Fuel Consumption Reduction of Multi-Lane Road Networks using Decentralized Mixed-Autonomy Control

In this work, we demonstrate optimization of fuel economy in a large, calibrated model of a portion of the Ventura Freeway using a low penetration rate of controlled autonomous vehicles. We create waves in this network using a string-unstable car-following model and introduce a ghost cell to allow waves to propagate out of the network. Using multi-agent reinforcement learning, we then design a controller that manages to partially dampen the waves and thus increase the average energy efficiency of the system, yielding a 25% fuel consumption reduction at a 10% penetration rate. Finally, we investigate the robustness properties of the designed controller. We find that the controller regulates the system to its equilibrium speed over a wide range of speeds and penetrations outside the training set, indicating generalization and robustness.