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：现代机器人需要精确预测以在现实世界中做出最优决策。例如，自动驾驶汽车需要准确预测其他智能体未来动作，以规划安全轨迹。现有方法高度依赖历史时间序列来精准预测未来。然而，完全依赖观测到的历史数据存在隐患，因为这些数据可能被噪声污染、包含异常值，或未能完全代表所有可能的结果。为解决这一问题，我们提出了一种生成鲁棒性机器人控制预测的新框架。为建模影响未来预测的现实因素，我们引入了“对抗体”概念——该对抗体会扰动观测到的历史时间序列，从而增加机器人的最终控制成本。具体而言，我们将此交互建模为机器人预测器与假设对抗体之间的零和双人博弈。研究表明，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，采用我们方法训练的预测器在真实世界车道变换数据的分布外测试中，性能较基线方法提升30.14%。