# Belief State Planning for Autonomously Navigating Urban Intersections

## TL;DR

This paper presents a POMDP-based approach with Monte Carlo sampling for autonomous vehicle navigation at urban intersections, improving safety and efficiency over heuristic methods in simulation.

## Contribution

It introduces a novel POMDP framework combined with Monte Carlo sampling for autonomous intersection navigation, addressing uncertainty and driver behavior.

## Key findings

- The proposed method outperforms heuristic strategies in simulation.
- The approach improves safety metrics during intersection navigation.
- Efficiency metrics are also enhanced with the new policy.

## Abstract

Urban intersections represent a complex environment for autonomous vehicles with many sources of uncertainty. The vehicle must plan in a stochastic environment with potentially rapid changes in driver behavior. Providing an efficient strategy to navigate through urban intersections is a difficult task. This paper frames the problem of navigating unsignalized intersections as a partially observable Markov decision process (POMDP) and solves it using a Monte Carlo sampling method. Empirical results in simulation show that the resulting policy outperforms a threshold-based heuristic strategy on several relevant metrics that measure both safety and efficiency.