{"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/seeing-all-the-angles-learning-multiview","title":"Seeing All the Angles: Learning Multiview Manipulation Policies for Contact-Rich Tasks from Demonstrations","arxiv_id":"2104.13907","date":"2021-04-28","proceeding":null,"authors":["Trevor Ablett","Yifan Zhai","Jonathan Kelly"],"abstract":"Learned visuomotor policies have shown considerable success as an alternative to traditional, hand-crafted frameworks for robotic manipulation. Surprisingly, an extension of these methods to the multiview domain is relatively unexplored. A successful multiview policy could be deployed on a mobile manipulation platform, allowing the robot to complete a task regardless of its view of the scene. In this work, we demonstrate that a multiview policy can be found through imitation learning by collecting data from a variety of viewpoints. We illustrate the general applicability of the method by learning to complete several challenging multi-stage and contact-rich tasks, from numerous viewpoints, both in a simulated environment and on a real mobile manipulation platform. Furthermore, we analyze our policies to determine the benefits of learning from multiview data compared to learning with data collected from a fixed perspective. We show that learning from multiview data results in little, if any, penalty to performance for a fixed-view task compared to learning with an equivalent amount of fixed-view data. Finally, we examine the visual features learned by the multiview and fixed-view policies. Our results indicate that multiview policies implicitly learn to identify spatially correlated features.","url_abs":"https://arxiv.org/abs/2104.13907v3","url_pdf":"https://arxiv.org/pdf/2104.13907v3.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":"seeing-all-the-angles-learning-multiview","repo_url":"https://github.com/utiasSTARS/multiview-manipulation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"}],"methods":[],"datasets_introduced":[{"slug":"multiview-manipulation-data","name":"Multiview Manipulation Data","full_name":"Multiview Manipulation Expert Data and Trained Models"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}