CARISSMA Institute of Automated Driving (C-IAD)
Refine
Document Type
- Conference Paper (131)
- Article (40)
- Part of a Compilation / Book Chapter (6)
- Book (3)
- Preprint (1)
Institute
- CARISSMA Institute of Automated Driving (C-IAD) (181)
- Human-Computer Interaction Group (HCIG) (132)
- Fakultät Informatik (125)
- Fakultät Elektro- und Informationstechnik (51)
- CARISSMA Institute of Electric, Connected and Secure Mobility (C-ECOS) (7)
- AImotion Bavaria (5)
- Fakultät Maschinenbau (2)
- Institut für Innovative Mobilität (IIMo) (1)
Review
- peer-review (129)
- nein (35)
- editorial review (4)
- ja (3)
Version
- published (50)
Es wurden bereits einige Lösungen vorgestellt, um die Kommunikation zwischen automatisierten Fahrzeugen und ungeschützten Verkehrsteilnehmern (sog. „Vulnerable Road Users“, VRUs) zu unterstützen. Noch ist jedoch unklar, ob diese Systeme den Anforderungen zukünftiger Benutzer auch gerecht werden. Ziel dieser Arbeit war es, Benutzeranforderungen von VRUs nach direktem Kontakt mit einem automatisierten Fahrzeug zu erfassen. Hierfür wurde eine Feldstudie mit 32 Teilnehmern durchgeführt. Die Resultate, welche sowohl auf subjektiven (Fragebögen, Interviews) als auch objektiven (Videoanalyse) Daten basieren, legen nahe, dass ungeschützte Verkehrsteilnehmer einfache und bekannte Konzepte (beispielsweise Ampelsysteme oder Hupen) zur Kommunikation bevorzugen. Des Weiteren wurden diverse Problemszenarien identifiziert, welche für eine Bereitstellung von automatisierten Fahrzeugen in „Shared Spaces“ von besonderer Bedeutung sind.
Da erst wenige automatisierte Fahrzeuge auf öffentlichen Straßen in Betrieb sind, ist aktuell noch unklar, ob potenzielle Nutzer diese akzeptieren und ihnen vertrauen. Um diesen Fragen nachzugehen, wurde eine Feldstudie mit 24 (jeweils zwölf älteren und jüngeren) Teilnehmern durchgeführt, wobei ein automatisiertes Fahrzeug direkt mit einem von menschlicher Hand gesteuerten Gruppentaxi verglichen wurde. Benutzerakzeptanz und -erlebnis, Vertrauen sowie subjektives Zeitempfinden wurden sowohl vor als auch nach der Fahrt mit dem jeweiligen Transportmittel mit standardisierten Messverfahren und Interviews erfasst. Die Resultate zeigen, dass automatisierte Fahrzeuge in ähnlichem Ausmaß akzeptiert werden wie auch menschliche Fahrer, jedoch gerade jüngere Probanden aufgrund der geringeren Geschwindigkeit der neuen Technologie gegenüber noch skeptisch eingestellt sind. Für diese Zielgruppe wirkte sich jedoch eine Fahrt mit dem automatisierten Fahrzeug positiv auf das Vertrauen aus. Eine Berücksichtigung der gewonnenen Erkenntnisse ist für eine weitere Implementierung der Technologie zu empfehlen.
The use of actor-critic algorithms can improve the controllers currently implemented in automotive applications. This method combines reinforcement learning (RL) and neural networks to achieve the possibility of controlling nonlinear systems with real-time capabilities. Actor-critic algorithms were already applied with success in different controllers including autonomous driving, antilock braking system (ABS), and electronic stability control (ESC). However, in the current researches, virtual environments are implemented for the training process instead of using real plants to obtain the datasets. This limitation is given by trial and error methods implemented for the training process, which generates considerable risks in case the controller directly acts on the real plant. In this way, the present research proposes and evaluates an open-loop training process, which permits the data acquisition without the control interaction and an open-loop training of the neural networks. The performance of the trained controllers is evaluated by a design of experiments (DOE) to understand how it is affected by the generated dataset. The results present a successful application of open-loop training architecture. The controller can maintain the slip ratio under adequate levels during maneuvers on different floors, including grounds that are not applied during the training process. The actor neural network is also able to identify the different floors and change the acceleration profile according to the characteristics of each ground.
