Enhancing SUMO simulator for simulation based testing and validation of autonomous vehicles

Kusari, Arpan; Li, Pei; Yang, Hanzhi; Punshi, Nikhil; Rasulis, Mich; Bogard, Scott E.; LeBlanc, David J.

doi:10.1109/iv51971.2022.9827241

Cited by 18 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Software packages such as SUMO are also important in the context of testing and validating new technological developments such as autonomous vehicles. This is, for example, discussed in Schwarz and Wang (2022), Szalai et al (2020), and Kusari et al (2022). To deploy autonomous vehicles in the real world, lengthy and expensive testing phases are required.…”

Section: Literaturementioning

confidence: 99%

See 1 more Smart Citation

Microscopic traffic models, accidents, and insurance losses

Kim,

Kleiber,

Weber

2024

ASTIN Bull.

View full text Add to dashboard Cite

The paper develops a methodology to enable microscopic models of transportation systems to be accessible for a statistical study of traffic accidents. Our approach is intended to permit an understanding not only of historical losses but also of incidents that may occur in altered, potential future systems. Through such a counterfactual analysis, it is possible, from an insurance, but also from an engineering perspective, to assess the impact of changes in the design of vehicles and transport systems in terms of their impact on road safety and functionality. Structurally, we characterize the total loss distribution approximatively as a mean-variance mixture. This also yields valuation procedures that can be used instead of Monte Carlo simulation. Specifically, we construct an implementation based on the open-source traffic simulator SUMO and illustrate the potential of the approach in counterfactual case studies.

show abstract

Section: Literaturementioning

confidence: 99%

“…(2020), and Kusari et al . (2022). To deploy autonomous vehicles in the real world, lengthy and expensive testing phases are required.…”

Section: Introductionmentioning

confidence: 99%

Microscopic traffic models, accidents, and insurance losses

Kim,

Kleiber,

Weber

2024

ASTIN Bull.

View full text Add to dashboard Cite

show abstract

“…In Li et al [9], the open-source simulator for autonomous driving research CARLA 3 is combined with SUMO to create a traffic environment for training AVs. Another approach is followed by Kusari et al [8]. Here, the background traffic is approximated to reality by adjusting the parameter distribution of well-known car-following models from driving databases.…”

Section: Related Workmentioning

confidence: 99%

SUMO4AV: An Environment to Simulate Scenarios for Shared Autonomous Vehicle Fleets with SUMO Based on OpenStreetMap Data

et al. 2022

View full text Add to dashboard Cite

In the past years the progress in the development of autonomous vehicles has increased tremendously. There are still technical, infrastructural and regulative obstacles which need to be overcome. However, there is a clear consent among experts that fully autonomous vehicles (level 5 of driving automation) will become reality in the coming years or at least in the coming decades. When fully autonomous vehicles are widely available for a fair trip price and when they can easily be utilized, a big shift from privately owned cars to carsharing will happen. On the one hand, this shift can bring a lot of chances for cities like the need of less parking space. But on the other hand, there is the risk of an increased traffic when walking or biking trips are substituted by trips with shared autonomous vehicle fleets. While the expected social, ecological and economical impact of widely used shared autonomous vehicle fleets is tremendous, there are hardly any scientific studies or data available for the effects on cities and municipalities. The research project KI4ROBOFLEET addressed this demand. A result of the project was SUMO4AV, a simulation environment for shared autonomous vehicle fleets, which we present in this paper. This simulation tool is based on SUMO, an open-source traffic simulation package. SUMO4AV can support city planners and carsharing companies to evaluate the chances and risks of running shared autonomous fleets in their local environment with their specific infrastructure. At its core it comprises the mapping of OpenStreetMap1 entities into SUMO objects as well as a Scenario Builder to create different operation scenarios for autonomous driving. Additionally, the simulation tool offers a recursive execution with different fleet sizes and optimization strategies evaluated by economic and ecologic parameters. As evaluation of the toolset a simulation of an ordinary scenario was performed. The workflow to simulate the scenario for shared autonomous vehicle fleets was successfully processed with the SUMO4AV environment.

show abstract

“…Simulation testing has been widely adopted to speed up the testing process. Simulation testing [ 16 , 17 , 18 ] greatly reduces the economic and time costs of testing and increases the safety of the testing process. In the actual testing, we have encountered the problem of inaccurate/untimely GPS positioning.…”

Section: Introductionmentioning

confidence: 99%

Review on Functional Testing Scenario Library Generation for Connected and Automated Vehicles

Zhu¹,

Wang²,

Meng³

et al. 2022

Sensors

View full text Add to dashboard Cite

The advancement of autonomous driving technology has had a significant impact on both transportation networks and people’s lives. Connected and automated vehicles as well as the surrounding driving environment are increasingly exchanging information. The traditional open road test or closed field test, which has large costs, lengthy durations, and few diverse test scenarios, cannot satisfy the autonomous driving system’s need for reliable and safe testing. Functional testing is the emphasis of the test since features such as frontal collision and traffic sign warning influence driving safety. As a result, simulation testing will undoubtedly emerge as a new technique for unmanned vehicle testing. A crucial aspect of simulation testing is the creation of test scenarios. With an emphasis on the map generating method and the dynamic scenario production method in the test scenarios, this article explains many scenarios and scenario construction techniques utilized in the process of self-driving car testing. A thorough analysis of the state of relevant research is conducted, and approaches for creating common scenarios as well as brand-new methods based on machine learning are emphasized.

show abstract

Enhancing SUMO simulator for simulation based testing and validation of autonomous vehicles

Cited by 18 publications

References 17 publications

Microscopic traffic models, accidents, and insurance losses

Microscopic traffic models, accidents, and insurance losses

SUMO4AV: An Environment to Simulate Scenarios for Shared Autonomous Vehicle Fleets with SUMO Based on OpenStreetMap Data

Review on Functional Testing Scenario Library Generation for Connected and Automated Vehicles

Contact Info

Product

Resources

About