arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.18053cs.ROcs.AI
收藏

DualAD:用于自动驾驶推理的双层规划

DualAD: Dual-Layer Planning for Reasoning in Autonomous Driving

Technical University Munich(慕尼黑工业大学);Munich Institute of Robotics and Machine Intelligence (MIRMI)(慕尼黑机器人与机器智能研究所)

Dingrui Wang, Marc Kaufeld, Johannes Betz

AI总结:

本文提出双层自动驾驶框架 DualAD,由规则运动规划器与 LLM 文本推理层协同决策,并通过闭环实验验证其在危险场景中的性能提升。

摘要:

我们提出了一种新颖的自动驾驶框架 DualAD,旨在模仿人类在驾驶过程中的推理。DualAD 包含两层:底层是基于规则的运动规划器,用于处理只需极少推理的常规驾驶任务;上层则配备基于规则的文本编码器,将驾驶场景从绝对状态转换为文本描述。随后,该文本由大型语言模型(LLM)处理,以作出驾驶决策。当检测到潜在危险时,上层会干预底层的决策,在关键情境中模拟人类推理。闭环实验表明,使用零样本预训练模型的 DualAD 显著优于缺乏推理能力的基于规则的运动规划器。我们的实验还凸显了文本编码器的有效性,它显著增强了模型对场景的理解。此外,集成后的 DualAD 模型会随着更强大的 LLM 而提升,表明该框架具有进一步增强的潜力。代码和基准可在 github.com/TUM-AVS/DualAD 获取。

英文摘要:

We present a novel autonomous driving framework, DualAD, designed to imitate human reasoning during driving. DualAD comprises two layers: a rule-based motion planner at the bottom layer that handles routine driving tasks requiring minimal reasoning, and an upper layer featuring a rule-based text encoder that converts driving scenarios from absolute states into text description. This text is then processed by a large language model (LLM) to make driving decisions. The upper layer intervenes in the bottom layer's decisions when potential danger is detected, mimicking human reasoning in critical situations. Closed-loop experiments demonstrate that DualAD, using a zero-shot pre-trained model, significantly outperforms rule-based motion planners that lack reasoning abilities. Our experiments also highlight the effectiveness of the text encoder, which considerably enhances the model's scenario understanding. Additionally, the integrated DualAD model improves with stronger LLMs, indicating the framework's potential for further enhancement. Code and benchmarks are available at github.com/TUM-AVS/DualAD.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