Virtual testing of automated vehicles using simulations is essential during their development. When it comes to the testing of motion planning algorithms, one is mainly interested in challenging, critical scenarios for which it is hard to find a feasible solution. However, these situations are rare under usual traffic conditions, demanding an automatic generation of critical test scenarios. We present an approach that automatically generates critical scenarios based on a minimization of the solution space of the vehicle under test. By formulating a scenario parametrization and automatic determination of relevant parameter intervals, we are able to optimize the criticality of complex scenarios. We use evolutionary algorithms to tackle the resulting highly nonlinear optimization problem. Compared to our previous approach, we are now able to handle complex situations, in particular those involving intersections. Finally, we demonstrate our approach by generating critical scenarios from initially uncritical scenarios.

Generating Critical Test Scenarios for Automated Vehicles with Evolutionary Algorithms.

Automated Driving Systems (ADS) have made great achievements in recent years thanks to the efforts from both academia and industry. A typical ADS is composed of multiple modules, including sensing, perception, planning, and control, which brings together the latest advances in different domains. Despite these achievements, safety assurance of ADS is of great significance, since unsafe behavior of ADS can bring catastrophic consequences. Testing has been recognized as an important system validation approach that aims to expose unsafe system behavior; however, in the context of ADS, it is extremely challenging to devise effective testing techniques, due to the high complexity and multidisciplinarity of the systems. There has been great much literature that focuses on the testing of ADS, and a number of surveys have also emerged to summarize the technical advances. Most of the surveys focus on the system-level testing performed within software simulators, and they thereby ignore the distinct features of different modules. In this paper, we provide a comprehensive survey on the existing ADS testing literature, which takes into account both module-level and system-level testing. Specifically, we make the following contributions: (1) we survey the module-level testing techniques for ADS and highlight the technical differences affected by the features of different modules; (2) we also survey the system-level testing techniques, with focuses on the empirical studies that summarize the issues occurring in system development or deployment, the problems due to the collaborations between different modules, and the gap between ADS testing in simulators and the real world; (3) we identify the challenges and opportunities in ADS testing, which pave the path to the future research in this field.

https://dl.acm.org/doi/pdf/10.1145/3579642

A Survey on Automated Driving System Testing: Landscapes and Trends

Congestion is an ongoing problem for many urban centres worldwide (such as London), leading to excessive delays, noise and air pollution, frustrated drivers, and high energy consumption. The carbon footprint of conventional transport systems can be high as a result and transport is among the highest contributors of greenhouse gas emissions. Therefore, with the growing interest in developing connected fully autonomous vehicles (ConFAVs), there is a pressing need to consider their effects within the congested urban setting. To address this, the current research study was designed to investigate the potential for ConFAVs in providing a sustainable transport solution. During this research, a simulation model was developed, calibrated, and validated using field data collected from several sites in East London, using the graphical user interface (GUI) simulation software PTV VISSIM to simulate the proposed driving and car following behaviour, which included the platooning of these ConFAVs, to assess how they could improve the level of service of the roads. Using the new model, this research addresses the shortcomings of two other adaptations of the Wiedemann 99 car-following models by changing the ConFAV’s behaviour to be more cautious when travelling behind a human driven vehicle, and less cautious when behind another ConFAV. As little is known about the transitional period from zero autonomy to full autonomy on the already congested road network, due to the fact that these vehicles are typically tested in small numbers (often one at a time in a controlled environment), the present research study introduced ConFAVs to the simulated network gradually and in large numbers at 20% intervals (namely 0% where there are no ConFAVs, 20%, 40%, 60%, 80%, and finally 100% where all vehicles within the network were ConFAVs). The average delays and subsequent level of service for the roads within the networks were then assessed against each ConFAV penetration level. This helped understand how the network’s efficiency changes when the number of ConFAVs increases, and the potential benefits for these self-driving vehicles on congestion and the ensuing greenhouse gas emissions. The model showed that a reduction in delay of up to 100% can be achieved by introducing ConFAVs, which translates to a significant reduction in greenhouse gas emissions. This, coupled with the fact that ConFAVs are predominantly electric, points to a future sustainable road transport system. The primary purpose of this research would be to investigate the potential of ConFAVs in reducing traffic congestion and, as a result, greenhouse gas emissions.

