Aimsun and UC Berkley announce traffic management tool | Smart Highways Magazine: Industry News

Aimsun and UC Berkley announce traffic management tool

Share this story...Tweet about this on TwitterShare on LinkedInShare on FacebookShare on Google+Email this to someonePrint this pageBuffer this pagePin on PinterestShare on StumbleUponShare on Tumblr

UC Berkeley’s Institute of Transportation Studies and Aimsun have created a tool for managing large-scale traffic systems that feature a mix of human-driven and autonomous vehicles.

Flow is now integrated with Aimsun Next mobility modelling software to become what the firm says is the first open source architecture to integrate microsimulation tools with state-of-the-art deep reinforcement learning libraries in the cloud.

“Working harmoniously with others, be those professional relationships or software interfaces, has always been a core value at Aimsun,” said the company’s President Alex Gerodimos. “Our ongoing collaboration with UC Berkeley exemplifies this philosophy perfectly at both levels: our decision to lend our direct and complete support to this project was very deliberate and our software users will be able to benefit immediately from these new machine learning libraries as a result.”

Aimsun explains that Flow provides a suite of pre-built traffic control scenarios, tools for designing custom traffic scenarios, and integration with deep reinforcement learning libraries such as RLlib and traffic microsimulation libraries, which can be used to apply deep reinforcement learning breakthroughs to various cases in traffic management, which involve classical traffic infrastructure such as traffic lights and metering, and mobile infrastructure which involves mixed autonomy traffic using connected and automated vehicles to regulate traffic.

Flow is designed to allow users to build modular traffic-scenarios which can be combined to tackle complex situations, breaking a problem down into smaller, tractable pieces that can be composed as controllers for new scenarios.

In mixed-autonomy traffic control, evaluating machine learning methods is challenging due to the lack of standardised benchmarks,” added Alexandre Bayen, Director, 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.”


No comments yet.