Machine Learning Approaches for Motor Learning: A Short Review

Caramiaux, Baptiste; Françoise, Jules; Liu, Wanyu; Sanchez, Téo; Bevilacqua, Frédéric

doi:10.3389/fcomp.2020.00016

Cited by 15 publications

(12 citation statements)

References 50 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this section, we will briefly describe how research in robot motor learning can expedite the research in human motor learning. Machine learning algorithms that are mainly used for robot motor learning are based on imitation learning, (deep) reinforcement learning, transfer learning or a combination of these [ 191 , 192 , 193 ]. Imitation learning or learning from demonstration is the task of teaching human behavior to a (humanoid) robotic agent [ 194 ].…”

Section: Machine Learning Algorithms For Human Motion Analysismentioning

confidence: 99%

“…This sequence of features needs to be learned by the robot. In reinforcement learning, the agent learns a new motor skill by trial-and-error, maximizing the reward function [ 191 ]. Finally, transfer learning is used to adapt a pretrained model in a training domain to a different test domains [ 195 ].…”

Section: Machine Learning Algorithms For Human Motion Analysismentioning

confidence: 99%

“…The algorithms described above can be helpful to solve an issue in the modeling of motor learning. Caramiaux et al [ 191 ] pointed out that machine learning for movement modeling did not address enough the motor learning aspects, i.e., the adaptability of the movement to fine-grained changes (motor adaptation) and to radical changes (motor skill acquisition). In their study, they identified three prominently used adaptation categories in machine learning-based robotic motor learning: (1) parameter adaptation in probabilistic models (e.g., Hidden Markov Model or Dynamic Bayesian Networks)—useful for motor adaptation, (2) transfer and imitation learning—faster learning of new skills and (3) adaptation through reinforcement learning—improving stability in unstructured environments.…”

Section: Machine Learning Algorithms For Human Motion Analysismentioning

confidence: 99%

See 2 more Smart Citations

Using Artificial Intelligence for Assistance Systems to Bring Motor Learning Principles into Real World Motor Tasks

Vandevoorde

Vollenkemper

Schwan

et al. 2022

Sensors

View full text Add to dashboard Cite

Humans learn movements naturally, but it takes a lot of time and training to achieve expert performance in motor skills. In this review, we show how modern technologies can support people in learning new motor skills. First, we introduce important concepts in motor control, motor learning and motor skill learning. We also give an overview about the rapid expansion of machine learning algorithms and sensor technologies for human motion analysis. The integration between motor learning principles, machine learning algorithms and recent sensor technologies has the potential to develop AI-guided assistance systems for motor skill training. We give our perspective on this integration of different fields to transition from motor learning research in laboratory settings to real world environments and real world motor tasks and propose a stepwise approach to facilitate this transition.

show abstract

Section: Machine Learning Algorithms For Human Motion Analysismentioning

confidence: 99%

Section: Machine Learning Algorithms For Human Motion Analysismentioning

confidence: 99%

Section: Machine Learning Algorithms For Human Motion Analysismentioning

confidence: 99%

See 1 more Smart Citation

Using Artificial Intelligence for Assistance Systems to Bring Motor Learning Principles into Real World Motor Tasks

Vandevoorde

Vollenkemper

Schwan

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Machine learning, however, can uncover important information that is undetected by routine clinical medical imaging, thus revealing potential biological information (11)(12)(13). Given its compelling advantages in the implementation of classification and prediction (14,15), machine learning has become a common method of scientific research (16,17). In this study, we analyzed ADC features combined with several machine learning models to effectively evaluate brain development differences between children with PRs and normal controls as well as the validity of the model.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Models on ADC Features to Assess Brain Changes of Children With Pierre Robin Sequence

et al. 2021

View full text Add to dashboard Cite

In order to evaluate brain changes in young children with Pierre Robin sequence (PRs) using machine learning based on apparent diffusion coefficient (ADC) features, we retrospectively enrolled a total of 60 cases (42 in the training dataset and 18 in the testing dataset) which included 30 PRs and 30 controls from the Children's Hospital Affiliated to the Nanjing Medical University from January 2017–December 2019. There were 21 and nine PRs cases in each dataset, with the remainder belonging to the control group in the same age range. A total of 105 ADC features were extracted from magnetic resonance imaging (MRI) data. Features were pruned using least absolute shrinkage and selection operator (LASSO) regression and seven ADC features were developed as the optimal signatures for training machine learning models. Support vector machine (SVM) achieved an area under the receiver operating characteristic curve (AUC) of 0.99 for the training set and 0.85 for the testing set. The AUC of the multivariable logistic regression (MLR) and the AdaBoost for the training and validation dataset were 0.98/0.84 and 0.94/0.69, respectively. Based on the ADC features, the two groups of cases (i.e., the PRs group and the control group) could be well-distinguished by the machine learning models, indicating that there is a significant difference in brain development between children with PRs and normal controls.

show abstract

“…There is an extensive research in human-robot interaction. Important current topics are—among others—the application of Artificial Intelligence and Machine learning (e.g., [ 1 ]), the significance of expert support (e.g., [ 2 ]), the impact of different forms of physical guidance (e.g., [ 3 ]) or the significance of motor variability (e.g., [ 4 ]). For example, if and under which conditions can robots profit from humans and vice versa.…”

Section: Introductionmentioning

confidence: 99%

Perception and prediction of the putting distance of robot putting movements under different visual/viewing conditions

et al. 2021

View full text Add to dashboard Cite

The purpose of this paper is to examine, whether and under which conditions humans are able to predict the putting distance of a robotic device. Based on the “flash-lag effect” (FLE) it was expected that the prediction errors increase with increasing putting velocity. Furthermore, we hypothesized that the predictions are more accurate and more confident if human observers operate under full vision (F-RCHB) compared to either temporal occlusion (I-RCHB) or spatial occlusion (invisible ball, F-RHC, or club, F-B). In two experiments, 48 video sequences of putt movements performed by a BioRob robot arm were presented to thirty-nine students (age: 24.49±3.20 years). In the experiments, video sequences included six putting distances (1.5, 2.0, 2.5, 3.0, 3.5, and 4.0 m; experiment 1) under full versus incomplete vision (F-RCHB versus I-RCHB) and three putting distances (2. 0, 3.0, and 4.0 m; experiment 2) under the four visual conditions (F-RCHB, I-RCHB, F-RCH, and F-B). After the presentation of each video sequence, the participants estimated the putting distance on a scale from 0 to 6 m and provided their confidence of prediction on a 5-point scale. Both experiments show comparable results for the respective dependent variables (error and confidence measures). The participants consistently overestimated the putting distance under the full vision conditions; however, the experiments did not show a pattern that was consistent with the FLE. Under the temporal occlusion condition, a prediction was not possible; rather a random estimation pattern was found around the centre of the prediction scale (3 m). Spatial occlusion did not affect errors and confidence of prediction. The experiments indicate that temporal constraints seem to be more critical than spatial constraints. The FLE may not apply to distance prediction compared to location estimation.

show abstract

Machine Learning Approaches for Motor Learning: A Short Review

Cited by 15 publications

References 50 publications

Using Artificial Intelligence for Assistance Systems to Bring Motor Learning Principles into Real World Motor Tasks

Using Artificial Intelligence for Assistance Systems to Bring Motor Learning Principles into Real World Motor Tasks

Machine Learning Models on ADC Features to Assess Brain Changes of Children With Pierre Robin Sequence

Perception and prediction of the putting distance of robot putting movements under different visual/viewing conditions

Contact Info

Product

Resources

About