/pdf/potential-of-connected-fully-autonomous-vehicles-in-reducing-2kva6nie.pdf

Potential of Connected Fully Autonomous Vehicles in Reducing Congestion and Associated Carbon Emissions

Trajectory planning is key component for autonomous vehicles. However, most existing trajectory planning methods which utilized a set of fixed weights to evaluate an optimal trajectory from a set of trajectory candidates may change abruptly in complex dynamic scenarios. In this study, a robust trajectory planning was proposed based on historical information. The developed trajectory planning is mainly consisting of candidate trajectories generation module, the collision detection module, the stability detection module and the speed planning module. Firstly, the candidate trajectories are generated according to the vehicle kinematics model. And then the collision detection module is used to remove the dangerous trajectories. Then, the optimal trajectory is selected by the multi-attribute indicators evaluation, and the selected trajectory is checked by the stability detection module based on the lateral deviation of the optimal trajectory from the historical trajectory. Based on its result, the current optimal trajectory or the historical trajectory is chosen as the output trajectory. Finally, based on the output trajectory, the speed planning module is executed to generate a smooth trajectory. Simulation and field experiments were conducted to evaluate the effectiveness of the proposed method.

A Robust Trajectory Planning Method Based on Historical Information for Autonomous Vehicles

Autonomous driving systems (ADS) are safety-critical systems that require thorough testing to ensure their safety. Current testing methods for ADS primarily focus on finding crash scenarios involving ADS. However, most of these scenarios are unavoidable by ADS, such as collisions caused by the reckless behavior of other vehicles. To address this limitation, we propose CollVer, a framework designed to generate and identify scenarios in which ADS violate driving rules. Specifically, CollVer utilizes multi-modal technology by taking the violation scenario and the corresponding accident description as inputs to judge whether the accident can be attributed to the ADS. Moreover, CollVer introduces a metric called collision position coverage (CPC), to quantify and guide the selection of test cases. Finally, CollVer integrates the multi-modal model and the CPC metric into a multi-objective genetic algorithm to explore more diverse and challenging scenarios. We evaluate CollVer on an industrial-grade ADS, Baidu Apollo, and experimental results show that CollVer can identify 10 distinct types of safety violations, with 4 of them resulting from ADS violating driving rules. 

From Collision to Verdict: Responsibility Attribution for Autonomous Driving Systems Testing

As the development of the autonomous vehicles, the test and evaluation of the autonomy of autonomous vehicles has receiving considerable attentions from both academic and industrial research fields recently. How to rapid identify the performance boundaries of autonomous vehicles and then to accelerate the testing has been considered as one of the most important problems. Simulation test and challenging scenarios are considered as two effective ways to solve above problems. In this research, a framework of rapid generation of challenging simulation scenarios based on adversarial test was proposed. An optimization model based on newly developed indicators, i.e., safety, smoothness, sharpness and smartness, was proposed to assess the autonomy of autonomous vehicles. Due to the high dimensionality of the configuration space and computation complexity of the optimization problem, a quantum genetic algorithm was employed to solve the optimization problem owing to its high search ability and lower population size required. A simulation system based on Prescan, Carsim and Simulink was built to validate the effectiveness of the proposed method. Comparative experiments also were conducted to illustrate the efficiency of the proposed optimization algorithm.

Rapid Generation of Challenging Simulation Scenarios for Autonomous Vehicles Based on Adversarial Test

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Bichun Li

Author Tools

Chat about Author

Papers

Rapid Generation of Challenging Simulation Scenarios for Autonomous Vehicles Based on Adversarial Test