Modeling Previous Trial Effect in Human Manipulation through Iterative Learning Control
In the execution of repetitive tasks, humans can capitalize on experience to improve their motor performance. Prominent examples of this ability can be recognized in our capacity of grasping and manipulating in uncertain conditions. With the aim of providing a mathematical description for such behav...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-09-01
|
| Series: | Advanced Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/aisy.201900074 |
| _version_ | 1819205185074888704 |
|---|---|
| author | Lorenzo Cenceschi Cosimo Della Santina Giuseppe Averta Manolo Garabini Qiushi Fu Marco Santello Matteo Bianchi Antonio Bicchi |
| author_facet | Lorenzo Cenceschi Cosimo Della Santina Giuseppe Averta Manolo Garabini Qiushi Fu Marco Santello Matteo Bianchi Antonio Bicchi |
| author_sort | Lorenzo Cenceschi |
| collection | DOAJ |
| description | In the execution of repetitive tasks, humans can capitalize on experience to improve their motor performance. Prominent examples of this ability can be recognized in our capacity of grasping and manipulating in uncertain conditions. With the aim of providing a mathematical description for such behavior, experiments are considered where participants are required to lift an object with an unexpected mass distribution. By repeating multiple times the same lifting action, participants can learn the correct motor command for task accomplishment. Three models are proposed that combine reactive terms and a learned anticipatory action to explain experimental data. The models feature intratrial and intertrial memory, and the effect of slowly and fast adaptive sensory receptors. The architectures’ effectiveness in explaining experimental data is compared with a general‐purpose state of the art model. The proposed algorithms conspicuously outperform the state of the art in all the considered validation routines. Global and within‐trial human behavior is predicted with 88% of accuracy in nominal conditions. When the object's center of mass is moved, the accuracy is maintained up to 83%. Finally, convergence properties of proposed algorithms are analytically discussed, and their stability and robustness against measurement noise are evaluated in simulation. |
| first_indexed | 2024-12-23T04:47:41Z |
| format | Article |
| id | doaj.art-608282a5854d41a49976baaec2892678 |
| institution | Directory Open Access Journal |
| issn | 2640-4567 |
| language | English |
| last_indexed | 2024-12-23T04:47:41Z |
| publishDate | 2020-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advanced Intelligent Systems |
| spelling | doaj.art-608282a5854d41a49976baaec28926782022-12-21T17:59:35ZengWileyAdvanced Intelligent Systems2640-45672020-09-0129n/an/a10.1002/aisy.201900074Modeling Previous Trial Effect in Human Manipulation through Iterative Learning ControlLorenzo Cenceschi0Cosimo Della Santina1Giuseppe Averta2Manolo Garabini3Qiushi Fu4Marco Santello5Matteo Bianchi6Antonio Bicchi7Research Center “Enrico Piaggio” University of Pisa Largo Lucio Lazzarino 1 Pisa 56126 ItalyComputer Science and Artificial Intelligence Laboratory (CSAIL) Massachusetts Institute of Technology 32 Vassar Street Cambridge MA 02139 USAResearch Center “Enrico Piaggio” University of Pisa Largo Lucio Lazzarino 1 Pisa 56126 ItalyResearch Center “Enrico Piaggio” University of Pisa Largo Lucio Lazzarino 1 Pisa 56126 ItalyDepartment of Mechanical and Aerospace Engineering University of Central Florida 12760 Pegasus Dr., Orlando FL 32816 USASchool of Biological and Health Systems Engineering Ira A. Fulton Schools of Engineering Arizona State University Tempe AZ USAResearch Center “Enrico Piaggio” University of Pisa Largo Lucio Lazzarino 1 Pisa 56126 ItalyResearch Center “Enrico Piaggio” University of Pisa Largo Lucio Lazzarino 1 Pisa 56126 ItalyIn the execution of repetitive tasks, humans can capitalize on experience to improve their motor performance. Prominent examples of this ability can be recognized in our capacity of grasping and manipulating in uncertain conditions. With the aim of providing a mathematical description for such behavior, experiments are considered where participants are required to lift an object with an unexpected mass distribution. By repeating multiple times the same lifting action, participants can learn the correct motor command for task accomplishment. Three models are proposed that combine reactive terms and a learned anticipatory action to explain experimental data. The models feature intratrial and intertrial memory, and the effect of slowly and fast adaptive sensory receptors. The architectures’ effectiveness in explaining experimental data is compared with a general‐purpose state of the art model. The proposed algorithms conspicuously outperform the state of the art in all the considered validation routines. Global and within‐trial human behavior is predicted with 88% of accuracy in nominal conditions. When the object's center of mass is moved, the accuracy is maintained up to 83%. Finally, convergence properties of proposed algorithms are analytically discussed, and their stability and robustness against measurement noise are evaluated in simulation.https://doi.org/10.1002/aisy.201900074grasping and manipulationiterative learning controlmathematical models of human motor controlprevious trial effect |
| spellingShingle | Lorenzo Cenceschi Cosimo Della Santina Giuseppe Averta Manolo Garabini Qiushi Fu Marco Santello Matteo Bianchi Antonio Bicchi Modeling Previous Trial Effect in Human Manipulation through Iterative Learning Control Advanced Intelligent Systems grasping and manipulation iterative learning control mathematical models of human motor control previous trial effect |
| title | Modeling Previous Trial Effect in Human Manipulation through Iterative Learning Control |
| title_full | Modeling Previous Trial Effect in Human Manipulation through Iterative Learning Control |
| title_fullStr | Modeling Previous Trial Effect in Human Manipulation through Iterative Learning Control |
| title_full_unstemmed | Modeling Previous Trial Effect in Human Manipulation through Iterative Learning Control |
| title_short | Modeling Previous Trial Effect in Human Manipulation through Iterative Learning Control |
| title_sort | modeling previous trial effect in human manipulation through iterative learning control |
| topic | grasping and manipulation iterative learning control mathematical models of human motor control previous trial effect |
| url | https://doi.org/10.1002/aisy.201900074 |
| work_keys_str_mv | AT lorenzocenceschi modelingprevioustrialeffectinhumanmanipulationthroughiterativelearningcontrol AT cosimodellasantina modelingprevioustrialeffectinhumanmanipulationthroughiterativelearningcontrol AT giuseppeaverta modelingprevioustrialeffectinhumanmanipulationthroughiterativelearningcontrol AT manologarabini modelingprevioustrialeffectinhumanmanipulationthroughiterativelearningcontrol AT qiushifu modelingprevioustrialeffectinhumanmanipulationthroughiterativelearningcontrol AT marcosantello modelingprevioustrialeffectinhumanmanipulationthroughiterativelearningcontrol AT matteobianchi modelingprevioustrialeffectinhumanmanipulationthroughiterativelearningcontrol AT antoniobicchi modelingprevioustrialeffectinhumanmanipulationthroughiterativelearningcontrol |