Robots are increasingly exploited in production plants. Within the Industry 4.0 paradigm, the robotcomplements the human’s capabilities, learning new tasks and adapting itself to compensate foruncertainties. With this aim, the presented paper focuses on the investigation of machine learningtechniques to make a sensorless robot able to learn and optimize an industrial assembly task.Relying on sensorless Cartesian impedance control, two main contributions are defined: (1) a task-trajectory learning algorithm based on a few human’s demonstrations (exploiting Hidden MarkovModel approach), and (2) an autonomous optimization procedure of the task execution (exploitingBayesian Optimization). To validate the proposed methodology, an assembly task has been selected asa reference application. The task consists of mounting a gear into its square-section shaft on a fixedbase to simulate the assembly of a gearbox. A Franka EMIKA Panda manipulator has been used as atest platform, implementing the proposed methodology. The experiments, carried out on a populationof 15 subjects, show the effectiveness of the proposed strategy, making the robot able to learn andoptimize its behavior to accomplish the assembly task, even in the presence of task uncertainties.
Human–robot collaboration in sensorless assembly task learning enhanced by uncertainties adaptation via Bayesian Optimization
2020-12-13
oai:zenodo.org:5118777
Elsevier Robotics and Autonomous Systems 136
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
DDC: | 629 |
Robot life-long task learning from human demonstrations: a Bayesian approach
British Library Online Contents | 2017
|Learning Action Duration and Synergy in Task Planning for Human-Robot Collaboration
BASE | 2022
|