Chameleon: Fast-slow Neuro-symbolic Lane Topology Extraction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912268175802368 |
|---|---|
| author | Zhang, Zongzheng Li, Xinrun Zou, Sizhe Chi, Guoxuan Li, Siqi Qiu, Xuchong Wang, Guoliang Zheng, Guantian Wang, Leichen Zhao, Hang Zhao, Hao |
| author_facet | Zhang, Zongzheng Li, Xinrun Zou, Sizhe Chi, Guoxuan Li, Siqi Qiu, Xuchong Wang, Guoliang Zheng, Guantian Wang, Leichen Zhao, Hang Zhao, Hao |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_07485 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Chameleon: Fast-slow Neuro-symbolic Lane Topology Extraction Zhang, Zongzheng Li, Xinrun Zou, Sizhe Chi, Guoxuan Li, Siqi Qiu, Xuchong Wang, Guoliang Zheng, Guantian Wang, Leichen Zhao, Hang Zhao, Hao Computer Vision and Pattern Recognition 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 |
| title | Chameleon: Fast-slow Neuro-symbolic Lane Topology Extraction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.07485 |