# Chameleon: Fast-slow Neuro-symbolic Lane Topology Extraction

Source: [Chameleon: Fast-slow Neuro-symbolic Lane Topology Extraction](<https://www.sota2.com/research/paper/68fa77571e209131cea72831>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:15:51.701Z

Authors: Zongzheng Zhang, Xinrun Li, Sizhe Zou, Guoxuan Chi, Siqi Li, Xuchong Qiu, Guoliang Wang, Guantian Zheng, Leichen Wang, Hang Zhao, Hao Zhao

Published: 2025-03-10T16:02:35.000Z

## Abstract

Lane topology extraction involves detecting lanes and traffic elements and determining their relationships, a key perception task for mapless autonomous driving. This task requires complex reasoning, such as determining whether it is possible to turn left into a specific lane. To address this challenge, we introduce neuro-symbolic methods powered by vision-language foundation models (VLMs). Existing approaches have notable limitations: (1) Dense visual prompting with VLMs can achieve strong performance but is costly in terms of both financial resources and carbon footprint, making it impractical for robotics applications. (2) Neuro-symbolic reasoning methods for 3D scene understanding fail to integrate visual inputs when synthesizing programs, making them ineffective in handling complex corner cases. To this end, we propose a fast-slow neuro-symbolic lane topology extraction algorithm, named Chameleon, which alternates between a fast system that directly reasons over detected instances using synthesized programs and a slow system that utilizes a VLM with a chain-of-thought design to handle corner cases. Chameleon leverages the strengths of both approaches, providing an affordable solution while maintaining high performance. We evaluate the method on the OpenLane-V2 dataset, showing consistent improvements across various baseline detectors. Our code, data, and models are publicly available at https://github.com/XR-Lee/neural-symbolic

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Panoramic Visual Question Answering on PanoVQA (test)](<https://www.sota2.com/research/sota/panoramic-visual-question-answering-on-panovqa-test.md>): Panoramic Visual Question Answering; PanoVQA (test); Accuracy (N1): 9.87.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.07485>)

[PDF](<https://arxiv.org/pdf/2503.07485.pdf>)