the effectiveness of the proposed method.
|
|
| 3. |
- Dolins, Sigma, 1985, et al.
(författare)
-
AVs Have a Sharing Problem: Examining User Acceptance of Shared, Autonomous Public Transport in Sweden
- 2023
-
Ingår i: IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC. - 2153-0017 .- 2153-0009. ; , s. 6102-6107
-
Konferensbidrag (refereegranskat)abstract
- This paper investigates the acceptance of shared, autonomous vehicles (SAVs) with participants who have been exposed to AV pilots in Sweden, with a specific focus on shared mobility and public transport contexts. The study aims to gain insights into individuals' attitudes, acceptance levels, and willingness to use autonomous vehicles (AVs) in shared mobility scenarios, particularly in the context of public transportation. The research methodology employed focus groups to gather qualitative insights from participants. The findings provide valuable insights into user perceptions and preferences, offering guidance for promoting SAVs and integrating them into public transport systems in Sweden.
|
|
| 4. |
- Gaetan, Elisa, et al.
(författare)
-
Modelling Traffic Scenarios via Markovian Opinion Dynamics
- 2023
-
Ingår i: IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC. - 2153-0017 .- 2153-0009. ; , s. 1072-1077
-
Konferensbidrag (refereegranskat)abstract
- We address the question of whether opinion dynamics models can be exploited in novel scenarios, such as traffic flow on highway lanes. In this paper, we design a Markovian model and compare its predictions with those obtained from the widely recognized Cell Transmission Model (CTM) for the same traffic scenario. We identify potential challenges that may arise and propose strategies to address them. Furthermore, we present a concise demonstration showcasing the predictive capabilities of our proposed model through a small-scale example.
|
|
| 5. |
- Grimm, Daniel, et al.
(författare)
-
Gap analysis of ISO/SAE 21434 – Improving the automotive cybersecurity engineering life cycle
- 2023
-
Ingår i: IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC. - 2153-0017 .- 2153-0009. ; , s. 1904-1911
-
Konferensbidrag (refereegranskat)abstract
- Due to the ongoing legislative shift towards mandated cybersecurity for road vehicles, the automotive cybersecurity engineering standard ISO/SAE 21434 is seeing fast adoption throughout the industry. Early efforts are focusing on threat analysis and risk assessment (TARA) in the concept and development phases, exposing the challenge of managing TARA results coherently throughout the supply chain and life cycle. While the industry focuses on TARA, other aspects such as vulnerability or incident handling are receiving less attention. However, the increasing threat landscape makes these processes increasingly important, posing another industry challenge. In order to better address these two challenges, we analyze the cybersecurity engineering framework of ISO/SAE 21434 for gaps or deficiencies regarding TARA management and vulnerability and incident handling, as well as similar processes for incident handling in IT security. The result is a proposal for modifications and augmentations of the ISO/SAE 21434 cybersecurity engineering framework. In particular, we propose a TARA management process to facilitate the coordination and information exchange between different systems and life cycle phases, and we propose improvements to the vulnerability and incident handling processes in ISO/SAE 21434 so that they are more aligned with established standards. This amounts to 13 new terminology definitions, 4 new process steps, 2 modified process steps and 1 entirely new process.
|
|
| 6. |
- Erlinge, David, et al.
