Interactions between road agents present a significant challenge in trajectory prediction, especially in cases involving multiple agents. Because existing diversity-aware predictors do not account for the interactive nature of multi-agent predictions, they may miss these important interaction outcomes. In this paper, we propose GAME-UP, a framework for trajectory prediction that leverages game-theoretic inverse reinforcement learning to improve coverage of multi-modal predictions. We use a training-time game-theoretic numerical analysis as an auxiliary loss resulting in improved coverage and accuracy without presuming a taxonomy of actions for the agents. We demonstrate our approach on the interactive subset of Waymo Open Motion Dataset, including three subsets involving scenarios with high interaction complexity. Experiment results show that our predictor produces accurate predictions while covering twice as many possible interactions versus a baseline model.

翻译：道路智能体之间的交互对轨迹预测构成了重大挑战，尤其在涉及多个智能体的场景中。由于现有的多样性感知预测器未考虑多智能体预测的交互特性，它们可能遗漏这些重要的交互结果。本文提出GAME-UP框架，该框架利用博弈论逆强化学习提升对多模态预测结果的覆盖能力。我们采用训练过程中的博弈论数值分析作为辅助损失函数，在不预设智能体动作类别的前提下，提升了预测覆盖率和准确性。我们在Waymo开放运动数据集的交互子集（包含三个高交互复杂度场景子集）上验证了该方法。实验结果表明，与基线模型相比，我们的预测器在保持精确预测的同时，对可能交互行为的覆盖范围提升了两倍。