Predicting the future motion of road agents is a critical task in an autonomous driving pipeline. In this work, we address the problem of generating a set of scene-level, or joint, future trajectory predictions in multi-agent driving scenarios. To this end, we propose FJMP, a Factorized Joint Motion Prediction framework for multi-agent interactive driving scenarios. FJMP models the future scene interaction dynamics as a sparse directed interaction graph, where edges denote explicit interactions between agents. We then prune the graph into a directed acyclic graph (DAG) and decompose the joint prediction task into a sequence of marginal and conditional predictions according to the partial ordering of the DAG, where joint future trajectories are decoded using a directed acyclic graph neural network (DAGNN). We conduct experiments on the INTERACTION and Argoverse 2 datasets and demonstrate that FJMP produces more accurate and scene-consistent joint trajectory predictions than non-factorized approaches, especially on the most interactive and kinematically interesting agents. FJMP ranks 1st on the multi-agent test leaderboard of the INTERACTION dataset.
翻译:预测道路上其他行驶物的未来运动轨迹对于自动驾驶至关重要。本文解决多智能体交互驾驶场景下生成一组联合的未来轨迹预测的问题。为此,我们提出了 FJMP,一种面向多智能体交互驾驶场景的因式分解联合运动预测框架。FJMP将未来场景交互动力学建模为一个稀疏的有向交互图,其中边表示智能体之间的显式交互。然后将图剪枝为一个有向无环图(DAG),并根据DAG的部分顺序将联合预测任务分解为一系列边际和条件预测,使用有向无环图神经网络(DAGNN)解码联合未来轨迹。我们在INTERACTION和Argoverse 2数据集上进行实验,并证明 FJMP 比非因式分解方法更准确和更符合场景,特别是对于最具交互性和运动性的智能体。FJMP 在 INTERACTION 数据集的多智能体测试排行榜上排名第一。