Robust Forecasting for Robotic Control: A Game-Theoretic Approach

2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA(2023)

引用 0|浏览13
暂无评分
摘要
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.
更多
查看译文
关键词
accurate forecast,agents,forecaster,future forecasts,game-theoretic approach,gradient-based optimization techniques,historical time series,modern robots,observed history,optimal decisions,out-of-distribution real-world lane change data,real-world factors,robot,robotic control,robust forecasting,robust forecasts,safe trajectories,self-driving cars,zero-sum two-player game
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要