{"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/beyond-the-self-using-grounded-affordances-to","title":"Beyond the Self: Using Grounded Affordances to Interpret and Describe Others' Actions","arxiv_id":"1902.09705","date":"2019-02-26","proceeding":null,"authors":["Giovanni Saponaro","Lorenzo Jamone","Alexandre Bernardino","Giampiero Salvi"],"abstract":"We propose a developmental approach that allows a robot to interpret and\ndescribe the actions of human agents by reusing previous experience. The robot\nfirst learns the association between words and object affordances by\nmanipulating the objects in its environment. It then uses this information to\nlearn a mapping between its own actions and those performed by a human in a\nshared environment. It finally fuses the information from these two models to\ninterpret and describe human actions in light of its own experience. In our\nexperiments, we show that the model can be used flexibly to do inference on\ndifferent aspects of the scene. We can predict the effects of an action on the\nbasis of object properties. We can revise the belief that a certain action\noccurred, given the observed effects of the human action. In an early action\nrecognition fashion, we can anticipate the effects when the action has only\nbeen partially observed. By estimating the probability of words given the\nevidence and feeding them into a pre-defined grammar, we can generate relevant\ndescriptions of the scene. We believe that this is a step towards providing\nrobots with the fundamental skills to engage in social collaboration with\nhumans.","url_abs":"http://arxiv.org/abs/1902.09705v1","url_pdf":"http://arxiv.org/pdf/1902.09705v1.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":"beyond-the-self-using-grounded-affordances-to","repo_url":"https://github.com/gsaponaro/tcds-gestures","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}