Observable and Attention-Directing BDI Agents for Human-Autonomy Teaming

TL;DR

This paper enhances Belief-Desire-Intention agents with observability and attention-directing features to improve transparency in human-autonomy teaming, verified through formal semantics and practical tools.

Contribution

It introduces observable and attention-directing extensions to CAN-based BDI agents, enabling better transparency and communication in human-autonomy collaboration.

Findings

Extended semantics for BDI agents to include observability and attention features

Formal encoding of agent behavior using bigraphs and verification with PRISM

Practical demonstration with UAV example and verification results

Abstract

Human-autonomy teaming (HAT) scenarios feature humans and autonomous agents collaborating to meet a shared goal. For effective collaboration, the agents must be transparent and able to share important information about their operation with human teammates. We address the challenge of transparency for Belief-Desire-Intention agents defined in the Conceptual Agent Notation (CAN) language. We extend the semantics to model agents that are observable (i.e. the internal state of tasks is available), and attention-directing (i.e. specific states can be flagged to users), and provide an executable semantics via an encoding in Milner's bigraphs. Using an example of unmanned aerial vehicles, the BigraphER tool, and PRISM, we show and verify how the extensions work in practice.