Modern robots require accurate forecasts to make optimal decisions in the real world. For example, self-driving cars need an accurate forecast of other agents' future actions to plan safe trajectories. Current methods rely heavily on historical time series to accurately predict the future. However, relying entirely on the observed history is problematic since it could be corrupted by noise, have outliers, or not completely represent all possible outcomes. To solve this problem, we propose a novel framework for generating robust forecasts for robotic control. In order to model real-world factors affecting future forecasts, we introduce the notion of an adversary, which perturbs observed historical time series to increase a robot's ultimate control cost. Specifically, we model this interaction as a zero-sum two-player game between a robot's forecaster and this hypothetical adversary. We show that our proposed game may be solved to a local Nash equilibrium using gradient-based optimization techniques. Furthermore, we show that a forecaster trained with our method performs 30.14% better on out-of-distribution real-world lane change data than baselines.

翻译：现代机器人需要准确的预测以在现实世界中做出最优决策。例如，自动驾驶车辆需要精确预测其他智能体未来的行为，才能规划安全的轨迹。当前方法高度依赖历史时间序列来准确预测未来。然而，完全依赖观测到的历史数据存在隐患，因为数据可能被噪声污染、包含异常值，或无法完全代表所有可能的结果。为解决这一问题，我们提出了一种用于生成机器人控制鲁棒预测的新框架。为建模影响未来预测的现实世界因素，我们引入了“对抗者”的概念——该对抗者会扰动观测到的历史时间序列，以增加机器人最终的控制成本。具体而言，我们将这一交互建模为机器人预测器与假设对抗者之间的零和双人博弈。我们证明，所提出的博弈可通过基于梯度的优化技术求解至局部纳什均衡。此外，实验表明，经我们方法训练的预测器在真实场景的换道数据上的分布外性能比基线方法提升30.14%。