Can I read KoMA: Knowledge-driven Multi-agent Framework for Autonomous Driving with Large Language Models on EtoBox?

KoMA: Knowledge-driven Multi-agent Framework for Autonomous Driving with Large Language Models by Jiang, Kemou; Cai, Xuan; Cui, Zhiyong; Li, Aoyong; Ren, Yilong; Yu, Haiyang; Yang, Hao; Fu, Daocheng; Wen, Licheng; Cai, Pinlong is a scholarly article available to read on EtoBox.

What is KoMA: Knowledge-driven Multi-agent Framework for Autonomous Driving with Large Language Models about?

Large language models (LLMs) as autonomous agents offer a novel avenue for tackling real-world challenges through a knowledge-driven manner. These LLM-enhanced methodologies excel in generalization and interpretability. However, the complexity of driving tasks often necessitates the collaboration of multiple, heterogeneous agents, underscoring the need for such LLM-driven agents to engage in cooperative knowledge sharing and cognitive synergy. Despite the promise of LLMs, current applications predominantly center around single agent scenarios. To broaden the horizons of knowledge-driven strategies and bolster the generalization capabilities of autonomous agents, we propose the KoMA framework consisting of multi-agent interaction, multi-step planning, shared-memory, and ranking-based reflection modules to enhance multi-agents' decision-making in complex driving scenarios. Based on the framework's generated text descriptions of driving scenarios, the multi-agent interaction module enables LLM agents to analyze and infer the intentions of surrounding vehicles, akin to human cognition. The multi-step planning module enables LLM agents to analyze and obtain final action decisions layer

Author

Jiang, Kemou; Cai, Xuan; Cui, Zhiyong; Li, Aoyong; Ren, Yilong; Yu, Haiyang; Yang, Hao; Fu, Daocheng; Wen, Licheng; Cai, Pinlong

Published

2024

Language

EN