用自回归模型预测驾驶行为，规模扩大后表现显著提升
DriveGPT: Scaling Autoregressive Behavior Models for Driving
- 基于Transformer建模驾驶为序列决策任务，自回归预测未来状态
- 模型参数和数据量扩大多个数量级，性能随规模提升明显
- 适合研究自动驾驶行为建模与大规模数据训练的从业者
我们提出DriveGPT，一种可扩展的自动驾驶行为模型。将驾驶建模为序列决策任务，采用Transformer模型以自回归方式预测未来交通参与者状态作为令牌。通过将模型参数和训练数据量扩大多个数量级，探索了数据集规模、模型参数和计算量之间的缩放特性。在规划任务中评估不同规模下的表现，结合定量指标与定性案例，包括复杂真实场景中的闭环驾驶。在独立预测任务中，DriveGPT超越现有最优基线，且通过大规模数据预训练进一步提升性能，验证了数据规模带来的优势。
原文摘要 · Abstract (English)
We present DriveGPT, a scalable behavior model for autonomous driving. We model driving as a sequential decision-making task, and learn a transformer model to predict future agent states as tokens in an autoregressive fashion. We scale up our model parameters and training data by multiple orders of magnitude, enabling us to explore the scaling properties in terms of dataset size, model parameters, and compute. We evaluate DriveGPT across different scales in a planning task, through both quantitative metrics and qualitative examples, including closed-loop driving in complex real-world scenarios. In a separate prediction task, DriveGPT outperforms state-of-the-art baselines and exhibits improved performance by pretraining on a large-scale dataset, further validating the benefits of data scaling.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。