概念から実際の原因へ：ロボット基盤モデルにおける概念-故障ギャップの解消に向けて
From Concepts to Actual Causes: Toward Closing the Concept-Malfunction Gap in Robot Foundation Models
ロボット基盤モデルの事故解析において、学習された概念の解読だけでは特定故障の実際の原因を特定できない「概念-故障ギャップ」を実際的因果性の枠組みで分析し、現行の機械論的解釈手法の限界と4つの研究課題を示したポジションペーパー。
著者: Gihyuk Ko
分類: cs.RO, cs.AI
原文アブストラクト
Post-incident analysis of a robot foundation model poses a singular causal question: which internal components caused this failure, and to what degree? Mechanistic interpretability (MI), however, establishes general causal claims by decoding the concepts a policy has learned, yet knowing which concepts are encoded is insufficient for identifying the actual cause of a specific incident. In this position paper, we analyze this concept-malfunction gap by posing fault isolation in the framework of actual causality. Specifically, we formalize a fault-isolation query as a tuple of intervened internal components, counterfactual values, contingencies, and read-outs, and lay out conditions for it to be well-specified. Through this lens, we identify shortcomings of current MI approaches: they assume fixed contingencies and read out only immediate effects, letting backups obscure actual causes. We demonstrate on a toy example that these shortcomings can lead to conflicting verdicts. Lastly, based on the well-specification conditions, we outline four open research tasks toward closing the gap.