?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Transformer-Based+Prediction+of+Human+Motions+and+Contact+Forces+for+Physical+Human-Robot+Interaction&rft.creator=Fusco%2C+A&rft.creator=Modugno%2C+V&rft.creator=Kanoulas%2C+D&rft.creator=Rizzo%2C+A&rft.creator=Cognetti%2C+M&rft.description=In+this+paper%2C+we+propose+a+transformer-based+architecture+for+predicting+contact+forces+during+a+physical+human-robot+interaction.+Our+Neural+Network+is+composed+of+two+main+parts%3A+a+Multi-Layer+Perceptron+called+Transducer+and+a+Transformer.+The+former+estimates%2C+based+on+the+kinematic+data+from+a+motion+capture+suit%2C+the+current+contact+forces.+The+latter+predicts+-+taking+as+input+the+same+kinematic+data+and+the+output+of+the+Transducer+-+the+human+motions+and+the+contact+forces+over+a+time+window+in+the+future.+We+validated+our+approach+by+testing+the+network+on+directions+of+motions+that+were+not+provided+in+the+training+set.+We+also+compared+our+approach+to+a+purely+Transformer-based+network%2C+showing+a+better+prediction+accuracy+of+the+contact+forces.&rft.subject=Training%2C+%0D%0ARobot+motion%2C+%0D%0ATransducers%2C+%0D%0AAccuracy%2C+%0D%0AHuman-robot+interaction%2C+%0D%0AKinematics%2C+%0D%0ATransformers&rft.publisher=IEEE&rft.date=2024-08-08&rft.type=Proceedings+paper&rft.language=eng&rft.source=+++++In%3A++Proceedings+-+IEEE+International+Conference+on+Robotics+and+Automation.++(pp.+pp.+3161-3167).++IEEE%3A+Yokohama%2C+Japan.+(2024)+++++&rft.format=text&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10197169%2F1%2Ficra_2024_fusco.pdf&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10197169%2F&rft.rights=open