TDM: Trustworthy Decision-Making via Interpretability Enhancement

TL;DR

This paper introduces TDM, a framework that combines symbolic planning with interpretability strategies to enhance trustworthiness in human-robot decision-making, providing formal evaluation and improved transparency.

Contribution

It presents a novel TDM framework that integrates symbolic planning with interpretability, enabling trust evaluation and subtask-level transparency in decision-making.

Findings

Trust-score-based planning improves trustworthiness.

Subtask interpretability enhances user understanding.

Framework converges to optimal symbolic plans.

Abstract

Human-robot interactive decision-making is increasingly becoming ubiquitous, and trust is an influential factor in determining the reliance on autonomy. However, it is not reasonable to trust systems that are beyond our comprehension, and typical machine learning and data-driven decision-making are black-box paradigms that impede interpretability. Therefore, it is critical to establish computational trustworthy decision-making mechanisms enhanced by interpretability-aware strategies. To this end, we propose a Trustworthy Decision-Making (TDM) framework, which integrates symbolic planning into sequential decision-making. The framework learns interpretable subtasks that result in a complex, higher-level composite task that can be formally evaluated using the proposed trust metric. TDM enables the subtask-level interpretability by design and converges to an optimal symbolic plan from the learned subtasks. Moreover, a TDM-based algorithm is introduced to demonstrate the unification of symbolic planning with other sequential-decision making algorithms, reaping the benefits of both. Experimental results validate the effectiveness of trust-score-based planning while improving the interpretability of subtasks.