Next Article in Journal
Underwater Structured Light Stripe Center Extraction with Normalized Grayscale Gravity Method
Next Article in Special Issue
Regression-Based Machine Learning for Predicting Lifting Movement Pattern Change in People with Low Back Pain
Previous Article in Journal
Electronics and Detectors for the Stellar Intensity Interferometer of the ASTRI Mini-Array Telescopes
Previous Article in Special Issue
Validation of Inertial Measurement Units for Analyzing Golf Swing Rotational Biomechanics
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

A Deep Learning Approach for Biped Robot Locomotion Interface Using a Single Inertial Sensor

Department of Mechanical Engineering, Graduate School of Science and Engineering, Ehime University, Bunkyo-cho 3, Matsuyama 790-8577, Ehime, Japan
*
Author to whom correspondence should be addressed.
Sensors 2023, 23(24), 9841; https://doi.org/10.3390/s23249841
Submission received: 26 October 2023 / Revised: 25 November 2023 / Accepted: 12 December 2023 / Published: 15 December 2023
(This article belongs to the Special Issue Feature Papers in Wearables 2023)

Abstract

In this study, we introduce a novel framework that combines human motion parameterization from a single inertial sensor, motion synthesis from these parameters, and biped robot motion control using the synthesized motion. This framework applies advanced deep learning methods to data obtained from an IMU attached to a human subject’s pelvis. This minimalistic sensor setup simplifies the data collection process, overcoming price and complexity challenges related to multi-sensor systems. We employed a Bi-LSTM encoder to estimate key human motion parameters: walking velocity and gait phase from the IMU sensor. This step is followed by a feedforward motion generator-decoder network that accurately produces lower limb joint angles and displacement corresponding to these parameters. Additionally, our method also introduces a Fourier series-based approach to generate these key motion parameters solely from user commands, specifically walking speed and gait period. Hence, the decoder can receive inputs either from the encoder or directly from the Fourier series parameter generator. The output of the decoder network is then utilized as a reference motion for the walking control of a biped robot, employing a constraint-consistent inverse dynamics control algorithm. This framework facilitates biped robot motion planning based on data from either a single inertial sensor or two user commands. The proposed method was validated through robot simulations in the MuJoco physics engine environment. The motion controller achieved an error of ≤5° in tracking the joint angles demonstrating the effectiveness of the proposed framework. This was accomplished using minimal sensor data or few user commands, marking a promising foundation for robotic control and human–robot interaction.
Keywords: motion synthesis; deep learning; walking controller; inertial sensor motion synthesis; deep learning; walking controller; inertial sensor

Share and Cite

MDPI and ACS Style

Alemayoh, T.T.; Lee, J.H.; Okamoto, S. A Deep Learning Approach for Biped Robot Locomotion Interface Using a Single Inertial Sensor. Sensors 2023, 23, 9841. https://doi.org/10.3390/s23249841

AMA Style

Alemayoh TT, Lee JH, Okamoto S. A Deep Learning Approach for Biped Robot Locomotion Interface Using a Single Inertial Sensor. Sensors. 2023; 23(24):9841. https://doi.org/10.3390/s23249841

Chicago/Turabian Style

Alemayoh, Tsige Tadesse, Jae Hoon Lee, and Shingo Okamoto. 2023. "A Deep Learning Approach for Biped Robot Locomotion Interface Using a Single Inertial Sensor" Sensors 23, no. 24: 9841. https://doi.org/10.3390/s23249841

APA Style

Alemayoh, T. T., Lee, J. H., & Okamoto, S. (2023). A Deep Learning Approach for Biped Robot Locomotion Interface Using a Single Inertial Sensor. Sensors, 23(24), 9841. https://doi.org/10.3390/s23249841

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop