Understanding the Unforeseen via the Intentional Stance
This work addresses the challenge of interpreting unforeseen agent behaviors for applications in AI and robotics, but it appears incremental as it builds on existing concepts like analogy and intentional stance.
The paper tackles the problem of understanding novel behaviors of observed agents by proposing an architecture that uses Dennett's intentional stance and analogical reasoning to construct hypothetical rationales, with a demonstration in a gas station environment.
We present an architecture and system for understanding novel behaviors of an observed agent. The two main features of our approach are the adoption of Dennett's intentional stance and analogical reasoning as one of the main computational mechanisms for understanding unforeseen experiences. Our approach uses analogy with past experiences to construct hypothetical rationales that explain the behavior of an observed agent. Moreover, we view analogies as partial; thus multiple past experiences can be blended to analogically explain an unforeseen event, leading to greater inferential flexibility. We argue that this approach results in more meaningful explanations of observed behavior than approaches based on surface-level comparisons. A key advantage of behavior explanation over classification is the ability to i) take appropriate responses based on reasoning and ii) make non-trivial predictions that allow for the verification of the hypothesized explanation. We provide a simple use case to demonstrate novel experience understanding through analogy in a gas station environment.