{"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/leveraging-contact-forces-for-learning-to","title":"Leveraging Contact Forces for Learning to Grasp","arxiv_id":"1809.07004","date":"2018-09-19","proceeding":null,"authors":["Hamza Merzic","Miroslav Bogdanovic","Daniel Kappler","Ludovic Righetti","Jeannette Bohg"],"abstract":"Grasping objects under uncertainty remains an open problem in robotics\nresearch. This uncertainty is often due to noisy or partial observations of the\nobject pose or shape. To enable a robot to react appropriately to unforeseen\neffects, it is crucial that it continuously takes sensor feedback into account.\nWhile visual feedback is important for inferring a grasp pose and reaching for\nan object, contact feedback offers valuable information during manipulation and\ngrasp acquisition. In this paper, we use model-free deep reinforcement learning\nto synthesize control policies that exploit contact sensing to generate robust\ngrasping under uncertainty. We demonstrate our approach on a multi-fingered\nhand that exhibits more complex finger coordination than the commonly used\ntwo-fingered grippers. We conduct extensive experiments in order to assess the\nperformance of the learned policies, with and without contact sensing. While it\nis possible to learn grasping policies without contact sensing, our results\nsuggest that contact feedback allows for a significant improvement of grasping\nrobustness under object pose uncertainty and for objects with a complex shape.","url_abs":"http://arxiv.org/abs/1809.07004v1","url_pdf":"http://arxiv.org/pdf/1809.07004v1.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":"leveraging-contact-forces-for-learning-to","repo_url":"https://github.com/machines-in-motion/grasping_sim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"reinforcement-learning","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}