{"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/improving-task-parameterised-movement","title":"Improving Task-Parameterised Movement Learning Generalisation with Frame-Weighted Trajectory Generation","arxiv_id":"1903.01240","date":"2019-03-04","proceeding":null,"authors":["Aran Sena","Brendan Michael","Matthew Howard"],"abstract":"Learning from Demonstration depends on a robot learner generalising its\nlearned model to unseen conditions, as it is not feasible for a person to\nprovide a demonstration set that accounts for all possible variations in\nnon-trivial tasks. While there are many learning methods that can handle\ninterpolation of observed data effectively, extrapolation from observed data\noffers a much greater challenge. To address this problem of generalisation,\nthis paper proposes a modified Task-Parameterised Gaussian Mixture Regression\nmethod that considers the relevance of task parameters during trajectory\ngeneration, as determined by variance in the data. The benefits of the proposed\nmethod are first explored using a simulated reaching task data set. Here it is\nshown that the proposed method offers far-reaching, low-error extrapolation\nabilities that are different in nature to existing learning methods. Data\ncollected from novice users for a real-world manipulation task is then\nconsidered, where it is shown that the proposed method is able to effectively\nreduce grasping performance errors by ${\\sim30\\%}$ and extrapolate to unseen\ngrasp targets under real-world conditions. These results indicate the proposed\nmethod serves to benefit novice users by placing less reliance on the user to\nprovide high quality demonstration data sets.","url_abs":"http://arxiv.org/abs/1903.01240v1","url_pdf":"http://arxiv.org/pdf/1903.01240v1.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":"improving-task-parameterised-movement","repo_url":"https://github.com/aransena/alphaTPGMR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}