SenseRAG: Constructing Environmental Knowledge Bases with Proactive Querying for LLM-Based Autonomous Driving

TL;DR

SenseRAG introduces a novel framework that integrates real-time sensor data into LLM-readable knowledge bases for autonomous driving, enhancing situational awareness and decision-making through proactive retrieval and reasoning.

Contribution

It presents a new approach combining multimodal data integration with proactive retrieval-augmented generation for improved autonomous driving perception.

Findings

Significant performance improvements in perception and prediction tasks

Enhanced safety and adaptability in autonomous driving scenarios

Effective real-time understanding using LLMs with multimodal data

Abstract

This study addresses the critical need for enhanced situational awareness in autonomous driving (AD) by leveraging the contextual reasoning capabilities of large language models (LLMs). Unlike traditional perception systems that rely on rigid, label-based annotations, it integrates real-time, multimodal sensor data into a unified, LLMs-readable knowledge base, enabling LLMs to dynamically understand and respond to complex driving environments. To overcome the inherent latency and modality limitations of LLMs, a proactive Retrieval-Augmented Generation (RAG) is designed for AD, combined with a chain-of-thought prompting mechanism, ensuring rapid and context-rich understanding. Experimental results using real-world Vehicle-to-everything (V2X) datasets demonstrate significant improvements in perception and prediction performance, highlighting the potential of this framework to enhance safety, adaptability, and decision-making in next-generation AD systems.