Project Goal:

Bottlenecks have the well known phenomenon of capacity drop, visible below, where increasing inflows to a system lead to a sudden decrease in outflow. Normally, this is avoided using traffic light ramp metering, but you can use autonomous vehicles instead! Unlike a traffic light, which can only control the inflow at one point, the autonomous vehicles can re-adjust their velocities to enable optimal merging. We call this control technique Lagrangian Control as the autonomous vehicles can apply control at any point in the traffic stream. Using deep reinforcement learning and Flow (https://flow-project.github.io) we can learn effective controllers that can help decongest this bottleneck.

Video Key

• Red vehicles are AVs
• White vehicles are human driven
• 10% of vehicles are autonomous
• Lane changing is disabled

Inflow 1000: No congestion for baseline and control

Inflow of 1800 - Controlled

• Permanent congestion is avoided
• Congestion occasionally forms but is recovered from
• Congestion forms before the bottleneck but this is unavoidable as the inflow exceeds maximum possible outflow

Inflow 2000 - Congestion without control, less with control

• Permanent congestion is avoided
• Congestion occasionally forms but is recovered from
• Congestion forms before the bottleneck but this is unavoidable as the inflow exceeds maximum possible outflow