Increasing efficiency in robot-supported assemblies through predictive mechanisms: An experimental evaluation

Abstract

The presented work focuses on investigating the influence of different hand-over timing strategies on the fluency and efficiency of a human-robot team in an assembly task.To this aim, four different timing strategies were experimentally evaluated: (I) a fixed time interval between two handovers, (II) a reactive behavior, where the robot is triggered by the human, (III) fixed time intervals depending on the current component, and (IV) a predictive assembly duration estimation algorithm. During the experiment, the time-to-completion of the task and the waiting times for human and robot were measured as reciprocal indication for the efficiency and respectively the fluency of the team.The results indicate that the efficiency of the human-robot team is significantly increased using a predictive timing strategy, because it enables the robot to provide the needed component just-in-time. The decrease in waiting times for the human worker leads to improved fluency of the collaboration. In addition, the predictive strategy enables the robot to perform preliminary tasks if no assistance is needed. Therefore, a nearly full usage of both partners' capacities can be reached.

Flexible human–robot cooperation models for assisted shop-floor tasks

“…A Bayesian framework is used in [23] to track a human hand position in the workspace with the aim of predicting an action's time-to-completion. The hand must be clearly visible for the estimate to be accurate, which limits certain motions with the aim of obtaining information about time-related aspects of the cooperation.…”

Assessment of Handover Prediction Models in Estimation of Cycle Times for Manual Assembly Tasks in a Human–Robot Collaborative Environment

“…Regarding the sociocognitive aspect, Endsley suggested that efficient collaboration requires common understanding of the task context between humans and robots and common expectations regarding the next step [27]. When two human working partners collaborate on an assembly task, they must be able to estimate the time required by their partner in the assembly process, including the effects of potential external and intrinsic factors (e.g., skill level, fatigue, and stress) that can affect the assembly rate [24]. Aleotti et al suggested that the precise and proactive estimation of handover time points by robots when handing over assembly parts to humans can minimize waiting times and maximize efficiency [28].…”

“…In this case, assembly time variation is simply caused by nonattributable random errors (e.g., accidentally dropping an assembly part, sudden itch as a trigger to scratch a body part, etc.). The present study used the common building blocks assembly task [24,25] as a collaborative task between robots and operators to explore the following two work scenarios: (1) a general repetitive assembly task during which mainly only nonattributable random errors occur in the cycle time; and (2) repetitive assembly in which the human operator exhibits a learning curve, resulting in causable and trending cycle time variation. The method-time measurement (MTM), Kalman filter [26], and trigger sensor predictive models were employed to compare the cycle time of the assembly task, waiting times of robot and operator, and the participants' subjective preferences.…”

Mechanisms and capabilities for human robot collaboration

“…The benefit of transferring anticipatory action to a human-robot context is also shown in [47], where a significant improvement of task efficiency compared to reactive behavior was possible. For an extensive evaluation of these hypothesis, we want to refer to previous publications [1], [48], [49], [50].…”

“…In [49] we have presented investigation on the influence of different hand-over timing strategies on the fluency and efficiency of such a human-robot team. Four different timing strategies were experimentally per-formed with 37 volunteers: (I) a fixed time interval between two hand overs, (II) a reactive behavior, where the robot is triggered by the human, (III) a fixed time intervals depending on the current component, and (IV) a predictive assembly duration estimation algorithm.…”