Flow: A Modular Learning Framework for Mixed Autonomy Traffic

Cathy Wu, Abdul Rahman Kreidieh, Kanaad Parvate, Eugene Vinitsky, Alexandre M. Bayen

Research output: Contribution to journalArticlepeer-review


The rapid development of autonomous vehicles (AVs) holds vast potential for transportation systems through improved safety, efficiency, and access to mobility. However, the progression of these impacts, as AVs are adopted, is not well understood. Numerous technical challenges arise from the goal of analyzing the partial adoption of autonomy: partial control and observation, multivehicle interactions, and the sheer variety of scenarios represented by real-world networks. To shed light into near-term AV impacts, this article studies the suitability of deep reinforcement learning (RL) for overcoming these challenges in a low AV-adoption regime. A modular learning framework is presented, which leverages deep RL to address complex traffic dynamics. Modules are composed to capture common traffic phenomena (stop-and-go traffic jams, lane changing, intersections). Learned control laws are found to improve upon human driving performance, in terms of system-level velocity, by up to 57% with only 4-7% adoption of AVs. Furthermore, in single-lane traffic, a small neural network control law with only local observation is found to eliminate stop-and-go traffic - surpassing all known model-based controllers to achieve near-optimal performance - and generalize to out-of-distribution traffic densities.

Original languageEnglish (US)
Pages (from-to)1270-1286
Number of pages17
JournalIEEE Transactions on Robotics
Issue number2
StatePublished - Apr 1 2022


  • Automation technologies for smart cities
  • deep learning in robotics and automation
  • deep reinforcement learning
  • intelligent transportation systems

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Flow: A Modular Learning Framework for Mixed Autonomy Traffic'. Together they form a unique fingerprint.

Cite this