Interaction design of automatic steering for collision avoidance: challenges and potentials of driver decoupling

Heesen, Matthias; Dziennus, Marc; Hesse, Tobias; Schieben, Anna; Brunken, Claas; Löper, Christian; Kelsch, Johann; Baumann, Martin

doi:10.1049/iet-its.2013.0119

Cited by 38 publications

(30 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CAA strategy and path planning When a CAA system in i-EFV detects an emergency situation, the controller evaluates the risk of collision and plans a practicable ideal CA path. The CAA strategy refers to the method of intervening and sharing feedback with the driver [53][54][55] to accomplish CA through human-machine shared control.…”

Section: Driver Behavior Modelmentioning

confidence: 99%

A review of essential technologies for collision avoidance assistance systems

Zhao

Zhou

Zhu

et al. 2017

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Compared with automatic collision avoidance systems, collision avoidance assistance systems have attracted more research interest because they help avoid collisions in near-accident situations. However, ensuring the robustness and reliability of collision avoidance assistances is difficult because of problems in reliable environment recognition, accurate collision avoidance decision making, and driver acceptance. This article reviews and analyzes three essential technologies for collision avoidance assistance systems in intelligent environment-friendly vehicles. The architecture of the human-inloop system is summarized, and available environment recognition methods used in collision avoidance assistances are compared. Moreover, the characteristics of path planning and collision avoidance decision making applied in emergency collision avoidance assistance systems are reviewed, and the advantages of applying haptic share control and yaw moment active intervention during path tracking are analyzed. The emergency collision avoidance assistance systems based on driver behavior models and HSC were found to be the most suitable for high-speed emergency conditions. Such systems are not only highly robust but also more likely to be accepted by drivers.

show abstract

Section: Driver Behavior Modelmentioning

confidence: 99%

A review of essential technologies for collision avoidance assistance systems

Zhao

Zhou

Zhu

et al. 2017

Advances in Mechanical Engineering

View full text Add to dashboard Cite

show abstract

“…The systems do not only react to driving situations, but are also able to actively intervene in order to protect occupants and vulnerable road users. Seven demonstrator vehicles -six passenger cars of di erent vehicle classes and one truck -were built up to develop, test, and evaluate the next generation of safety systems (Heesen et al, 2015).…”

Section: Interactivementioning

confidence: 99%

Experimental vehicles FASCar®-II and FASCar®-E

Kaschwich¹,

Wölfel²

2017

JLSRF

View full text Add to dashboard Cite

Abstract:The main goal of the large-scale research facility FASCar ® are scienti c studies and analyses in the eld of driver assistance and vehicle automation. This includes also studies of human behavior, acceptance studies, test of new assistance systems and automation, as well as user friendliness. FASCar ® makes it possible to test and analyze innovative systems and developed functions in a simulated or even real tra c environment.

show abstract

“…Moreover, despite of advanced sensing and control techniques, Advance Driver Assistance System (ADAS) with emergency steering for collision avoidance is not yet available for public [5]. Additionally, drivers tend to perform actions that are against automatic steering assistance at subconscious level [6]. Overall, the applicability of steering interventions have a limited agreement with drivers whereas braking is in favor.…”

Section: Introductionmentioning

confidence: 99%

Brake Maneuver Prediction – An Inference Leveraging RNN Focus on Sensor Confidence

Liu

Koch

Gahr

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

In recent years, driver behavior analysis has led to countless driver assistance systems. In these systems, earlier detection of a driver's maneuver intentions offers opportunities to improve driving experience and safety. Especially brake maneuvers are of fundamental importance because they are directly related to the avoidance of potential hazards. Current state-of-the-art brake assistance systems rely on the release speed of accelerator pedal as an indicator whether a brake event is planned. However, this simple and practical algorithm, fails to capture the overall movement pattern of accelerator pedal behaviors and cannot utilize rich information from different vehicle sensors. To address this issue, we propose a novel recurrent neural network architecture for the purpose of brake maneuver prediction. The proposed method exploits the advantages of multiple sensors. Unlike conventional practices where all signals are aggregated to a single neural network, we leverage the confidence of each sensor. We evaluate our approach based on a dataset of 44 drivers, comprising around 500 hours of naturalistic driving data. The evaluation results show that the proposed algorithm outperforms baseline method by large margin.

show abstract

Interaction design of automatic steering for collision avoidance: challenges and potentials of driver decoupling

Cited by 38 publications

References 15 publications

A review of essential technologies for collision avoidance assistance systems

A review of essential technologies for collision avoidance assistance systems

Experimental vehicles FASCar®-II and FASCar®-E

Brake Maneuver Prediction – An Inference Leveraging RNN Focus on Sensor Confidence

Contact Info

Product

Resources

About