Sequential Sensor Fusion-Based Real-Time LSTM Gait Pattern Controller for Biped Robot

Li, Tzuu-Hseng S.; Kuo, Ping‐Huan; Cheng, Chuan-Han; Hung, Chia-Ching; Luan, Po‐Chien; Chang, Chien-Hsin

doi:10.1109/jsen.2020.3016968

Cited by 13 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The present study serves this purpose by utilizing nonnormalized sEMG amplitudes and LSTM architecture for ankle joint position and moment predictions in level-ground walking. This structure can be implemented in real-time robotic control applications (e.g., Li et al, 2021 ) and used to generate reference inputs for advanced powered prosthesis controllers such as impedance control ( Aghasadeghi et al, 2013 ; Wu et al, 2022 ).…”

Section: Discussionmentioning

confidence: 99%

“…Presently, we used the muscle combination MG + BF + GMax for sEMG feature selection. Previous studies with a similar aim of utilizing sEMG in predicting joint kinematics and kinetics conducted either a feature (e.g., Phinyomark et al, 2011) or a muscle combination selection (e.g., Wang et al, 2021), or report only the utilized feature per muscle (Phinyomark et al, 2011;Li et al, 2021). Note that, taking into account the challenging nature of determining which specific parameter or combination of parameters is responsible for an improved neural network output (Goodfellow et al, 2016), a separate evaluation of the effects of multiple parameters has been suggested (Molnar, 2020).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

The use of nonnormalized surface EMG and feature inputs for LSTM-based powered ankle prosthesis control algorithm development

Keleş,

Türksoy,

Yucesoy

2023

Front. Neurosci.

View full text Add to dashboard Cite

Advancements in instrumentation support improved powered ankle prostheses hardware development. However, control algorithms have limitations regarding number and type of sensors utilized and achieving autonomous adaptation, which is key to a natural ambulation. Surface electromyogram (sEMG) sensors are promising. With a minimized number of sEMG inputs an economic control algorithm can be developed, whereas limiting the use of lower leg muscles will provide a practical algorithm for both ankle disarticulation and transtibial amputation. To determine appropriate sensor combinations, a systematic assessment of the predictive success of variations of multiple sEMG inputs in estimating ankle position and moment has to conducted. More importantly, tackling the use of nonnormalized sEMG data in such algorithm development to overcome processing complexities in real-time is essential, but lacking. We used healthy population level walking data to (1) develop sagittal ankle position and moment predicting algorithms using nonnormalized sEMG, and (2) rank all muscle combinations based on success to determine economic and practical algorithms. Eight lower extremity muscles were studied as sEMG inputs to a long-short-term memory (LSTM) neural network architecture: tibialis anterior (TA), soleus (SO), medial gastrocnemius (MG), peroneus longus (PL), rectus femoris (RF), vastus medialis (VM), biceps femoris (BF) and gluteus maximus (GMax). Five features extracted from nonnormalized sEMG amplitudes were used: integrated EMG (IEMG), mean absolute value (MAV), Willison amplitude (WAMP), root mean square (RMS) and waveform length (WL). Muscle and feature combination variations were ranked using Pearson’s correlation coefficient (r > 0.90 indicates successful correlations), the root-mean-square error and one-dimensional statistical parametric mapping between the original data and LSTM response. The results showed that IEMG+WL yields the best feature combination performance. The best performing variation was MG + RF + VM (rposition = 0.9099 and rmoment = 0.9707) whereas, PL (rposition = 0.9001, rmoment = 0.9703) and GMax+VM (rposition = 0.9010, rmoment = 0.9718) were distinguished as the economic and practical variations, respectively. The study established for the first time the use of nonnormalized sEMG in control algorithm development for level walking.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

The use of nonnormalized surface EMG and feature inputs for LSTM-based powered ankle prosthesis control algorithm development

Keleş,

Türksoy,

Yucesoy

2023

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…LSTM is suitable for system identification; it models complex system dynamics by capturing temporal input-output dependencies and managing non-linearities [19,20]. For control, it predicts future states, detects anomalies, and adapts actions based on learned complex system dynamics, involving a comprehensive process from data preparation to real-time implementation.…”

Section: Lstm For Identification and Controlmentioning

confidence: 99%

LSTM-Based Visual Control for Complex Robot Interactions

Djelal,

Ouanane,

Bouriachi

2023

JESA

View full text Add to dashboard Cite

This paper introduces a novel application of the Long Short-Term Memory (LSTM) recurrent neural network for the identification and control of complex systems. The computation-intensive task of calculating the interaction matrix, a necessity for visual control laws in these systems, makes LSTM a fitting solution. The proposed control law unfolds in two phases: an offline phase, where the LSTM is trained on a set of visual features to generate a kinematic screw vector, and an online phase, where the trained LSTM is utilized for real-time system control. To assess the efficacy of the LSTM-based approach, we undertook a case study involving a manipulator robot, the UR5. We executed a series of simulations under various conditions to illustrate the effectiveness of the proposed LSTM-based control law. The outcomes from these experiments affirm the robustness of the LSTM controller, outperforming traditional methods even when faced with rapid fluctuations in visual features, partial loss of visual information, and model uncertainties in the robot.

show abstract

“…The operating range is 0~5V with <1ms response time for determining the foot-contact force of the robot during walking on different surfaces with different walking speeds. The application of other types of force sensors is also possible for supporting the generation of a stable robot walking pattern in a dynamic walking environment [27][28][29].…”

Section: B Pizo-resistive Membrane Force Sensor (Prmfs)mentioning

confidence: 99%

Energy Efficiency of Force-Sensor-Controlled Humanoid-Robot Walking on Indoor Surfaces

et al. 2020

View full text Add to dashboard Cite

Sequential Sensor Fusion-Based Real-Time LSTM Gait Pattern Controller for Biped Robot

Cited by 13 publications

References 46 publications

The use of nonnormalized surface EMG and feature inputs for LSTM-based powered ankle prosthesis control algorithm development

The use of nonnormalized surface EMG and feature inputs for LSTM-based powered ankle prosthesis control algorithm development

LSTM-Based Visual Control for Complex Robot Interactions

Energy Efficiency of Force-Sensor-Controlled Humanoid-Robot Walking on Indoor Surfaces

Contact Info

Product

Resources

About