Search Results

This works presents a Reinforcement Learning (RL) agent to implement a Cooperative Adaptive Cruise Control (CACC) system that simultaneously enhances energy efficiency and comfort, while also ensuring string stability. CACC systems are a new generation of ACC which systems rely on the communication of the so-called ego-vehicle with other vehicles and infrastructure using V2V and/or V2X connectivity. This enables the availability of robust information about the environment thanks to the exchange of information, rather than their estimation or enabling some redundancy of data. CACC systems have the potential to overcome one typical issue that arises with regular ACC, that is the lack of string stability. String stability is the ability of the ACC of a vehicle to avoid unnecessary fluctuations in speed that can cause traffic jams, dampening these oscillations along the vehicle string rather than amplifying them.

This paper deals with the energy efficiency of cooperative cruise control technologies when considering vehicle strings in a realistic driving environment. In particular, we design a cooperative longitudinal controller using a state-of-the-art model predictive control (MPC) implementation. Rather than testing our controller on a limited set of short maneuvers, we thoroughly assess its performance on a number of regulatory drive cycles and on a set of driving missions of similar length that were constructed based on real driving data. This allows us to focus our assessment on the energetic aspects in addition to testing the controller’s robustness. The analyzed controller, based on linear MPC, uses vehicle sensor data and information transmitted by the vehicle driving the string to adjust the longitudinal trajectory of the host vehicle to maintain a reduced inter-vehicular distance while simultaneously optimizing energy efficiency.