Anticipation in Human-Robot Cooperation: A Recurrent Neural Network Approach for Multiple Action Sequences Prediction
Authors:
- Paul SchydloPSPaul Schydlo
- Mirko RakovicMRMirko Rakovic
- Lorenzo JamoneLJLorenzo Jamone
- José Santos-VictorJSJosé Santos-Victor
Preprint
Abstract
Close human-robot cooperation is a key enabler for new developments in advanced manufacturing and assistive applications. Close cooperation require robots that can predict human actions and intent, and understand human non-verbal cues. Recent approaches based on neural networks have led to encouraging results in the human action prediction problem both in continuous and discrete spaces. Our approach extends the research in this direction. Our contributions are three-fold. First, we validate the use of gaze and body pose cues as a means of predicting human action through a feature selection method. Next, we address two shortcomings of existing literature: predicting multiple and variable-length action sequences. This is achieved by introducing an encoder-decoder recurrent neural network topology in the discrete action prediction problem. In addition, we theoretically demonstrate the importance of predicting multiple action sequences as a means of estimating the stochastic reward in a human robot cooperation scenario. Finally, we show the ability to effectively train the prediction model on a action prediction dataset, involving human motion data, and explore the influence of the model's parameters on its performance. Source code repository: https://github.com/pschydlo/ActionAnticipationKeywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Speaking and Listening with the Eyes: Gaze Signaling during Dyadic InteractionsPLOS ONE, 2015
- Using gaze patterns to predict task intent in collaborationFrontiers in Psychology, 2015
- Anticipating Human Activities Using Object Affordances for Reactive Robotic ResponseIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Learning robotic eye–arm–hand coordination from human demonstration: a coupled dynamical systems approachBiological Cybernetics, 2014
- On the Properties of Neural Machine Translation: Encoder–Decoder Approaches2014
- Learning human activities and object affordances from RGB-D videosThe International Journal of Robotics Research, 2013
- Attractive, Informative, and Communicative Robot System on Guide Plate as an Attendant with Awareness of User’s GazePaladyn, 2013
- A review of feature selection techniques in bioinformaticsBioinformatics, 2007
- Visual Learning by Imitation With Motor RepresentationsIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2005
- Functional relations between the manual and oculomotor control systemsExperimental Neurology, 1970