SenseRAG: Constructing Environmental Knowledge Bases with Proactive Querying for LLM-Based Autonomous Driving
It addresses the critical need for enhanced safety and adaptability in autonomous driving systems, representing a novel application rather than an incremental improvement.
This study tackles the problem of situational awareness in autonomous driving by integrating multimodal sensor data into an LLM-readable knowledge base with proactive RAG and chain-of-thought prompting, achieving significant improvements in perception and prediction performance on real-world V2X datasets.
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.