When will automated vehicles come onto the market? This question has puzzled the automotive industry and society for years. The technology and its implementation have made rapid progress over the last decade, but the challenge of how to prove the safety of these systems has not yet been solved. Since a market launch without proof of safety would neither be accepted by society nor by legislators, much time and many resources have been invested into safety assessment in recent years in order to develop new approaches for an efficient assessment. This paper therefore provides an overview of various approaches, and gives a comprehensive survey of the so-called scenario-based approach. The scenario-based approach is a promising method, in which individual traffic situations are typically tested by means of virtual simulation. Since an infinite number of different scenarios can theoretically occur in real-world traffic, even the scenario-based approach leaves the question unanswered as to how to break these down into a finite set of scenarios, and find those which are representative in order to render testing more manageable. This paper provides a comprehensive literature review of related safety-assessment publications that deal precisely with this question. Therefore, this paper develops a novel taxonomy for the scenario-based approach, and classifies all literature sources. Based on this, the existing methods will be compared with each other and, as one conclusion, the alternative concept of formal verification will be combined with the scenario-based approach. Finally, future research priorities are derived.

/pdf/survey-on-scenario-based-safety-assessment-of-automated-2u2a6wl7tk.pdf

Survey on Scenario-Based Safety Assessment of Automated Vehicles

The automotive industry is undergoing major transformation, with the emergence of vehicular networks, intelligent transportation systems, and autonomous cars over the last decade. These technologies are made possible by recent advances of software, hardware, and communication systems, along with the development of various applications and standards. Today, new technologies are incorporated into cars that detect potential road hazards and improve the driving experience. There are three key components being integrated into cars: sensors, information systems, and communication technologies to create connected vehicle networks. Vehicle-to-vehicle (V2V) communication is being used in connected networks to reduce traffic congestion, improve passengers’ safety, and enable the efficient management of vehicles on roads. Here, we present recent research developments and current trends in V2V communications. We discuss architectural issues and wireless technologies that support V2V. We also present recently proposed security solutions for V2V. Finally, we discuss outstanding challenges for enabling the deployment and adoption of V2V technology.

A tutorial survey on vehicle-to-vehicle communications

One major task in automated driving is the development of robust and safe visual perception modules. It is of utmost importance that visual perception reacts adequately to so-called corner cases, which range from overexposure of the image sensor to unexpected and potentially dangerous traffic situations. Their detection thus has high significance both as an online system in the intelligent vehicle, but also in the extraction of relevant training and test data for perception modules. In this paper, we provide a systematization of corner cases for visual perception in automated driving, with the categories being structured by detection complexity. Furthermore, we discuss existing metrics and datasets which can be used for the evaluation of corner case detection methods depending on their suitability to provide beneficial information for the various categories.

Systematization of Corner Cases for Visual Perception in Automated Driving

For a successful market launch of automated vehicles (AVs), proof of their safety is essential. Due to the open parameter space, an infinite number of traffic situations can occur, which makes the proof of safety an unsolved problem. With the so-called scenario-based approach, all relevant test scenarios must be identified. This paper introduces an approach that finds particularly challenging scenarios from real driving data (\RDDwo) and assesses their difficulty using a novel metric. Starting from the highD data, scenarios are extracted using a hierarchical clustering approach and then assigned to one of nine pre-defined functional scenarios using rule-based classification. The special feature of the subsequent evaluation of the concrete scenarios is that it is independent of the performance of the test vehicle and therefore valid for all AVs. Previous evaluation metrics are often based on the criticality of the scenario, which is, however, dependent on the behavior of the test vehicle and is therefore only conditionally suitable for finding "good" test cases in advance. The results show that with this new approach a reduced number of particularly challenging test scenarios can be derived.

