Fine-Tuning ADAS Algorithm Parameters

With the development of the Connected Vehicle technology that facilitates wirelessly communication among vehicles and road-side infrastructure, the Advanced Driver Assistance Systems (ADAS) can be adopted as an effective tool for accelerating traffic safety and mobility optimization at various highway facilities. To this end, the traffic management centers identify the optimal ADAS algorithm parameter set that enables the maximum improvement of the traffic safety and mobility performance, and broadcast the optimal parameter set wirelessly to individual ADAS-equipped vehicles. After adopting the optimal parameter set, the ADAS-equipped drivers become active agents in the traffic stream that work collectively and consistently to prevent traffic conflicts, lower the intensity of traffic disturbances, and suppress the development of traffic oscillations into heavy traffic jams. Successful implementation of this objective requires the analysis capability of capturing the impact of the ADAS on driving behaviors, and measuring traffic safety and mobility performance under the influence of the ADAS. To address this challenge, this research proposes a synthetic methodology that incorporates the ADAS-affected driving behavior modeling and state-of-the-art microscopic traffic flow modeling into a virtually simulated environment. Building on such an environment, the optimal ADAS algorithm parameter set is identified through an optimization programming framework to enable the maximum safety and mobility improvement. The developed methodology is tested at a freeway facility under both low and high ADAS market penetration rate scenarios. The identified optimal ADAS algorithm parameter set can be used to establish multiple traffic management strategies. These strategies form a pool of candidate plans for the traffic management team to select when they face different control objectives (e.g., safety improvement more important, mobility improvement more important, or balanced safety and mobility improvement). It is also found that the traffic system optimization becomes easier to achieve as the ADAS penetration rate becomes higher. This dataset is associated with the following publication: Liu, H., H. Wei, T. Zuo, Z. Li, and J. Yang. Fine-Tuning ADAS Algorithm Parameters for Optimizing Traffic Safety and Mobility in Connected Vehicle Environment. TRANSPORTATION RESEARCH. Elsevier Science Ltd, New York, NY, USA, 76: 132-149, (2017).

                                            [
  "020:00"
]
                                        

                                            {
  "fn": "Yingping Yang",
  "hasEmail": "mailto:yang.jeff@epa.gov"
}
                                        

                                            [
  {
    "title": "Supplemental Data File_Fine-Tuning ADAS Algorithm Parameters .docx",
    "mediaType": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
    "downloadURL": "https://pasteur.epa.gov/uploads/10.23719/1390778/Supplemental%20Data%20File_Fine-Tuning%20ADAS%20Algorithm%20Parameters%20.docx"
  }
]
                                        

                                            [
  "Advanced Driver Assistance System (ADAS)",
  "driver behavior modeling",
  "microscopic traffic flow modeling",
  "traffic safety and mobility optimization"
]
                                        

                                            [
  "020:097"
]
                                        

                                            {
  "name": "U.S. EPA Office of Research and Development (ORD)",
  "subOrganizationOf": {
    "name": "U.S. Environmental Protection Agency",
    "subOrganizationOf": {
      "name": "U.S. Government"
    }
  }
}
                                        

                                            [
  "https://doi.org/10.1016/j.trc.2017.01.003"
]
                                        

                                            null