Search

Collaborative robots are widely utilized in intelligent manufacturing to cooperate with the human to accomplish different assembly tasks. To improve the efficiency of human–robot cooperation, robots should be able to recognize human intentions and provide necessary assistance proactively. The major challenge for current human intention recognition methods is that they only deal with known human intentions of predefined tasks and lack of ability to learn unknown intentions corresponding to new tasks. This article introduces an evolving hidden Markov model (EHMM)-based approach to learn new human intentions incrementally by carrying out structure and parameter updating based on the observed sequence, in parallel with the recognition. The incremental learning ability makes it applicable in dynamic environments with changing tasks. A set of assistive execution policies has been developed for the robot to provide appropriate assistance to the human partner based on the intention recognition results in real time. Experiments have been carried out to verify the effectiveness of our approach in human–robot cooperative assembly tasks. The results show very high recognition accuracy (≥95.45%), and the human subjects show their high satisfaction with the intention learning ability of the proposed approach. Note to Practitioners—This article aims to effectively improve the productivity of human–robot cooperation by exploiting human adaptability and robot repeatability. Smooth cooperation requires the peer robot to provide proactive assistance to humans by inferring human intention after training. Moreover, the robot should also be able to learn untrained intentions online by human demonstrations. This is made possible by our proposed evolving hidden Markov model (EHMM) that unifies intention inference and incremental learning. Simplified cooperative assembly tasks have been designed to verify the proposed unified intention inference and learning model. A robotic assembly platform has been introduced to integrate the proposed EHMM with a perception module and a collaborative manipulation module. We have demonstrated, through experiments and surveys, that the proposed approach can promote efficacy and acceptance of human–robot cooperative assembly. [ABSTRACT FROM AUTHOR]

A trend towards drier conditions during the April to October 'cool' season across southern Australia has been observed in the past few decades. Frequent and prolonged droughts have a significant impact on the financial stability of affected farming communities. Forecast-based Financing (FbF) is a novel proactive aid approach that provides support measures to increase resilience during the window between drought early warnings, and the actual onset and intensification of drought. Using the Northern Murray-Darling Basin as a case study, we investigated whether FbF combined with a user-centred Integrated Early Warning System (I-EWS) for drought has the potential to increase the drought resilience of Australian farming communities. This study shows that farming businesses most impacted by drought have three common factors: (i) lower levels of business management skills, (ii) lower levels of pre-drought preparedness during non-drought periods, and (iii) slower responses when the intensity of drought increases. The results suggest that FbF in its current form is not recommended for a market economy such as Australia, as forms of direct assistance may have adverse long-term effects through disrupting the market itself and may not encourage farm operators to regularly assess and adapt their drought management strategies. Results also suggest that providing farmers, service providers, and all levels of government with tools that incorporate a user-centred I-EWS for drought can improve overall decision-making before, during, and even after drought. This change from a reactive to a proactive approach to managing drought impacts can be a highly effective form of increasing the drought resilience of farming communities. [ABSTRACT FROM AUTHOR]

Smart environments can already observe the actions of a human through pervasive sensors. Based on these observations, our work aims to predict the actions a human is likely to perform next. Predictions can enable a robot to proactively assist humans by autonomously executing an action on their behalf. In this paper, Action Graphs are introduced to model the order constraints between actions. Action Graphs are derived from a problem defined in Planning Domain Definition Language (PDDL). When an action is observed, the node values are updated and next actions predicted. Subsequently, a robot executes one of the predicted actions if it does not impact the flow of the human by obstructing or delaying them. Our Action Graph approach is applied to a kitchen domain. [ABSTRACT FROM AUTHOR]

Copyright of Informatica (03505596) is the property of Slovene Society Informatika and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)