Variational Autoencoder-Based Vehicle Trajectory Prediction with an Interpretable Latent Space
(2021)
Interpretable Early Prediction of Lane Changes Using a Constrained Neural Network Architecture
(2021)
Automatisiertes Fahren wird aktuell auf allen Ebenen diskutiert. Dieses Open Access Buch greift das Thema aus Sicht des ÖPNV auf und stellt Chancen und Risiken des Einsatzes automatisierter Shuttlebusse im Nahverkehr dar. Am Beispiel Bad Birnbach/Niederbayern wird gezeigt, welche Herausforderungen bei der Einführung eines solchen Services zu erwarten sind und wie diese gelöst werden können. Dabei fokussiert sich das Buch auf die Vermittlung von im Feld erhobenen Daten, z.B. zu technischen Schwierigkeiten, Erfahrungsberichten von Anwohnern und Gästen, Akzeptanz in der Bevölkerung, infrastrukturellen Anforderungen, etc. Konkrete Handlungsempfehlungen für Städteplaner, ÖPNV-Betreiber/-Strategen oder Kommunen, die eine Einführung automatisierter Busse in Erwägung ziehen, runden das Werk ab.
Numerous statistics show that cyclists are often involved in road traffic accidents, often with serious outcomes. One potential hazard of cycling, especially in cities, is “dooring”—passing parked vehicles that still have occupants inside. These occupants could open the vehicle door unexpectedly in the cyclist’s path—requiring a quick evasive response by the cyclist to avoid a collision. Dooring can be very poorly anticipated; as a possible solution, we propose in this work a system that notifies the cyclist of opening doors based on a networked intelligent transportation infrastructure. In a user study with a bicycle simulator (N = 24), we examined the effects of three user interface designs compared to a baseline (no notifications) on cycling behavior (speed and lateral position), perceived safety, and ease of use. Awareness messages (either visual message, visual message + auditory icon, or visual + voice message) were displayed on a smart bicycle helmet at different times before passing a parked, still-occupied vehicle. Our participants found the notifications of potential hazards very easy to understand and appealing and felt that the alerts could help them navigate traffic more safely. Those concepts that (additionally) used auditory icons or voice messages were preferred. In addition, the lateral distance increased significantly when a potentially opening door was indicated. In these situations, cyclists were able to safely pass the parked vehicle without braking. In summary, we are convinced that notification systems, such as the one presented here, are an important component for increasing road safety, especially for vulnerable road users.
Automated driving functions (ADF) are considered as a potential solver of current problems in road traffic regarding safety, efficiency and comfort. However, testing ADF by naturalistic driving in the real world is subject to technical and ethical constraints. Virtual randomized controlled trial designs potentially contribute to bypass these limitations. For this purpose, real traffic is replaced by simulated traffic, constituting the “reference” in analogy to randomized controlled trials in medicine. Specific realizations of ADF can then be integrated into the simulated traffic as a “treatment” to evaluate their efficacy. A key challenge is modelling current manual traffic, taking into account stochastic variations in the cognitive and kinematic behavior of both drivers and vulnerable road users (VRU) such as pedestrians, cyclists, or e-scooter riders. Odd sample combinations of the underlying distributions can lead to accident risk and therefore have to be modeled realistically to generate validated efficacy estimates. In particular perceptual failures and degrading of perceived stimuli are regarded causal factors for failures in traffic, which is in general remarkably safe due to multiple redundancies. Therefore a model of human information acquisition constitutes an essential ingredient to our assessment paradigm. However, complex cognitive processes play a key role, which are themselves still under scientific investigation. What we do know is that inherent limited processing abilities of humans contribute to failures in the otherwise remarkably safe traffic flow process, especially in urban areas where cognitive demand is high. We therefore restrict ourselves to model the failure and degrading processes which ultimately lead to accident risk. The computational model we propose takes the limited processing capacity of humans into account and is suitable for the stochastic simulation of traffic scenarios.
While virtual reality (VR) interfaces have been researched extensively over the last decades, studies on their application in vehicles have only recently advanced. In this paper, we systematically review 12 years of VR research in the context of automated driving (AD), from 2009 to 2020. Due to the multitude of possibilities for studies with regard to VR technology, at present, the pool of findings is heterogeneous and non-transparent. We investigated N = 176 scientific papers of relevant journals and conferences with the goal to analyze the status quo of existing VR studies in AD, and to classify the related literature into application areas. We provide insights into the utilization of VR technology which is applicable at specific level of vehicle automation and for different users (drivers, passengers, pedestrians) and tasks. Results show that most studies focused on designing automotive experiences in VR, safety aspects, and vulnerable road users. Trust, simulator and motion sickness, and external human-machine interfaces (eHMIs) also marked a significant portion of the published papers, however a wide range of different parameters was investigated by researchers. Finally, we discuss a set of open challenges, and give recommendation for future research in automated driving at the VR side of the reality-virtuality continuum.
