Assistive Robotics for Upper Limb Physical Rehabilitation:A Systematic Review and Future Prospects

Physical assistive robotics are oriented to support and improve functional capacities of people.In physical rehabilitation,robots are indeed useful for functional recovery of affected limb.However,there are still open questions related to technological aspects.This work presents a systematic review of upper limb rehabilitation robotics in order to analyze and establish technological challenges and future directions in this area.A bibliometric analysis was performed for the systematic literature review.Literature from the last six years,conducted between August 2020 and May 2021,was reviewed.The methodology for the literature search and a bibliometric analysis of the metadata are presented.After a preliminary search resulted in 820 articles,a total of 66 articles were included.A concurrency network and bibliographic analysis were provided.And an analysis of occurrences,taxonomy,and rehabilitation robotics reported in the literature is presented.This review aims to provide to the scientific community an overview of the state of the art in assistive robotics for upper limb physical rehabilitation.The literature analysis allows access to a gap of unexplored options to define the technological prospects applied to upper limb physical rehabilitation robotics.

TMCA-Net: A Compact Convolution Network for Monitoring Upper Limb Rehabilitation

This study proposed a lightweight but high-performance convolu-tion network for accurately classifying five upper limb movements of arm,involving forearm flexion and rotation,arm extension,lumbar touch and no reaction state,aiming to monitoring patient’s rehabilitation process and assist the therapist in elevating patient compliance with treatment.To achieve this goal,a lightweight convolution neural network TMCA-Net(Time Mul-tiscale Channel Attention Convolutional Neural Network)is designed,which combines attention mechanism,uses multi-branched convolution structure to automatically extract feature information at different scales from sensor data,and filters feature information based on attention mechanism.In particular,channel separation convolution is used to replace traditional convolution.This reduces the computational complexity of the model,decouples the convolution operation of the time dimension and the cross-channel feature interaction,which is helpful to the target optimization of feature extraction.TMCA-Net shows excellent performance in the upper limb rehabilitation ges-ture data,achieves 99.11%accuracy and 99.16%F1-score for the classification and recognition of five gestures.Compared with CNN and LSTM network,it achieves 65.62%and 89.98%accuracy in the same task.In addition,on the UCI smartphone public dataset,with the network parameters of one tenth of the current advanced model,the recognition accuracy rate of 95.21%has been achieved,which further proves the light weight and performance characteristics of the model.The clinical significance of this study is to accurately monitor patients’upper limb rehabilitation gesture by an affordable intelligent model as an auxiliary support for therapists’decision-making.