PKRD-CoT structures multimodal LLM prompts into perception, knowledge, reasoning, and decision steps, and the authors report improved driving decision accuracy for GPT-4.0 and several other models.
In: 2019 IEEE Intelligent vehicles symposium (IV)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PKRD-CoT: A Unified Chain-of-thought Prompting for Multi-Modal Large Language Models in Autonomous Driving
PKRD-CoT structures multimodal LLM prompts into perception, knowledge, reasoning, and decision steps, and the authors report improved driving decision accuracy for GPT-4.0 and several other models.