知覚システムの安全要件を効率的に決定する手法
Efficient Determination of Safety Requirements for Perception Systems
閉ループ系のブラックボックスシミュレータを用い、知覚システムが満たすべき安全な性能特性の集合を効率的に推定する「スムージングバンディット」を提案し、視覚ベースの航空機衝突回避問題で有効性を示した。
著者: Sydney M. Katz, Anthony L. Corso, Esen Yel, Mykel J. Kochenderfer
分類: cs.RO, cs.AI
原文アブストラクト
Perception systems operate as a subcomponent of the general autonomy stack, and perception system designers often need to optimize performance characteristics while maintaining safety with respect to the overall closed-loop system. For this reason, it is useful to distill high-level safety requirements into component-level requirements on the perception system. In this work, we focus on efficiently determining sets of safe perception system performance characteristics given a black-box simulator of the fully-integrated, closed-loop system. We combine the advantages of common black-box estimation techniques such as Gaussian processes and threshold bandits to develop a new estimation method, which we call smoothing bandits. We demonstrate our method on a vision-based aircraft collision avoidance problem and show improvements in terms of both accuracy and efficiency over the Gaussian process and threshold bandit baselines.
