Human-like Semantic Navigation for Autonomous Driving using Knowledge Representation and Large Language Models

2025-05-22

AI Summary

Autonomous semantic navigation in dynamic urban environments suffers from over-reliance on pre-built maps, leading to poor adaptability to sudden road changes and map incompleteness. Method: This paper proposes an LLM-driven approach for automatic generation of non-monotonic logic rules, translating natural-language navigation instructions end-to-end into Answer Set Programming (ASP) rules—enabling map-free, interpretable, and human-like decision-making. Contribution/Results: We introduce the first paradigm mapping informal natural-language instructions to formal logical reasoning rules via large language models, integrating knowledge representation with semantic reasoning. Experiments demonstrate that the generated ASP rules accurately encode real-world driving logic, significantly improving navigation robustness under map absence and temporary detour scenarios. Crucially, all decisions are fully traceable and formally verifiable, ensuring transparency and reliability in autonomous navigation.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Knowledge Representation and Reasoning: Logic Programming
• Natural Language Processing: Safety and Robustness

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Achieving full automation in self-driving vehicles remains a challenge, especially in dynamic urban environments where navigation requires real-time adaptability. Existing systems struggle to handle navigation plans when faced with unpredictable changes in road layouts, spontaneous detours, or missing map data, due to their heavy reliance on predefined cartographic information. In this work, we explore the use of Large Language Models to generate Answer Set Programming rules by translating informal navigation instructions into structured, logic-based reasoning. ASP provides non-monotonic reasoning, allowing autonomous vehicles to adapt to evolving scenarios without relying on predefined maps. We present an experimental evaluation in which LLMs generate ASP constraints that encode real-world urban driving logic into a formal knowledge representation. By automating the translation of informal navigation instructions into logical rules, our method improves adaptability and explainability in autonomous navigation. Results show that LLM-driven ASP rule generation supports semantic-based decision-making, offering an explainable framework for dynamic navigation planning that aligns closely with how humans communicate navigational intent.

Problem

• Autonomous vehicles struggle with dynamic urban navigation adaptability
• Existing systems rely heavily on predefined maps, limiting flexibility
• Translating human instructions into logical rules for explainable navigation

Innovation

• LLMs generate ASP rules for navigation
• ASP enables non-monotonic reasoning without maps
• Automated translation improves adaptability and explainability