Energy-Saving Speed Planning for Electric Vehicles Based on RHRL in Car following Scenarios

Abstract

Eco-driving is a driving vehicle strategy aimed at minimizing energy consumption; that is, it is a method to improve vehicle efficiency by optimizing driving behavior without making any hardware changes, especially for autonomous vehicles. To enhance energy efficiency across various driving scenarios, including road slopes, car following scenarios, and traffic signal interactions, this research introduces an energy-conserving speed planning approach for self-driving electric vehicles employing reinforcement learning. This strategy leverages vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication to acquire real-time data regarding traffic signal timing, leading vehicle speeds, and other pertinent driving conditions. In the framework of rolling horizon reinforcement learning (RHRL), predictions are made in each window using a rolling time domain approach. In the evaluation stage, Q-learning is used to obtain the optimal evaluation value, so that the vehicle can reach a reasonable speed. In conclusion, the algorithm’s efficacy is confirmed through vehicle simulation, with the results demonstrating that reinforcement learning adeptly modulates vehicle speed to minimize energy consumption, all while taking into account factors like road grade and maintaining a secure following distance from the preceding vehicle. Compared with the results of traditional adaptive cruise control (ACC), the algorithm can save 11.66% and 30.67% of energy under two working conditions.

The Impact of Unconditional Priority for Escorted Vehicles in Traffic Networks on Sustainable Urban Mobility

“…An alternative towards the minimization of fuel consumption and exhaust gas emission involves the optimized routing of individual vehicles within urban traffic networks and the implementation of adaptive signal control at signalized intersections. These interventions have a direct impact on the frequency of stopand-go actions and culminate in reduced average delays at signalized intersections [12][13][14]. Simulation software serves as a common and inevitable tool for assessing diverse approaches in traffic control and vehicle movement optimization within networks.…”

“…Simulation software serves as a common and inevitable tool for assessing diverse approaches in traffic control and vehicle movement optimization within networks. Several studies have delineated the correlation between average travel times, fuel consumption, and simulation-based optimization techniques [14,15]. The advancements were made with q-learning algorithms, which presented improvements in CO 2 reduction and a reduction in the number of vehicles in queue lengths [16][17][18].…”