Gait Trajectory and Event Prediction from State Estimation for Exoskeletons During Gait

Tanghe, Kevin; Groote, Friedl De; Lefeber, Dirk; Schutter, Joris De; Aertbeliën, Erwin

doi:10.1109/tnsre.2019.2950309

Cited by 32 publications

(33 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A lesser known but similar approach is based on probabilistic Principal Component Analysis and has been proposed by Aertebeliën and De Schutter [3]. It is used by Tanghe et al to model gait [11] and by Vergara et al in the control of a robotic arm [1]. Other probabilistic approaches use Gaussian Mixture Models (GMM) to recognize reaching motions [12].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Framework for Recognition and Prediction of Human Motions in Human-Robot Collaboration Using Probabilistic Motion Models

Callens

Have

Rossom

et al. 2020

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

This paper presents a framework for recognition and prediction of ongoing human motions. The predictions generated by this framework could be used in a controller for a robotic device, enabling the emergence of intuitive and predictable interactions between humans and a robotic collaborator. The framework includes motion onset detection, phase speed estimation, intent estimation and conditioning. For recognition and prediction of a motion, the framework makes use of a motion model database. This database contains several motion models learned using the probabilistic Principal Component Analysis (PPCA) method. The proposed framework is evaluated with joint angle trajectories of eight subjects performing squatting, stooping and lifting tasks. The motion onset and phase speed estimation modules are first evaluated separately. Next, an evaluation of the full framework provides more insight in the current challenges regarding motion prediction. A brief comparison between PPCA and the Probabilistic Movement Primitives (ProMP) method for learning motion models is made based on the influence of both methodologies on the performance of the framework. Both PPCA and ProMP motion models are able to predict motions over a short time horizon but struggle to predict motions over a longer horizon.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Finally, the performance of the IEKF was compared with the Moving Horizon Estimation (MHE) proposed in [11], with a horizon containing 10 observations. Comparison was done based on the average cumulative euclidean distance between estimated phase speed curves (such as shown in figure 3a) and benchmark curves.…”

Section: B Evaluation Of Phase Speed Estimationmentioning

confidence: 99%

A Framework for Recognition and Prediction of Human Motions in Human-Robot Collaboration Using Probabilistic Motion Models

Callens

Have

Rossom

et al. 2020

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The predicted kinematic feature variables, LA and AV, for the shank and thigh were reliably predicted up to 10 samples or time steps, i.e., up to 60 ms in the future. A 60-ms prediction of future trajectories adds a feedforward term to an assistive device controller rather than being reactive and predominantly relying on feedback terms (i.e., sensory information; Tanghe et al, 2019). This enables the assistive device to adapt to changes in human gait, allowing smoother synchronisation with user intentions and minimising interruptions when the user changes their movement pattern (Elliott et al, 2014;Zhang et al, 2017;Ding et al, 2018;Zaroug et al, 2019).…”

Section: Discussionmentioning

confidence: 99%

“…Another technique was implemented in the Lower Extremity Powered Exoskeleton (LOPES) device to emulate the trajectories from a healthy limb to the impaired limb (Vallery et al, 2008). Prediction of the lower limb joint angles future trajectory that effectively leads to foot events timing was also investigated in the works of Aertbeliën and De Schutter (2014) and Tanghe et al (2019) using probabilistic principal component analysis (PPCA).…”

Section: Introductionmentioning

confidence: 99%

Lower Limb Kinematics Trajectory Prediction Using Long Short-Term Memory Neural Networks

Zaroug

Lai

Mudie

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

This study determined whether the kinematics of lower limb trajectories during walking could be extrapolated using long short-term memory (LSTM) neural networks. It was hypothesised that LSTM auto encoders could reliably forecast multiple time-step trajectories of the lower limb kinematics, specifically linear acceleration (LA) and angular velocity (AV). Using 3D motion capture, lower limb position-time coordinates were sampled (100 Hz) from six male participants (age 22 ± 2 years, height 1.77 ± 0.02 m, body mass 82 ± 4 kg) who walked for 10 min at 5 km/h on a 0% gradient motordriven treadmill. These data were fed into an LSTM model with a sliding window of four kinematic variables with 25 samples or time steps: LA and AV for thigh and shank. The LSTM was tested to forecast five samples (i.e., time steps) of the four kinematic input variables. To attain generalisation, the model was trained on a dataset of 2,665 strides from five participants and evaluated on a test set of 1 stride from a sixth participant. The LSTM model learned the lower limb kinematic trajectories using the training samples and tested for generalisation across participants. The forecasting horizon suggested higher model reliability in predicting earlier future trajectories. The mean absolute error (MAE) was evaluated on each variable across the single tested stride, and for the fivesample forecast, it obtained 0.047 m/s 2 thigh LA, 0.047 m/s 2 shank LA, 0.028 deg/s thigh AV and 0.024 deg/s shank AV. All predicted trajectories were highly correlated with the measured trajectories, with correlation coefficients greater than 0.98. The motion prediction model may have a wide range of applications, such as mitigating the risk of falls or balance loss and improving the human-machine interface for wearable assistive devices.

show abstract

“…Several studies describe methods to identify locomotion modes and transitions among them based on integrating EMG signals with ground reaction forces [21], accelerometers [22], [23], and both accelerometers and gyroscopes [24]. Tanghe et al [25] fused different types of mechanical sensors to predict gait events and joint trajectories through a probabilistic principle component model. Results from these studies indicate that sensor fusion methods can increase the accuracy and robustness of a myoelectrical control system.…”

Section: Introductionmentioning

confidence: 99%

A Muscle Synergy-Inspired Method of Detecting Human Movement Intentions Based on Wearable Sensor Fusion

Liu

Wang

Gutierrez-Farewik

2021

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Detecting human movement intentions is fundamental to neural control of robotic exoskeletons, as it is essential for achieving seamless transitions between different locomotion modes. In this study, we enhanced a muscle synergyinspired method of locomotion mode identification by fusing the electromyography data with two types of data from wearable sensors (inertial measurement units), namely linear acceleration and angular velocity. From the finite state machine perspective, the enhanced method was used to systematically identify 2 static modes, 7 dynamic modes, and 27 transitions among them. In addition to the five broadly studied modes (level ground walking, ramps ascent/descent, stairs ascent/descent), we identified the transition between different walking speeds and modes of ramp walking at different inclination angles. Seven combinations of sensor fusion were conducted, on experimental data from 8 able-bodied adult subjects, and their classification accuracy and prediction time were compared. Prediction based on a fusion of electromyography and gyroscope (angular velocity) data predicted transitions earlier and with higher accuracy. All transitions and modes were identified with a total average classification accuracy of 94.5% with fused sensor data. For nearly all transitions, we were able to predict the next locomotion mode 300-500 ms prior to the step into that mode.

show abstract

Gait Trajectory and Event Prediction from State Estimation for Exoskeletons During Gait

Cited by 32 publications

References 35 publications

A Framework for Recognition and Prediction of Human Motions in Human-Robot Collaboration Using Probabilistic Motion Models

A Framework for Recognition and Prediction of Human Motions in Human-Robot Collaboration Using Probabilistic Motion Models

Lower Limb Kinematics Trajectory Prediction Using Long Short-Term Memory Neural Networks

A Muscle Synergy-Inspired Method of Detecting Human Movement Intentions Based on Wearable Sensor Fusion

Contact Info

Product

Resources

About