Human-robot mobile co-manipulation of flexible objects by fusing wrench and skeleton tracking data

Abstract

Over the past decades, robots have been extensively deployed in multiple industries. More recently, industrial robots have been taken out of their cages, being more present in dynamic environments, interacting in the close vicinity of human operators. Traditionally, robots have been mainly developed to perform pre-programmed tasks. However, some tasks are too complex or expensive to be performed by a robotic system alone. Examples are the handling of large sheet-like objects in the composite part production or plastic film wrapping industry. This work presents a hybrid wrench and vision reactive control approach towards the handling of large (non-)rigid materials. The presented approach fuses force-torque data and skeleton tracking to control a mobile manipulator in an intuitive manner, by using the intelligence of the operator as much as possible. Using this approach, tools such as path planning, or object modelling are not essential to obtain the results. The hybrid controller is subject to stability experiments where the controller responses are monitored when the mobile manipulator is subject to a step and sinusoidal function as input. Lastly, the overall approach is illustrated with a proof-of-concept task in which a flexible sheet is handled by a mobile manipulator and human operator together.