# Traffic Management of Autonomous Vehicles using Policy Based Deep Reinforcement Learning and Intelligent Routing

arXiv: https://arxiv.org/abs/2206.14608 · HTML: https://mlsanity.com/paper/2206.14608/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Cooperative and V2X driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 5 of its 38 references that are in the map.
- First posted on arXiv 28 Jun 2022.

## Placed in

- End-to-end autonomous driving / [Cooperative and V2X driving](https://mlsanity.com/driving/cooperative-and-v2x-driving/)

## Builds on (most cited first, 5 of 5)

- [A Brief Survey of Deep Reinforcement Learning](https://mlsanity.com/paper/1708.05866/) (2017)
- [Traffic Light Control Using Deep Policy-Gradient and Value-Function Based Reinforcement Learning](https://mlsanity.com/paper/1704.08883/) (2017)
- [Using a Deep Reinforcement Learning Agent for Traffic Signal Control](https://mlsanity.com/paper/1611.01142/) (2016)
- [An Efficient Deep Reinforcement Learning Model for Urban Traffic Control](https://mlsanity.com/paper/1808.01876/) (2018)
- [Assessment of Reward Functions for Reinforcement Learning Traffic Signal Control under Real-World Limitations](https://mlsanity.com/paper/2008.11634/) (2020)

## Abstract (arXiv)

Deep Reinforcement Learning (DRL) uses diverse, unstructured data and makes RL capable of learning complex policies in high dimensional environments. Intelligent Transportation System (ITS) based on Autonomous Vehicles (AVs) offers an excellent playground for policy-based DRL. Deep learning architectures solve computational challenges of traditional algorithms while helping in real-world adoption and deployment of AVs. One of the main challenges in AVs implementation is that it can worsen traffic congestion on roads if not reliably and efficiently managed. Considering each vehicle's holistic effect and using efficient and reliable techniques could genuinely help optimise traffic flow management and congestion reduction. For this purpose, we proposed a intelligent traffic control system that deals with complex traffic congestion scenarios at intersections and behind the intersections. We proposed a DRL-based signal control system that dynamically adjusts traffic signals according to the current congestion situation on intersections. To deal with the congestion on roads behind the intersection, we used re-routing technique to load balance the vehicles on road networks. To achieve the actual benefits of the proposed approach, we break down the data silos and use all the data coming from sensors, detectors, vehicles and roads in combination to achieve sustainable results. We used SUMO micro-simulator for our simulations. The significance of our proposed approach is manifested from the results.