Identification of Challenging Highway-Scenarios for the Safety Validation of Automated Vehicles Based on Real Driving Data

An immense test space is pushing the development and testing of automated driving functions from real to virtual environments. The virtual world is provided by interconnected simulation models representing sensors, vehicle dynamics, and both static and dynamic environment. For the virtual validation of automated driving, special attention must be paid to the simulation’s credibility, which can be impaired by inappropriate or inaccurate simulation models and tools. Therefore, in this work a method is proposed to assess the credibility of simulation-based testing for automated driving. The approach allows a qualitative and relatively quantitative comparisons between scenarios as well as between different simulation setups. Therefore, several uni- and multivariate metrics are applied towards a scoring of similarity of the behavior between simulation and real test drive. This is achieved by using ground truth data in form of simulation scenarios from real world measurement data. In this way, the virtual automated vehicle encounters the same conditions and surroundings than its counterpart in the real world for evaluating their similarity. The practical applicability of the proposed credibility assessment approach is demonstrated in a case study, in which the credibility of an exemplary simulation-based test bench is inferred.

/pdf/a-credibility-assessment-approach-for-scenario-based-virtual-t51vaz2b.pdf

A Credibility Assessment Approach for Scenario-Based Virtual Testing of Automated Driving Functions

Advanced Driver Assistance Systems are becoming more dominant due to their improved safety and comfort potential. Any functional development performed in this domain progresses conjointly with its validation and testing. The current trend is to use scenario-based testing approaches which are formed by the hand-driven scenario data-sets and expert inputs. However, in Autonomous Driving domain, testing all possible cases and combination of multiple parameters is not feasible due to sheer number of test-cases required, while the coverage of these expert-knowledge based sets cannot be quantitatively assessed. Extracted scenarios from realworld data can be used to strengthen the breadth of the expert knowledge driven scenario data-set. In this work, we propose three methods to extract scenarios from the time-series states of the real-world measurement data. Specifically, multiple classification algorithms are deployed for inference on i) time domain that identifies when an action occurred and ii) scenario domain that identifies what happened during this time period. Experimental evaluation over real-world collected data validates the efficacy of each of these methods even under sensor noise and other artefacts propagated to the realworld measurement values. Varying precision and recall metrics observed over the models identify the strength/weaknesses of the evaluated approach.

Real- World Maneuver Extraction for Autonomous Vehicle Validation: A Comparative Study

We present an Adaptive Cruise Control (ACC) architecture which is focused on solving repetitive switching issues between two modes of ACC, speed control and distance control. A cascaded controller structure has been used. First controller (upper) includes two modes: a speed controller (PI) and a distance controller (time-gap). Outputs of these controllers are acceleration reference signals. The second controller (lower) is responsible of providing the desired acceleration by controlling throttle. The switching problem occurs in most algorithms between two modes of the upper controller. In the proposed method, additional to the normal switching logic which is checking the distance with the leading vehicle, a set of logical comparisons have been used to prevent repetitive mode changing at the exact desired distance.

Adaptive switching method for Adaptive Cruise Control

Vehicle autonomy definitionally is the act of processing information gathered from the environment and acting on the decisions formed based on this information. Therefore, any autonomous paradigm can only perform as good as the quality of the information it can understand. Lane identification forms the foundation of many of the autonomous drive and driver-assist technologies. However, current methods are not always reliable, especially under the edge-cases. In this paper, we have experimentally evaluated and extended the state-of-the-art deterministic lane detection methods. Our evaluation provides experimental evidence towards their efficacy in extreme cases: real-data with sharp shadows and varying lighting that is recorded through a camera that has a limited field of view. Experimental results suggest that a method that builds similarly to human perception performs better—with an increase of 32% in its accuracy. Our hypothesis is that autonomous vehicles that can perform even under these extreme conditions will play an important role on the fully autonomous systems.

Erkan Adali

Papers

Real- World Maneuver Extraction for Autonomous Vehicle Validation: A Comparative Study

Adaptive switching method for Adaptive Cruise Control

Detecting Road Lanes under Extreme Conditions: A Quantitative Performance Evaluation

Real- World Maneuver Extraction for Autonomous Vehicle Validation: A Comparative Study.