Aimsun enters partnership to develop tool for managing mixed-autonomy traffic

Aimsun has partnered with UC Berkeley’s Institute of Transportation Studies to develop Flow, a tool for managing large-scale traffic systems where human-driven and autonomous vehicles (AVs) operate together. Flow offers a suite of pre-built traffic scenarios and is now integrated with Aimsun Next mobility modelling software. The open source architecture knits together microsimulation tools with deep reinforcement learning libraries in the cloud. Launched last September, Flow allows users to build and
January 15, 2019 Read time: 2 mins

16 Aimsun has partnered with UC Berkeley’s Institute of Transportation Studies to develop Flow, a tool for managing large-scale traffic systems where human-driven and autonomous vehicles (AVs) operate together.

Flow offers a suite of pre-built traffic scenarios and is now integrated with Aimsun Next mobility modelling software. The open source architecture knits together microsimulation tools with deep reinforcement learning libraries in the cloud.

Launched last September, Flow allows users to build and combine modular traffic scenarios to tackle complex situations, the company says. For example, single-lane/multi-lane and merge building blocks can be used to study stop-and-go merging traffic behaviours along a highway.  

“In mixed-autonomy traffic control, evaluating machine learning methods is challenging due to the lack of standardised benchmarks,” says Alexandre Bayen, director, 8895 ITS Berkeley. “Systematic evaluation and comparison will not only further our understanding of the strengths of existing algorithms but also reveal their limitations and suggest directions for future research.”

Urban Traffic Control

For more information on companies in this article

Related Content

  • TRA 2018: Vienna conference highlights
    June 5, 2018
    Digitalisation of transport systems, the regulation of new technologies and more charging points for electric vehicles in cities were among the talking points at this year’s Transport Research Arena conference. Alan Dron sifts through the highlights in Vienna. More than 3,000 transport sector specialists converged on TRA 2018, where the four-day event’s agenda included scores of topics covering regulation, technology and the effect of the digitalisation of road transport systems. Who should control those
    Read More
  • Infrastructure and the autonomous vehicle
    December 12, 2014
    Harold Worrall ponders the effect of autonomous vehicles on transportation infrastructure. For the last century the transportation industry has been focused on the supply of infrastructure to support the ever growing fleet of vehicles and the greater number of miles covered by each vehicle. Our focus has been planning, funding, designing, building and maintaining roadways. Politicians, engineers, planners, financial managers … all of us have had this focus. We have experienced demand growth since the first
    Read More
  • PTV takes lessons from logistics software to help test AV behaviour
    June 7, 2018
    Some people in the transportation industry may be reluctant to treat travellers as goods that need to be shipped from point A to point B. The traffic software engineers at PTV Group are not some of those people. According to Jongsun Won, the lessons he and his colleagues have learned from years of creating logistics software are extremely useful in the new age of autonomous vehicles. “In an autonomous vehicle, people are essentially the goods that are being transported around a city,” Won said. “There are
    Read More
  • Self-driving cars ‘a US$87 billion opportunity in 2030’
    May 22, 2014
    The latest research from Lux Research indicates that automakers and technology developers are closer than ever to bringing self-driving cars to market, with basic Level 2 autonomous behaviour already coming to market, in the form of relatively modest self-driving features like adaptive cruise control, lane departure warning, and collision avoidance braking. With these initial steps, automakers are already on the road to some level of autonomy, but costs remain high in many cases. It is the higher levels
    Read More

Highlighted Content