(1) Background: Primary driving tasks are increasingly being handled by vehicle automation so that support for non-driving related tasks (NDRTs) is becoming more and more important. In SAE L3 automation, vehicles can require the driver-passenger to take over driving controls, though. Interfaces for NDRTs must therefore guarantee safe operation and should also support productive work.
(2) Method: We conducted a within-subjects driving simulator study (N=53) comparing Heads-Up Displays (HUDs) and Auditory Speech Displays (ASDs) for productive NDRT engagement. In this article, we assess the NDRT displays’ effectiveness by evaluating eye-tracking measures and setting them into relation to workload measures, self-ratings, and NDRT/take-over performance.
(3) Results: Our data highlights substantially higher gaze dispersion but more extensive glances on the road center in the auditory condition than the HUD condition during automated driving. We further observed potentially safety-critical glance deviations from the road during take-overs after a HUD was used. These differences are reflected in self-ratings, workload indicators and take-over reaction times, but not in driving performance.
(4) Conclusion: NDRT interfaces can influence visual attention even beyond their usage during automated driving. In particular, the HUD has resulted in safety-critical glances during manual driving after take-overs. We found this impacted workload and productivity but not driving performance
A current trend in automotive research is autonomous driving. For the proper testing and validation of automated driving functions a reference vehicle state is required. Global Navigation Satellite Systems (GNSS) are useful in the automation of the vehicles because of their practicality and accuracy. However, there are situations where the satellite signal is absent or unusable. This research work presents a methodology that addresses those situations, thus largely reducing the dependency of Inertial Navigation Systems (INSs) on the SatNav. The proposed methodology includes (1) a standstill recognition based on machine learning, (2) a detailed mathematical description of the horizontation of inertial measurements, (3) sensor fusion by means of statistical filtering, (4) an outlier detection for correction data, (5) a drift detector, and (6) a novel LiDAR-based Positioning Method (LbPM) for indoor navigation. The robustness and accuracy of the methodology are validated with a state-of-the-art INS with Real-Time Kinematic (RTK) correction data. The results obtained show a great improvement in the accuracy of vehicle state estimation under adverse driving conditions, such as when the correction data is corrupted, when there are extended periods with no correction data and in the case of drifting. The proposed LbPM method achieves an accuracy closely resembling that of a system with RTK.
During the last decade, research has brought forth a large amount of studies that investigated driving automation from a human factor perspective. Due to the multitude of possibilities for the study design with regard to the investigated constructs, data collection methods, and evaluated parameters, at present, the pool of findings is heterogeneous and nontransparent. This literature review applied a structured approach, where five reviewers investigated n = 161 scientific papers of relevant journals and conferences focusing on driving automation between 2010 and 2018. The aim was to present an overview of the status quo of existing methodological approaches and investigated constructs to help scientists in conducting research with established methods and advanced study setups. Results show that most studies focused on safety aspects, followed by trust and acceptance, which were mainly collected through self-report measures. Driving/Take-Over performance also marked a significant portion of the published papers; however, a wide range of different parameters were investigated by researchers. Based on our insights, we propose a set of recommendations for future studies. Amongst others, this includes validation of existing results on real roads, studying long-term effects on trust and acceptance (and of course other constructs), or triangulation of self-reported and behavioral data. We furthermore emphasize the need to establish a standardized set of parameters for recurring use cases to increase comparability. To assure a holistic contemplation of automated driving, we moreover encourage researchers to investigate other constructs that go beyond safety.
Investigation of Fluid-Structure Interaction Induced Bending for Elastic Flaps in a Cross Flow
(2020)
With the recent increase in the design of light and flexible structures, numerical investigations of fluid and structure together play a significant role in most engineering applications. Therefore, the current study presents an examination of fluid-structure interaction involving flexible structures. The problem is numerically solved by a commercial software ANSYS-Workbench. Two-way coupled three-dimensional transient simulations are carried out for the flexible flaps of different thicknesses in glycerin for a laminar flow and Reynolds number ranging from 3 < Re < 12. The bending line of the flaps is compared with experimental data for different alignments of the flaps relative to the fluid flow. The study reports the computation of the maximum tip-deflection and deformation of flaps fixed at the bottom and mounted normal to the flow. Additionally, drag coefficients for flexible flaps are computed and flow regimes in the wake of the flaps are presented. As well, the study gives an understanding on how the fluid response changes as the structure deforms and the model is appropriate to predict the behavior of thick and comparatively thinner flaps. The results are sufficiently encouraging to consider the present model for analyzing turbulent flow processes against flexible objects.
