# Deep execution monitor for robot assistive tasks

## TL;DR

This paper presents a deep learning-based execution monitor that predicts subtasks and evaluates task states to improve robot assistive task performance, effectively bridging planning and execution in non-deterministic environments.

## Contribution

Introduces a novel deep model for predicting subtasks and visually assessing task states, enhancing high-level robot task execution and robustness.

## Key findings

- Deep execution monitor improves task success rates.
- Supports non-deterministic task execution environments.
- Enhances coordination between planning and robot operations.

## Abstract

We consider a novel approach to high-level robot task execution for a robot assistive task. In this work we explore the problem of learning to predict the next subtask by introducing a deep model for both sequencing goals and for visually evaluating the state of a task. We show that deep learning for monitoring robot tasks execution very well supports the interconnection between task-level planning and robot operations. These solutions can also cope with the natural non-determinism of the execution monitor. We show that a deep execution monitor leverages robot performance. We measure the improvement taking into account some robot helping tasks performed at a warehouse.