U-Parking: Distributed UWB-Assisted Autonomous Parking System with Robust Localization and Intelligent Planning
🤖 AI Summary
This work proposes a novel autonomous parking system to address the insufficient reliability of self-driving vehicles in complex indoor environments. The system integrates ultra-wideband (UWB)-based distributed high-precision localization, multi-sensor fusion positioning, and large language model (LLM)-assisted decision-making and planning. Notably, this is the first study to incorporate an LLM into the parking decision layer, enabling semantic reasoning and high-level command generation. Combined with UWB for centimeter-level indoor positioning accuracy, the approach achieves closed-loop validation through trajectory tracking control. Real-vehicle experiments demonstrate that the proposed system exhibits high robustness and consistently reliable parking performance even in challenging indoor scenarios.
Application Category
📝 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.
Problem
Research questions and friction points this paper is trying to address.
autonomous parking
indoor environments
robust localization
UWB-assisted
automated parking
Innovation
Methods, ideas, or system contributions that make the work stand out.
UWB-assisted localization
Large Language Models (LLMs)
autonomous parking
fusion localization
intelligent planning
🔎 Similar Papers
No similar papers found.
