Risk Assessment for Integral Safety in Automated Driving

Hruschka, Clemens Markus; Töpfer, Daniel; Zug, Sebastian

doi:10.1109/icoias.2019.00025

Cited by 14 publications

(8 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [37]- [41], risk quantification is proposed for real-time use, e.g., to support the path planning of a self-driving vehicle, so this is not intended to be used for a prospective risk assessment. In [42], a method for quantifying the risk of scenarios is proposed based on the probability of occurrence of so-called environmental conditions and the probability that an error propagates in the fault tree given a specified environment condition.…”

Section: A Risk Quantification Of Automated Driving Systemsmentioning

confidence: 99%

Risk Quantification for Automated Driving Systems in Real-World Driving Scenarios

Gelder¹,

Elrofai²,

Saberi

et al. 2021

IEEE Access

View full text Add to dashboard Cite

The development of safety validation methods is essential for the safe deployment and operation of Automated Driving Systems (ADSs). One of the goals of safety validation is to prospectively evaluate the risk of an ADS dealing with real-world traffic. ISO 26262 and ISO/DIS 21448, the leading standards in automotive safety, provide an approach to estimate the risk where the former focuses on risks due to potential malfunctioning of components and the latter focuses on risks due to possible functional insufficiencies. The main shortcomings of the approach provided in ISO 26262 are that it depends on subjective judgments of safety experts and that only a qualitative risk estimation is performed. ISO/DIS 21448 addresses these shortcomings partially by providing statistical methods to guide the safety validation, but no complete method is provided to quantify the risk. The first objective of this article is to propose a method to estimate the risk of an ADS in a more quantitative and objective manner. A data-driven approach is used to rely less on subjective judgments of safety experts. The output of the method is the expected number of injuries in a potential collision. Thus, the method is quantitative, the result is easily interpretable, and the result can be compared with road crash statistics. The second objective is to provide a method that supports the risk assessment as stipulated by the ISO 26262 and ISO/DIS 21448 standards by decomposing the quantified risk into the 3 aspects of risk as mentioned in these standards: exposure, severity, and controllability. The proposed methods are illustrated by means of a case study in which the risk is quantified for a longitudinal controller in 3 different types of scenarios. The code of the case study is publicly available.

show abstract

Section: A Risk Quantification Of Automated Driving Systemsmentioning

confidence: 99%

Risk Quantification for Automated Driving Systems in Real-World Driving Scenarios

Gelder¹,

Elrofai²,

Saberi

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The speed of ACV in highway scenarios should be bounded, as illustrated in Eq. (25). Meanwhile, the ACV should stay within the drivable area, as shown in Eq.…”

Section: ) Motion Prediction Of Acvmentioning

confidence: 99%

“…Interactive multiple models (IMMs) is used for motion prediction of surrounding vehicles. Hruschka et al used maneuver-based motion models to predict the motion of SVs, and evaluated the collision risk with a combination of collision probability and collision severity [25]. In literature [26], the risk is defined as the expectation value of the cost related to a future critical event.…”

Section: Introductionmentioning

confidence: 99%

Surrounding Vehicles Motion Prediction for Risk Assessment and Motion Planning of Autonomous Vehicle in Highway Scenarios

et al. 2020

View full text Add to dashboard Cite

Safety is the cornerstone of autonomous driving vehicles. For autonomously controlled vehicles driving safely in complex and dynamic traffic scenarios, it is essential to predict the evolution of the current traffic situation in the near future and make an accurate situation risk assessment. The precise motion prediction of surrounding vehicles is an essential prerequisite for risk assessment and motion planning of autonomous vehicles. In this paper, we propose a risk assessment and motion planning method for autonomously controlled vehicles based on motion prediction of surrounding vehicles. Firstly, surrounding vehicles' trajectories are predicted based on fusing constant turn rate and acceleration-based motion prediction model and maneuver-based motion prediction model with interactive multiple models. Then, the collision risk assessment between autonomously controlled vehicle and surrounding vehicles is conducted with a collision risk index considering both the probability of collision event and collision severity. After that, the motion planning of autonomously controlled vehicle is formulated as a multiobjectives and multi-constraints optimization problem with model predictive control. Finally, the proposed method is applied to several traffic scenarios to validate its feasibility and effectiveness. INDEX TERMS Autonomous vehicles, motion prediction, risk assessment, motion planning, model predictive control.

show abstract

“…In our work, we rely on a defined environment and vehicle transition model to explicitly incorporate traffic rules and provide safety [16]. We propose to couple the reliability of a model-based planning system with the generalization ability of deep inverse reinforcement learning.…”

Section: Related Workmentioning

confidence: 99%

Driving Style Encoder: Situational Reward Adaptation for General-Purpose Planning in Automated Driving

Rosbach,

James,

Großjohann

et al. 2019

Preprint

View full text Add to dashboard Cite

General-purpose planning algorithms for automated driving combine mission, behavior, and local motion planning. Such planning algorithms map features of the environment and driving kinematics into complex reward functions. To achieve this, planning experts often rely on linear reward functions. The specification and tuning of these reward functions is a tedious process and requires significant experience. Moreover, a manually designed linear reward function does not generalize across different driving situations. In this work, we propose a deep learning approach based on inverse reinforcement learning that generates situation-dependent reward functions. Our neural network provides a mapping between features and actions of sampled driving policies of a modelpredictive control-based planner and predicts reward functions for upcoming planning cycles. In our evaluation, we compare the driving style of reward functions predicted by our deep network against clustered and linear reward functions. Our proposed deep learning approach outperforms clustered linear reward functions and is at par with linear reward functions with a-priori knowledge about the situation.

show abstract

Risk Assessment for Integral Safety in Automated Driving

Cited by 14 publications

References 28 publications

Risk Quantification for Automated Driving Systems in Real-World Driving Scenarios

Risk Quantification for Automated Driving Systems in Real-World Driving Scenarios

Surrounding Vehicles Motion Prediction for Risk Assessment and Motion Planning of Autonomous Vehicle in Highway Scenarios

Driving Style Encoder: Situational Reward Adaptation for General-Purpose Planning in Automated Driving

Contact Info

Product

Resources

About