Dynamic Task Control Method of a Flexible Manipulator Using a Deep Recurrent Neural Network

TL;DR

This paper introduces DTXNET, a deep recurrent neural network that enables real-time control of flexible manipulators for dynamic tasks without explicit intermediate postures, demonstrated through Japanese drum performance.

Contribution

The paper presents a novel real-time control method using DTXNET that learns control relationships directly, overcoming modeling and posture derivation challenges in flexible manipulators.

Findings

DTXNET effectively controls flexible manipulators in real-time.

Application to Japanese drum drumming validates the method.

Optimal network configuration identified for task execution.

Abstract

The flexible body has advantages over the rigid body in terms of environmental contact thanks to its underactuation. On the other hand, when applying conventional control methods to realize dynamic tasks with the flexible body, there are two difficulties: accurate modeling of the flexible body and the derivation of intermediate postures to achieve the tasks. Learning-based methods are considered to be more effective than accurate modeling, but they require explicit intermediate postures. To solve these two difficulties at the same time, we developed a real-time task control method with a deep recurrent neural network named Dynamic Task Execution Network (DTXNET), which acquires the relationship among the control command, robot state including image information, and task state. Once the network is trained, only the target event and its timing are needed to realize a given task. To demonstrate the effectiveness of our method, we applied it to the task of Wadaiko (traditional Japanese drum) drumming as an example, and verified the best configuration of DTXNET.