This paper provides a framework for examining human-vehicle interactions with respect to three dimensions that can involve models or simulations: the agents, the environments, and the scenarios. Agents are considered on a spectrum from human to artificial actors. Environments are considered on a spectrum from simulated to real. Scenarios are considered on a spectrum from constrained to unconstrained. It is argued that these three dimensions capture key differences in research approaches within the field of human-vehicle interaction, and that explicitly situating research and discussions within this framework will allow researchers to better compare and contrast research outcomes and contributions. The framework is used to locate different disciplines in the community with respect to one another, and to identify areas which are as-yet unexplored.
There is a growing body of research in the field of interaction between automated vehicles and other road users in their vicinity. To facilitate such interactions, researchers and designers have explored designs, and this line of work has yielded several concepts of external Human-Machine Interfaces (eHMI) for vehicles. Literature and media review reveals that the description of interfaces is often lacking in fidelity or details of their functionalities in specific situations, which makes it challenging to understand the originating concepts. There is also a lack of a universal understanding of the various dimensions of a communication interface, which has impeded a consistent and coherent addressal of the different aspects of the functionalities of such interface concepts. In this paper, we present a unified taxonomy that allowsa systematic comparison of the eHMI across 18 dimensions, covering their physical characteristics and communication aspects from the perspective of human factors and human-machine interaction. We analyzed and coded 70eHMI concepts according to this taxonomy to portray the state of the art and highlight the relative maturity of different contributions. The results point to a number of unexplored research areas that could inspire future work. Additionally, we believe that our proposed taxonomy can serve as a checklist for user interface designers and researchers when developing their interfaces.
As a precursor to future public transportation, automated shuttle buses can already be experienced in some test regions, but the general public still has reservations and may not yet be ready for this change. For example, the fact that such vehicles might operate independently (without a human driver) creates a barrier of uncertainty and mistrust among people. In this work, we aim to identify and classify the prevailing reservations and propose solutions. We followed the User Centered Design (UCD) process to design concepts that are specifically tailored to the needs of future public transport users. After related work analysis, on-site research, and pre-studies, two main studies were conducted specifically to address communication in the exterior (n = 24) and interior/service design (n = 21). For both studies, we applied a mixed-methods approach combining quantitative and qualitative measures. Our results indicate that, in general, existing ways of communication in the exterior are insufficient to meet future needs. The two visualization concepts for external communication developed in this work were rated (significantly) better in most dimensions of the User Experience Questionnaire (UEQ), when compared to the baseline condition with no additional visualization. Furthermore, preferences among the study participants towards simple, highly visible, and well-known lighting concepts could be observed. As for the interior, the results show that participants rated attractiveness highly for the two design concepts (closer, further in the future) as compared to current, state-of-the-art solutions (automated buses currently in operation). For the “near future” concept, the pragmatic quality dominated, while in the other (the “far future”) concept the hedonic quality was in the foreground. From the results, design recommendations in different categories were derived, which reflect the general openness of the public towards new technologies and interior approaches, but also point out the importance for privacy and designated personal spaces inside an (automated) shuttle bus. Some of the results do not strictly apply to automated shuttle buses, and can serve as valuable suggestions for improving conventional shuttle buses.
The spread of automated vehicles (AVs) is expected to disrupt our mobility behavior. Currently, a male bias is prevalent in the technology industry in general, and in the automotive industry in particular, mainly focusing on white men. This leads to an under-representation of groups of people with other social, physiological, and psychological characteristics. The advent of automated driving (AD) should be taken as an opportunity to mitigate this bias and consider a diverse variety of people within the development process. We conducted a qualitative, exploratory study to investigate how shared automated vehicles (SAVs) should be designed from a pluralistic perspective considering a holistic viewpoint on the whole passenger journey by including booking, pick-up, and drop-off points. Both, men and women, emphasized the importance of SAVs being flexible and clean, whereas security issues were mentioned exclusively by our female participants. While proposing different potential solutions to mitigate security matters, we discuss them through the lens of the feminist HCI framework.