{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/anticipation-in-human-robot-cooperation-a","title":"Anticipation in Human-Robot Cooperation: A Recurrent Neural Network Approach for Multiple Action Sequences Prediction","arxiv_id":"1802.10503","date":"2018-02-28","proceeding":null,"authors":["Paul Schydlo","Mirko Rakovic","Lorenzo Jamone","José Santos-Victor"],"abstract":"Close human-robot cooperation is a key enabler for new developments in\nadvanced manufacturing and assistive applications. Close cooperation require\nrobots that can predict human actions and intent, and understand human\nnon-verbal cues. Recent approaches based on neural networks have led to\nencouraging results in the human action prediction problem both in continuous\nand discrete spaces. Our approach extends the research in this direction. Our\ncontributions are three-fold. First, we validate the use of gaze and body pose\ncues as a means of predicting human action through a feature selection method.\nNext, we address two shortcomings of existing literature: predicting multiple\nand variable-length action sequences. This is achieved by introducing an\nencoder-decoder recurrent neural network topology in the discrete action\nprediction problem. In addition, we theoretically demonstrate the importance of\npredicting multiple action sequences as a means of estimating the stochastic\nreward in a human robot cooperation scenario. Finally, we show the ability to\neffectively train the prediction model on a action prediction dataset,\ninvolving human motion data, and explore the influence of the model's\nparameters on its performance. Source code repository:\nhttps://github.com/pschydlo/ActionAnticipation","url_abs":"http://arxiv.org/abs/1802.10503v3","url_pdf":"http://arxiv.org/pdf/1802.10503v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"anticipation-in-human-robot-cooperation-a","repo_url":"https://github.com/pschydlo/ActionAnticipation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.10503","atlas_url":"https://app.syntology.ai/?focus=1802.10503","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}