# Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments

## TL;DR

This paper introduces a modular safe reinforcement learning approach with scene decomposition and belief updates for autonomous vehicle navigation in complex urban intersections, ensuring safety and robustness.

## Contribution

It presents a novel safe RL algorithm with a model-checker, belief update, and scene decomposition to improve urban navigation safety and scalability.

## Key findings

- Outperforms rule-based methods in complex intersection scenarios
- Demonstrates robustness to perception errors and occlusions
- Scales effectively to environments with multiple traffic participants

## Abstract

Navigating urban environments represents a complex task for automated vehicles. They must reach their goal safely and efficiently while considering a multitude of traffic participants. We propose a modular decision making algorithm to autonomously navigate intersections, addressing challenges of existing rule-based and reinforcement learning (RL) approaches. We first present a safe RL algorithm relying on a model-checker to ensure safety guarantees. To make the decision strategy robust to perception errors and occlusions, we introduce a belief update technique using a learning based approach. Finally, we use a scene decomposition approach to scale our algorithm to environments with multiple traffic participants. We empirically demonstrate that our algorithm outperforms rule-based methods and reinforcement learning techniques on a complex intersection scenario.