Task recognition and future human activity prediction are of importance for a safe and profitable human-robot cooperation. In real scenarios, the robot has to extract this information merging the knowledge of the task with contextual information from the sensors, minimizing possible misunderstandings. In this paper, we focus on tasks that can be represented as a sequence of manipulated objects and performed actions. The task is modelled with a Dynamic Bayesian Network (DBN), which takes as input manipulated objects and performed actions. Objects and actions are separately classified starting from RGB-D raw data. The DBN is responsible for estimating the current task, predicting the most probable future pairs of action-object and correcting possible misclassification. The effectiveness of the proposed approach is validated on a case of study, consisting of three typical tasks of a kitchen scenario.
A Bayesian approach for task recognition and future human activity prediction / Magnanimo, V.; Saveriano, M.; Rossi, S.; Lee, D.. - 2014-:October(2014), pp. 726-731. (Intervento presentato al convegno 23rd IEEE International Symposium on Robot and Human Interactive Communication, IEEE RO-MAN 2014 tenutosi a Heriot-Watt University, gbr nel 2014) [10.1109/ROMAN.2014.6926339].
A Bayesian approach for task recognition and future human activity prediction
Saveriano M.;Rossi S.;
2014-01-01
Abstract
Task recognition and future human activity prediction are of importance for a safe and profitable human-robot cooperation. In real scenarios, the robot has to extract this information merging the knowledge of the task with contextual information from the sensors, minimizing possible misunderstandings. In this paper, we focus on tasks that can be represented as a sequence of manipulated objects and performed actions. The task is modelled with a Dynamic Bayesian Network (DBN), which takes as input manipulated objects and performed actions. Objects and actions are separately classified starting from RGB-D raw data. The DBN is responsible for estimating the current task, predicting the most probable future pairs of action-object and correcting possible misclassification. The effectiveness of the proposed approach is validated on a case of study, consisting of three typical tasks of a kitchen scenario.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione