U-Parking: Distributed UWB-Assisted Autonomous Parking System with Robust Localization and Intelligent Planning

TL;DR

U-Parking is an autonomous parking system that combines UWB localization, LLM-assisted planning, and trajectory tracking to enable reliable indoor parking, demonstrated on real vehicles.

Contribution

It introduces a novel distributed UWB-assisted parking system integrating LLMs for planning and robust localization for indoor environments.

Findings

Successful real-vehicle demonstrations in challenging indoor settings

Effective fusion localization and trajectory tracking achieved

Enhanced reliability of autonomous parking in complex environments

Abstract

This demonstration presents U-Parking, a distributed Ultra-Wideband (UWB)-assisted autonomous parking system. By integrating Large Language Models (LLMs)-assisted planning with robust fusion localization and trajectory tracking, it enables reliable automated parking in challenging indoor environments, as validated through real-vehicle demonstrations.