{"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/deep-learning-for-detecting-robotic-grasps","title":"Deep Learning for Detecting Robotic Grasps","arxiv_id":"1301.3592","date":"2013-01-16","proceeding":null,"authors":["Ian Lenz","Honglak Lee","Ashutosh Saxena"],"abstract":"We consider the problem of detecting robotic grasps in an RGB-D view of a\nscene containing objects. In this work, we apply a deep learning approach to\nsolve this problem, which avoids time-consuming hand-design of features. This\npresents two main challenges. First, we need to evaluate a huge number of\ncandidate grasps. In order to make detection fast, as well as robust, we\npresent a two-step cascaded structure with two deep networks, where the top\ndetections from the first are re-evaluated by the second. The first network has\nfewer features, is faster to run, and can effectively prune out unlikely\ncandidate grasps. The second, with more features, is slower but has to run only\non the top few detections. Second, we need to handle multimodal inputs well,\nfor which we present a method to apply structured regularization on the weights\nbased on multimodal group regularization. We demonstrate that our method\noutperforms the previous state-of-the-art methods in robotic grasp detection,\nand can be used to successfully execute grasps on two different robotic\nplatforms.","url_abs":"http://arxiv.org/abs/1301.3592v6","url_pdf":"http://arxiv.org/pdf/1301.3592v6.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":[],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"robotic-grasping","task_name":"Robotic Grasping"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/robotic-grasping-on-cornell-grasp-dataset-1","task":"Robotic Grasping","dataset":"Cornell Grasp Dataset","model":"Fast Search","rank_in_archive_order":7,"of":7,"metrics":{"5 fold cross validation":"60.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1301.3592","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}