Deep RL-Based Smart Signaling Using Space-Time Vehicular Features Under C-V2X Scenario

As of recent, the majority of developing countries have faced traffic congestion issues. As a result, vehicular communication technologies such as DSRC and Cellular-V2X are standardized by the 3GPP to support the transportation community. The C-V2X standard proposed in 3GPP Re114 provides high data transmission facilities for V2V and V2I communication. In this paper, we attempt to solve the traffic congestion problem by considering the V2I communication facility as per the C-V2X standard. We propose an online learning strategy based on Deep Reinforcement Learning for smart signaling to avoid traffic congestion at the intersections. These are the key aspects to address the congestion issue. We conduct extensive near-real-time simulations in PTV VISSIM considering the Swastik Cross Road intersection at Ahmedabad, Gujarat, India, imported via OpenStreetMap. With the proposed smart signaling strategy, we found significant improvement in vehicles' average travel time and average space occupancy compared to existing traffic signaling methods. Uplifting this research and implementing such real-time strategies will significantly impact the current transportation system.