arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.19620cs.ROcs.AIcs.CV
收藏

大型轨迹模型是可扩展的运动预测器与规划器

Large Trajectory Models are Scalable Motion Predictors and Planners

Shanghai Qi Zhi Institute(上海期智研究院);Fudan University(复旦大学);Pegasus Tech(飞马科技);Tsinghua University(清华大学);Shanghai Jiaotong University(上海交通大学)

Qiao Sun, Shiduo Zhang, Danjiao Ma, Jingzhe Shi, Derun Li, Simian Luo, Yu Wang, Ningyi Xu, Guangzhi Cao, Hang Zhao

AI总结:

本文提出 State Transformer(STR),将运动预测与规划统一为序列建模任务,并证明大型轨迹模型遵循扩展定律,可在分布外场景中实现合理预测和长期规划推理。

摘要:

运动预测和规划是自动驾驶中的关键任务,近期研究工作已转向基于机器学习的方法。其挑战包括理解多样的道路拓扑、在较长时间范围内推理交通动态、解释异构行为,以及在大型连续状态空间中生成策略。受大型语言模型通过模型扩展解决类似复杂性的成功启发,我们提出了一种可扩展的轨迹模型,称为 State Transformer(STR)。STR 将观测、状态和动作组织为一个统一的序列建模任务,从而重新表述运动预测和运动规划问题。我们的方法将轨迹生成问题与其他序列建模问题统一起来,能够借助语言建模等邻近领域的突破实现快速迭代。值得注意的是,实验结果表明,诸如 STR 之类的大型轨迹模型(LTM)遵循扩展定律,表现出出色的适应性和学习效率。定性结果进一步证明,LTM 能够在与训练数据分布显著不同的场景中作出合理预测。LTM 还能学会为长期规划进行复杂推理,而无需显式的损失设计或昂贵的高层标注。

英文摘要:

Motion prediction and planning are vital tasks in autonomous driving, and recent efforts have shifted to machine learning-based approaches. The challenges include understanding diverse road topologies, reasoning traffic dynamics over a long time horizon, interpreting heterogeneous behaviors, and generating policies in a large continuous state space. Inspired by the success of large language models in addressing similar complexities through model scaling, we introduce a scalable trajectory model called State Transformer (STR). STR reformulates the motion prediction and motion planning problems by arranging observations, states, and actions into one unified sequence modeling task. Our approach unites trajectory generation problems with other sequence modeling problems, powering rapid iterations with breakthroughs in neighbor domains such as language modeling. Remarkably, experimental results reveal that large trajectory models (LTMs), such as STR, adhere to the scaling laws by presenting outstanding adaptability and learning efficiency. Qualitative results further demonstrate that LTMs are capable of making plausible predictions in scenarios that diverge significantly from the training data distribution. LTMs also learn to make complex reasonings for long-term planning, without explicit loss designs or costly high-level annotations.

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。

↑