Low-Cost Urban Test Scenario Generation Using Microscopic Traffic Simulation

Abstract

Scenario-based testing is already a well-known test approach to the automotive industry for the Validation, Verification and Testing of Connected and Automated Vehicles. How to construct the scenarios of complex traffic environment is a major challenge to this method. A common approach for generating scenarios is collecting and post-processing natural traffic data with a lot of time and money costs. In order to reduce the cost of scenario collection, we propose a low-cost method based on Microscopic Traffic Simulation to obtain a large number of urban traffic scenarios. Based on public data, we establish a microscopic traffic model for a specific area within the Shenzhen urban. Through a simulation, the 24-hour traffic behavior of vehicles for this area is simulated. About 189,752 scenarios covering the entire travel process are generated, which is equivalent to the data collected by a well-equipped car traveling 254,480 kms or 8,288 h. Our scenarios include not only typical urban scenarios such as U-turn and Parallel-driving (two vehicles driving in parallel on a single lane), but also collision accident scenarios of various forms. In addition, in order to evaluate the risks faced by Connected and Automated Vehicles in different scenarios, we design a new criticality metric, Scenario Risk Index, based on the risk assessment principle. The Scenario Risk Index has nothing to do with a certain function, and can quantitatively comprehensively evaluate the criticality and loss of potential accidents. INDEX TERMS Test scenario, microscopic traffic simulation, traffic conflict technique, risk assessment.

Finding Critical Scenarios for Automated Driving Systems: A Systematic Literature Review

“…By searching for the combination that contains the fewest scenarios but still covers all the SCPs, and using this set of scenarios to replace the original combination of test scenarios, the redundant evaluation scenarios were deleted. Using simulation as the method, the authors in [74] used public traffic data to calibrate SUMO (simulation tool, Simulation of Urban MObility) to perform traffic simulation. Based on the simulation results, the data is post-processed to extract concrete crash scenarios.…”

“…However, none of the primary studies provide an explicit ODD definition. Some of the primary studies explicitly or implicitly provide the scope of the ODD, e.g., driving on a highway [30], [61] and driving on a structured road [62], [63], [73], [74]. Methods in these studies make assumptions about the environment (e.g., the behavior of other vehicles) within the ODD, and propose systematics to reason about critical functional scenarios based on these assumptions.…”

“…These methods can be found in Sections 6.1, 6.2 and 6.5. The second type requires multiple critical concrete scenarios to synthesize new critical scenarios [73], [74], [94], [109]. This type of method is introduced in Section 6.3.…”

“…Compared to the previous section, articles [74], [94], [101], [109] in this section do not use accident databases as the data source to find the critical pre-crash scenarios. Their used data type can be mainly grouped into sensor data, traffic data and others.…”

Multisource‐multitarget cooperative positioning based on the fusion of inter‐vehicle relative vector in internet of vehicles

“…So, a variety of traffic behaviours are reproduced by MTS. Based on public data, we have simulated an ITS traffic scenario by MTS in a specific area of Shenzhen [38]. The open source software Simulation of Urban Transportation (SUMO) [39] is used as the core tool for MTS to simulate real traffic scenarios, and export the state parameters and trajectory information of ICVs.…”