BaTCAVe: Trustworthy Explanations for Robot Behaviors

TL;DR

This paper introduces BaTCAVe, a method for providing trustworthy, human-interpretable explanations with uncertainty scores for neural network decisions in robots, enhancing transparency and trustworthiness in real-world applications.

Contribution

It presents a novel explainability technique grounded in high-level concepts that offers uncertainty-aware explanations for robot neural networks, addressing gaps in existing explainable AI methods.

Findings

Effective in simulated and real-world robot models

Provides human-interpretable explanations with uncertainty scores

Enhances trust and diagnostics in robotic decision-making

Abstract

Black box neural networks are an indispensable part of modern robots. Nevertheless, deploying such high-stakes systems in real-world scenarios poses significant challenges when the stakeholders, such as engineers and legislative bodies, lack insights into the neural networks' decision-making process. Presently, explainable AI is primarily tailored to natural language processing and computer vision, falling short in two critical aspects when applied in robots: grounding in decision-making tasks and the ability to assess trustworthiness of their explanations. In this paper, we introduce a trustworthy explainable robotics technique based on human-interpretable, high-level concepts that attribute to the decisions made by the neural network. Our proposed technique provides explanations with associated uncertainty scores for the explanation by matching neural network's activations with human-interpretable visualizations. To validate our approach, we conducted a series of experiments with various simulated and real-world robot decision-making models, demonstrating the effectiveness of the proposed approach as a post-hoc, human-friendly robot diagnostic tool.