Task-sequencing Simulator: Integrated Machine Learning to Execution Simulation for Robot Manipulation

TL;DR

This paper introduces a task-sequencing simulator for robot manipulation that integrates learning and execution simulations using a modular, trainable concept model to enhance reusability and transferability.

Contribution

It proposes a novel modular simulation framework with a unified concept model that bridges learning and execution in robotic manipulation tasks.

Findings

Reusability of the simulator for different tasks

Unified framework for learning-to-execution transfer

Improved simulation-to-real transfer performance

Abstract

A task-sequencing simulator in robotics manipulation to integrate simulation-for-learning and simulation-for-execution is introduced. Unlike existing machine-learning simulation where a non-decomposed simulation is used to simulate a training scenario, the task-sequencing simulator runs a composed simulation using building blocks. This way, the simulation-for-learning is structured similarly to a multi-step simulation-for-execution. To compose both learning and execution scenarios, a unified trainable-and-composable description of blocks called a concept model is proposed and used. Using the simulator design and concept models, a reusable simulator for learning different tasks, a common-ground system for learning-to-execution, simulation-to-real is achieved and shown.