{"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/reinforcement-learning-for-contact-rich-tasks","title":"Reinforcement Learning for Contact-Rich Tasks: Robotic Peg Insertion Strategies","arxiv_id":null,"date":"2020-12-14","proceeding":"CUHK Course IERG5350 2020 12","authors":["Jianbang Liu","Ang ZHANG"],"abstract":"Vision and touch are especially important when doing contact-rich manipulation\ntasks in unstructured environments. It is non-trivial to manually design a robot con-\ntroller that combines these modalities which have very different characteristics. In\nthis project, to connect vision and touch, we first equip robots with both visual and\ntactile sensors and collect a large-scale dataset of corresponding vision and tactile\nsequences. We use self-supervision to learn a compact and multimodal representa-\ntion of our sensory inputs, which can then be used to improve the sample efficiency\nof our policy learning. We will train a policy in a simulation environment using\ndeep reinforcement learning algorithms. The learned policy is also transferable to\nhandle real-world tasks. The peg insertion is chosen as the task for demonstration\nin this project. A preliminary version of our python implementation is avail-\nable at: https://github.com/Henry1iu/ierg5350_rl_course_project.\nA video introducing our project is available at: https://mycuhk-my.\nsharepoint.com/:v:/g/personal/1155071948_link_cuhk_edu_hk/\nEaKiGmkUvjJOoSqdWxrqjXYBpz3dCSAfOD9Co8krttyqUQ?e=RXsHD2","url_abs":"https://openreview.net/forum?id=s7-yAok04gI","url_pdf":"https://openreview.net/pdf?id=s7-yAok04gI","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":"reinforcement-learning-for-contact-rich-tasks","repo_url":"https://github.com/Henry1iu/ierg5350_rl_course_project","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contact-rich-manipulation","task_name":"Contact-rich Manipulation"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}