# Multi-Agent Sensor Fusion Methodology Using Deep Reinforcement Learning: Vehicle Sensors to Localization

## TL;DR

This paper introduces a new method using AI to improve vehicle perception by combining sensor data for better localization in complex environments.

## Contribution

The novel contribution is a perception-focused deep reinforcement learning framework called CarAware for sensor fusion in autonomous vehicles.

## Key findings

- The CarAware framework effectively fuses multiple sensor data types for vehicle localization.
- The PPO algorithm was successfully used to train and evaluate the proposed methodology.
- The approach shows potential for improving obstacle detection in complex urban settings.

## Abstract

Despite recent major advances in autonomous driving, several challenges remain. Even with modern advanced sensors and processing systems, vehicles are still unable to detect all possible obstacles present in complex urban settings and under diverse environmental conditions. Consequently, numerous studies have investigated artificial intelligence methods to improve vehicle perception capabilities. This paper presents a new methodology using a framework named CarAware, which fuses multiple types of sensor data to predict vehicle positions using Deep Reinforcement Learning (DRL). Unlike traditional DRL applications centered on control, this approach focuses on perception. As a case study, the PPO algorithm was used to train and evaluate the effectiveness of this methodology.