Radio Resource Management and Path Planning in Intelligent Transportation Systems via Reinforcement Learning for Environmental Sustainability

TL;DR

The paper addresses the problem of jointly optimizing radio resource management and path planning in CV-enabled urban networks to minimize the age of information (AoI) and improve routing accuracy. It introduces a multi-agent reinforcement learning framework based on MADDPG with TD3 enhancements, where each CV selects sub-channel access and transmit power while AoI feeds back into capacity estimation used by the path-planning module. Key contributions include a formal AoI-minimization objective, an AoI-aware capacity-update model, a dual-critic MADDPG design with global and local rewards, and simulation results showing AoI maintained around 5–10 ms and improvements in travel time and V/C across urban scenarios. The approach offers practical impact for reliable, timely V2I information in dense urban ITS, enabling more efficient routing under dynamic conditions.

Abstract

Efficient and dynamic path planning has become an important topic for urban areas with larger density of connected vehicles (CV) which results in reduction of travel time and directly contributes to environmental sustainability through reducing energy consumption. CVs exploit the cellular wireless vehicle-to-everything (C-V2X) communication technology to disseminate the vehicle-to-infrastructure (V2I) messages to the Base-station (BS) to improve situation awareness on urban roads. In this paper, we investigate radio resource management (RRM) in such a framework to minimize the age of information (AoI) so as to enhance path planning results. We use the fact that V2I messages with lower AoI value result in less error in estimating the road capacity and more accurate path planning. Through simulations, we compare road travel times and volume over capacity (V/C) against different levels of AoI and demonstrate the promising performance of the proposed framework.

Figures (5)

• Figure 1: Radio resource management system model
• Figure 2: Average V/C with different value of $\Delta m$
• Figure 3: Average roads travel times with different value of $\Delta m$
• Figure 4: Average reward over learning episodes.
• Figure 5: Average AoI over learning episodes.