Accelerating Structured Chain-of-Thought in Autonomous Vehicles
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910009824116736 |
|---|---|
| author | Gu, Yi Wang, Yan Chen, Yuxiao You, Yurong Luo, Wenjie Wang, Yue Ding, Wenhao Li, Boyi Yang, Heng Ivanovic, Boris Pavone, Marco |
| author_facet | Gu, Yi Wang, Yan Chen, Yuxiao You, Yurong Luo, Wenjie Wang, Yue Ding, Wenhao Li, Boyi Yang, Heng Ivanovic, Boris Pavone, Marco |
| contents | Chain-of-Thought (CoT) reasoning enhances the decision-making capabilities of vision-language-action models in autonomous driving, but its autoregressive nature introduces significant inference latency, making it impractical for real-time applications. To address this, we introduce FastDriveCoT, a novel parallel decoding method that accelerates template-structured CoT. Our approach decomposes the reasoning process into a dependency graph of distinct sub-tasks, such as identifying critical objects and summarizing traffic rules, some of which can be generated in parallel. By generating multiple independent reasoning steps concurrently within a single forward pass, we significantly reduce the number of sequential computations. Experiments demonstrate a 3-4$\times$ speedup in CoT generation and a substantial reduction in end-to-end latency across various model architectures, all while preserving the original downstream task improvements brought by incorporating CoT reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02864 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Accelerating Structured Chain-of-Thought in Autonomous Vehicles Gu, Yi Wang, Yan Chen, Yuxiao You, Yurong Luo, Wenjie Wang, Yue Ding, Wenhao Li, Boyi Yang, Heng Ivanovic, Boris Pavone, Marco Robotics Chain-of-Thought (CoT) reasoning enhances the decision-making capabilities of vision-language-action models in autonomous driving, but its autoregressive nature introduces significant inference latency, making it impractical for real-time applications. To address this, we introduce FastDriveCoT, a novel parallel decoding method that accelerates template-structured CoT. Our approach decomposes the reasoning process into a dependency graph of distinct sub-tasks, such as identifying critical objects and summarizing traffic rules, some of which can be generated in parallel. By generating multiple independent reasoning steps concurrently within a single forward pass, we significantly reduce the number of sequential computations. Experiments demonstrate a 3-4$\times$ speedup in CoT generation and a substantial reduction in end-to-end latency across various model architectures, all while preserving the original downstream task improvements brought by incorporating CoT reasoning. |
| title | Accelerating Structured Chain-of-Thought in Autonomous Vehicles |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.02864 |