How safe is automated driving? Human driver models for safety performance assessment

2017 ◽  
Author(s):  
Christian Roesener ◽  
Johannes Hiller ◽  
Hendrik Weber ◽  
Lutz Eckstein
Keyword(s):  
Performance Assessment ◽  
Safety Performance ◽  
Automated Driving ◽  
Human Driver

Safety Enhancement by Automated Driving: What are the Relevant Scenarios?

2020 ◽  
Vol 64 (1) ◽  
pp. 1686-1690
Author(s):  
Niklas Grabbe ◽  
Michael Höcher ◽  
Alexander Thanos ◽  
Klaus Bengler
Keyword(s):  
Traffic Safety ◽  
Road Traffic ◽  
Test Cases ◽  
Automated Driving ◽  
Road Traffic Safety ◽  
Human Driver ◽  
Driving Task ◽  
Promising Solution ◽  
Vehicle Automation ◽  
Safety Enhancement

Automated driving offers great possibilities in traffic safety advancement. However, evidence of safety cannot be provided by current validation methods. One promising solution to overcome the approval trap (Winner, 2015) could be the scenario-based approach. Unfortunately, this approach still results in a huge number of test cases. One possible way out is to show the current, incorrect path in the argumentation and strategy of vehicle automation, and focus on the systemic mechanisms of road traffic safety. This paper therefore argues the case for defining relevant scenarios and analysing them systemically in order to ultimately reduce the test cases. The relevant scenarios are based on the strengths and weaknesses, in terms of the driving task, for both the human driver and automation. Finally, scenarios as criteria for exclusion are being proposed in order to systemically assess the contribution of the human driver and automation to road safety.

scholarly journals Driver intervention performance assessment as a key aspect of L3–L4 automated vehicles deployment

2021 ◽  
Vol 11 (1) ◽  
pp. 845-852
Author(s):  
Aleksandra Rodak ◽  
Paweł Budziszewski ◽  
Małgorzata Pędzierska ◽  
Mikołaj Kruszewski
Keyword(s):  
Performance Assessment ◽  
Minimal Risk ◽  
Automated Vehicles ◽  
Automated Driving ◽  
Driving System ◽  
Driving Task ◽  
Driving Conditions

Abstract In L3–L4 vehicles, driving task is performed primarily by automated driving system (ADS). Automation mode permits to engage in non-driving-related tasks; however, it necessitates continuous vigilance and attention. Although the driver may be distracted, a request to intervene may suddenly occur, requiring immediate and appropriate response to driving conditions. To increase safety, automated vehicles should be equipped with a Driver Intervention Performance Assessment module (DIPA), ensuring that the driver is able to take the control of the vehicle and maintain it safely. Otherwise, ADS should regain control from the driver and perform a minimal risk manoeuvre. The paper explains the essence of DIPA, indicates possible measures, and describes a concept of DIPA framework being developed in the project.

Exposure data and risk indicators for safety performance assessment in Europe

2013 ◽  
Vol 60 ◽  
pp. 371-383 ◽  
Author(s):  
Eleonora Papadimitriou ◽  
George Yannis ◽  
Frits Bijleveld ◽  
João L. Cardoso
Keyword(s):  
Performance Assessment ◽  
Safety Performance ◽  
Risk Indicators ◽  
Exposure Data

scholarly journals Development of Deep Learning Based Human-Centered Threat Assessment for Application to Automated Driving Vehicle

2019 ◽  
Vol 10 (1) ◽  
pp. 253 ◽  
Author(s):  
Donghoon Shin ◽  
Hyun-geun Kim ◽  
Kang-moon Park ◽  
Kyongsu Yi
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Threat Assessment ◽  
Collision Probability ◽  
Driver Model ◽  
Sequential Data ◽  
Automated Driving ◽  
Human Driver ◽  
Acceleration And Deceleration ◽  
The Individual

This paper describes the development of deep learning based human-centered threat assessment for application to automated driving vehicle. To achieve naturalistic driver model that would feel natural while safe to a human driver, manual driving characteristics are investigated through real-world driving test data. A probabilistic threat assessment with predicted collision time and collision probability is conducted to evaluate driving situations. On the basis of collision risk analysis, two kinds of deep learning have been implemented to reflect human driving characteristics for automated driving. A deep neural network (DNN) and recurrent neural network (RNN) are designed by neural architecture search (NAS), and by learning from the sequential data, respectively. The NAS is used to automatically design the individual driver’s neural network for efficient and effortless design process while ensuring training performance. Sequential trends in the host vehicle’s state can be incorporated through hand-made RNN. It has been shown from human-centered risk assessment simulations that two successfully designed deep learning driver models can provide conservative and progressive driving behavior similar to a manual human driver in both acceleration and deceleration situations by preventing collision.

scholarly journals Road Safety Performance Assessment: A New Road Network Risk Index for Info Mobility

2014 ◽  
Vol 111 ◽  
pp. 624-633 ◽  
Author(s):  
Vaiana Rosolino ◽  
Iuele Teresa ◽  
Astarita Vittorio ◽  
Festa D. Carmine ◽  
Tassitani Antonio ◽  
...  
Keyword(s):  
Performance Assessment ◽  
Road Safety ◽  
Road Network ◽  
Risk Index ◽  
Safety Performance ◽  
Network Risk

Safety performance assessment among control room operators based on feature extraction and genetic fuzzy system in the process industry

2018 ◽  
Vol 116 ◽  
pp. 590-602 ◽  
Author(s):  
Leila Omidi ◽  
Seyed Abolfazl Zakerian ◽  
Jebraeil Nasl Saraji ◽  
Esmaeil Hadavandi ◽  
Mir Saeed Yekaninejad
Keyword(s):  
Feature Extraction ◽  
Performance Assessment ◽  
Fuzzy System ◽  
Safety Performance ◽  
Process Industry ◽  
Control Room ◽  
Genetic Fuzzy System

Effects of Task-Induced Fatigue in Prolonged Conditional Automated Driving

2019 ◽  
Vol 61 (7) ◽  
pp. 1186-1199 ◽  
Author(s):  
Oliver Jarosch ◽  
Hanna Bellem ◽  
Klaus Bengler
Keyword(s):  
Automated Driving ◽  
Good Opportunity ◽  
Monitoring Task ◽  
Human Driver

Objective: The aim of this study was to investigate the effects of task-induced fatigue in prolonged conditional automated driving on takeover performance. Background: In conditional automated driving, the driver can engage in non–driving related tasks (NDRTs) and does not have to monitor the system and the driving environment. In the event that the system hits its limits, the human driver must regain control of the car. To ensure safety, adequate driver fallback performance is necessary. Effects of the drivers’ state and the engagement in NDRTs need to be investigated. Method: Seventy-three participants experienced prolonged conditional automated rides and simultaneously had to engage in either an activating quiz or a fatiguing monitoring task (between subjects). After 50 minutes, a takeover situation occurred, and participants had to regain control of the car. Results: Prolonged conditional automated driving and simultaneously engaging in NDRTs affected the driver’s state and the takeover performance of the participants. Takeover performance was impaired when participants had to deal with monotonous NDRTs. Conclusion: An engagement in monotonous monitoring tasks in conditional automated driving affects the driver’s state and takeover performance when it comes to takeover situations. Especially in prolonged automated driving, an adequate driver state seems to be necessary for safety reasons. Application: The results of this study demonstrate that engagement in monotonous NDRTs while driving conditionally automated may negatively affect takeover performance. A monitoring of the driver state and adapted assistance in a takeover situation seems to be a good opportunity to ensure safety.

Sign in / Sign up

Export Citation Format

Share Document