Petri Net Machines for Human-Agent Interaction

TL;DR

This paper introduces Petri Net Machines, a formal framework for controlling human-agent interactions that can handle concurrency and plan interleaving, addressing data limitations of reinforcement learning in smart devices.

Contribution

It presents a novel Petri Net-based formalism for state machines that improve reliability and concurrency in human-agent interaction systems.

Findings

Petri Net Machines can execute concurrent actions reliably.

They enable interleaving multiple plans simultaneously.

The approach is demonstrated in a shopping mall human-robot interaction scenario.

Abstract

Smart speakers and robots become ever more prevalent in our daily lives. These agents are able to execute a wide range of tasks and actions and, therefore, need systems to control their execution. Current state-of-the-art such as (deep) reinforcement learning, however, requires vast amounts of data for training which is often hard to come by when interacting with humans. To overcome this issue, most systems still rely on Finite State Machines. We introduce Petri Net Machines which present a formal definition for state machines based on Petri Nets that are able to execute concurrent actions reliably, execute and interleave several plans at the same time, and provide an easy to use modelling language. We show their workings based on the example of Human-Robot Interaction in a shopping mall.