(författare)
-
Therapeutic Hypothermia for the Treatment of Acute Myocardial Infarction-Combined Analysis of the RAPID MI-ICE and the CHILL-MI Trials
- 2015
-
Ingår i: Therapeutic Hypothermia and Temperature Management. - : Mary Ann Liebert Inc. - 2153-7658 .- 2153-7933. ; 5:2, s. 77-84
-
Tidskriftsartikel (refereegranskat)abstract
- In the randomized rapid intravascular cooling in myocardial infarction as adjunctive to percutaneous coronary intervention (RAPID MI-ICE) and rapid endovascular catheter core cooling combined with cold saline as an adjunct to percutaneous coronary intervention for the treatment of acute myocardial infarction CHILL-MI studies, hypothermia was rapidly induced in conscious patients with ST-elevation myocardial infarction (STEMI) by a combination of cold saline and endovascular cooling. Twenty patients in RAPID MI-ICE and 120 in CHILL-MI with large STEMIs, scheduled for primary percutaneous coronary intervention (PCI) within <6 hours after symptom onset were randomized to hypothermia induced by rapid infusion of 600-2000mL cold saline combined with endovascular cooling or standard of care. Hypothermia was initiated before PCI and continued for 1-3 hours after reperfusion aiming at a target temperature of 33 degrees C. The primary endpoint was myocardial infarct size (IS) as a percentage of myocardium at risk (IS/MaR) assessed by cardiac magnetic resonance imaging at 4 +/- 2 days. Patients randomized to hypothermia treatment achieved a mean core body temperature of 34.7 degrees C before reperfusion. Although significance was not achieved in CHILL-MI, in the pooled analysis IS/MaR was reduced in the hypothermia group, relative reduction (RR) 15% (40.5, 28.0-57.6 vs. 46.6, 36.8-63.8, p=0.046, median, interquartile range [IQR]). IS/MaR was predominantly reduced in early anterior STEMI (0-4h) in the hypothermia group, RR=31% (40.5, 28.8-51.9 vs. 59.0, 45.0-67.8, p=0.01, median, IQR). There was no mortality in either group. The incidence of heart failure was reduced in the hypothermia group (2 vs. 11, p=0.009). Patients with large MaR (>30% of the left ventricle) exhibited significantly reduced IS/MaR in the hypothermia group (40.5, 27.0-57.6 vs. 55.1, 41.1-64.4, median, IQR; hypothermia n=42 vs. control n=37, p=0.03), while patients with MaR<30% did not show effect of hypothermia (35.8, 28.3-57.5 vs. 38.4, 27.4-59.7, median, IQR; hypothermia n=15 vs. control n=19, p=0.50). The prespecified pooled analysis of RAPID MI-ICE and CHILL-MI indicates a reduction of myocardial IS and reduction in heart failure by 1-3 hours with endovascular cooling in association with primary PCI of acute STEMI predominantly in patients with large area of myocardium at risk. (ClinicalTrials.gov id NCT00417638 and NCT01379261).
|
|
| 7. |
|
|
| 8. |
- Chandru, Rajashekar, 1991, et al.
(författare)
-
Safe autonomous lane changes in dense traffic
- 2017
-
Ingår i: IEEE International Conference on Intelligent Transportation Systems-ITSC. - 2153-0009. - 9781538615263 ; 2018-March
-
Konferensbidrag (refereegranskat)abstract
- Lane change manoeuvres are complex driving manoeuvres to automate since the vehicle has to anticipate and adapt to intentions of several surrounding vehicles. Selecting a suitable gap to move/merge into the adjacent lane and performing the lane change can be challenging, especially in dense traffic. Existing gap selection methods tend to be either cautious or opportunistic, both of which directly affect the overall availability and safety of the autonomous feature. In this paper we present a method which enables the autonomous vehicles to increase the availability of lane change manoeuvres by reducing the required margins to ensure a safe manoeuvre. The required safety margins are first calculated by making use of the steering and braking capability of the vehicle. It is then shown that this method can be used to perform autonomous lane changes in dense traffic situations with small inter-vehicle gaps. The proposed solution is evaluated by using Model Predictive Control (MPC) to plan and execute the complete motion trajectory.
|
|
| 9. |
- Colombo, Alessandro, et al.
(författare)
-
Cooperative intersection collision avoidance in a constrained communication environment
- 2015
-
Ingår i: IEEE International Conference on Intelligent Transportation Systems. - 2153-0009. - 9781467365963 ; 2015-October, s. 375-380
-
Konferensbidrag (refereegranskat)abstract
- Intersections remain among the most accidentprone subsystems in modern traffic. With the introduction of vehicle-to-infrastructure communication, it is possible for the intersection to become aware of the incoming stream of vehicles and issue warnings when needed. We consider an approach where vehicles can act automatically on those warnings, leaving drivers maximal freedom of manoeuvre while guaranteeing safety with minimal intervention. We also quantify the impact of imperfect communication in the uplink (from vehicle to infrastructure) and the downlink (from infrastructure to vehicle).
|
|
| 10. |
- Innocenti, Christopher, et al.
(författare)
-
Imitation Learning for Vision-based Lane Keeping Assistance
- 2017
-
Ingår i: IEEE International Conference on Intelligent Transportation Systems-ITSC. - 2153-0009. - 9781538615263 ; 2018-March
-
Konferensbidrag (refereegranskat)abstract
- This paper aims to investigate direct imitation learning from human drivers for the task of lane keeping assistance in highway and country roads using grayscale images from a single front view camera. The employed method utilizes convolutional neural networks (CNN) to act as a policy that is driving a vehicle. The policy is successfully learned via imitation learning using real-world data collected from human drivers and is evaluated in closed-loop simulated environments, demonstrating good driving behaviour and a robustness for domain changes. Evaluation is based on two proposed performance metrics measuring how well the vehicle is positioned in a lane and the smoothness of the driven trajectory.
|
|
