Flexible-Joint Manipulator Trajectory Tracking with Learned Two-Stage Model employing One-Step Future Prediction

TL;DR

This paper introduces a learning-based two-stage model with one-step future prediction to enhance trajectory tracking in flexible-joint manipulators, especially at high velocities, demonstrating improved accuracy over classical controllers.

Contribution

The paper presents a novel two-stage model incorporating one-step future prediction for flexible-joint manipulators, trained end-to-end on real data to improve high-velocity trajectory tracking.

Findings

Enhanced tracking accuracy with future state prediction

Outperforms classical baseline controllers

Effective on real-world Baxter robot data

Abstract

Flexible-joint manipulators are frequently used for increased safety during human-robot collaboration and shared workspace tasks. However, joint flexibility significantly reduces the accuracy of motion, especially at high velocities and with inexpensive actuators. In this paper, we present a learning-based approach to identify the unknown dynamics of a flexible-joint manipulator and improve the trajectory tracking at high velocities. We propose a two-stage model which is composed of a one-step forward dynamics future predictor and an inverse dynamics estimator. The second part is based on linear time-invariant dynamical operators to approximate the feed-forward joint position and velocity commands. We train the model end-to-end on real-world data and evaluate it on the Baxter robot. Our experiments indicate that augmenting the input with one-step future state prediction improves the performance, compared to the same model without prediction. We compare joint position, joint velocity and end-effector position tracking accuracy against the classical baseline controller and several simpler models.