Reinforcement Learning of Action and Query Policies with LTL Instructions under Uncertain Event Detector

TL;DR

This paper introduces LAQBL, a reinforcement learning framework enabling robots to follow LTL instructions under uncertain event detection by learning action and query policies that handle multiple instruction branches.

Contribution

It proposes a novel RL approach that models belief LTL with a graph neural network and learns when to query event detectors to improve task success under uncertainty.

Findings

Successfully follows LTL instructions with uncertain detectors in simulations

Learns effective action and query policies to handle instruction branching

Reduces unnecessary event detector queries, improving efficiency

Abstract

Reinforcement learning (RL) with linear temporal logic (LTL) objectives can allow robots to carry out symbolic event plans in unknown environments. Most existing methods assume that the event detector can accurately map environmental states to symbolic events; however, uncertainty is inevitable for real-world event detectors. Such uncertainty in an event detector generates multiple branching possibilities on LTL instructions, confusing action decisions. Moreover, the queries to the uncertain event detector, necessary for the task's progress, may increase the uncertainty further. To cope with those issues, we propose an RL framework, Learning Action and Query over Belief LTL (LAQBL), to learn an agent that can consider the diversity of LTL instructions due to uncertain event detection while avoiding task failure due to the unnecessary event-detection query. Our framework simultaneously learns 1) an embedding of belief LTL, which is multiple branching possibilities on LTL instructions using a graph neural network, 2) an action policy, and 3) a query policy which decides whether or not to query for the event detector. Simulations in a 2D grid world and image-input robotic inspection environments show that our method successfully learns actions to follow LTL instructions even with uncertain event detectors.