テイント解析と強化学習による自律ロボットソフトウェアの修復
Using Taint Analysis and Reinforcement Learning (TARL) to Repair Autonomous Robot Software
ROSベースの自律ロボットソフトウェアに対し、テイント解析でデータフローを抽出し強化学習で設計者の意図する効用を推定、オンラインでの性能違反を検知して自動修復する手法を提案した。
著者: D. M. Lyons, S. Zahra
分類: cs.RO, cs.SE
原文アブストラクト
It is important to be able to establish formal performance bounds for autonomous systems. However, formal verification techniques require a model of the environment in which the system operates; a challenge for autonomous systems, especially those expected to operate over longer timescales. This paper describes work in progress to automate the monitor and repair of ROS-based autonomous robot software written for an a-priori partially known and possibly incorrect environment model. A taint analysis method is used to automatically extract the data-flow sequence from input topic to publish topic, and instrument that code. A unique reinforcement learning approximation of MDP utility is calculated, an empirical and non-invasive characterization of the inherent objectives of the software designers. By comparing off-line (a-priori) utility with on-line (deployed system) utility, we show, using a small but real ROS example, that it's possible to monitor a performance criterion and relate violations of the criterion to parts of the software. The software is then patched using automated software repair techniques and evaluated against the original off-line utility.
