Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Yifei, Greer, Ross
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.11124
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908406307094528
author Chen, Yifei
Greer, Ross
author_facet Chen, Yifei
Greer, Ross
contents Scenario mining from extensive autonomous driving datasets, such as Argoverse 2, is crucial for the development and validation of self-driving systems. The RefAV framework represents a promising approach by employing Large Language Models (LLMs) to translate natural-language queries into executable code for identifying relevant scenarios. However, this method faces challenges, including runtime errors stemming from LLM-generated code and inaccuracies in interpreting parameters for functions that describe complex multi-object spatial relationships. This technical report introduces two key enhancements to address these limitations: (1) a fault-tolerant iterative code-generation mechanism that refines code by re-prompting the LLM with error feedback, and (2) specialized prompt engineering that improves the LLM's comprehension and correct application of spatial-relationship functions. Experiments on the Argoverse 2 validation set with diverse LLMs-Qwen2.5-VL-7B, Gemini 2.5 Flash, and Gemini 2.5 Pro-show consistent gains across multiple metrics; most notably, the proposed system achieves a HOTA-Temporal score of 52.37 on the official test set using Gemini 2.5 Pro. These results underline the efficacy of the proposed techniques for reliable, high-precision scenario mining.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11124
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Technical Report for Argoverse2 Scenario Mining Challenges on Iterative Error Correction and Spatially-Aware Prompting
Chen, Yifei
Greer, Ross
Computer Vision and Pattern Recognition
Software Engineering
Scenario mining from extensive autonomous driving datasets, such as Argoverse 2, is crucial for the development and validation of self-driving systems. The RefAV framework represents a promising approach by employing Large Language Models (LLMs) to translate natural-language queries into executable code for identifying relevant scenarios. However, this method faces challenges, including runtime errors stemming from LLM-generated code and inaccuracies in interpreting parameters for functions that describe complex multi-object spatial relationships. This technical report introduces two key enhancements to address these limitations: (1) a fault-tolerant iterative code-generation mechanism that refines code by re-prompting the LLM with error feedback, and (2) specialized prompt engineering that improves the LLM's comprehension and correct application of spatial-relationship functions. Experiments on the Argoverse 2 validation set with diverse LLMs-Qwen2.5-VL-7B, Gemini 2.5 Flash, and Gemini 2.5 Pro-show consistent gains across multiple metrics; most notably, the proposed system achieves a HOTA-Temporal score of 52.37 on the official test set using Gemini 2.5 Pro. These results underline the efficacy of the proposed techniques for reliable, high-precision scenario mining.
title Technical Report for Argoverse2 Scenario Mining Challenges on Iterative Error Correction and Spatially-Aware Prompting
topic Computer Vision and Pattern Recognition
Software Engineering
url https://arxiv.org/abs/2506.11124