In everyday life, people instinctively reach for objects without knowing their exact position. Robots, on the other hand, usually require precise environmental information and complex calculations. The newly developed robotic hand from EPFL dispenses with this computational burden. Instead, the robotic hand uses soft materials, spring mechanisms and an intelligent design that enables human-like gripping without high-resolution sensors.<\/p>\n\n\n\n\n\n
Self-organising movements with a<\/strong>93% success rate From rigid machines to adaptive systems New perspectives for robotics and locations with a future The ADAPT hand shows that intelligent robotics is not only created in the code, but also in the material. Investing in adaptive systems opens up new markets, from collaborative manufacturing to human-centred assistance systems. The EPFL project sends a strong signal about the role of research and site development in a world where machines will have to act autonomously and safely in the future.<\/p>\n\n","protected":false},"excerpt":{"rendered":" Researchers at EPFL have developed a robotic hand that can grasp 24 different objects with human-like precision without complex programming – simply through the strategic use of flexibility in materials and mechanics. The ADAPT project marks a paradigm shift in robotics: away from centralised control and towards distributed intelligence in skin, joints and materials.<\/p>\n","protected":false},"author":2,"featured_media":132350,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"pmpro_default_level":"","_surecart_dashboard_logo_width":"180px","_surecart_dashboard_show_logo":true,"_surecart_dashboard_navigation_orders":true,"_surecart_dashboard_navigation_invoices":true,"_surecart_dashboard_navigation_subscriptions":true,"_surecart_dashboard_navigation_downloads":true,"_surecart_dashboard_navigation_billing":true,"_surecart_dashboard_navigation_account":true,"inline_featured_image":false,"_monsterinsights_skip_tracking":false,"footnotes":""},"categories":[12476,12483],"tags":[52950,13451,52951,52952,15738],"class_list":["post-132415","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-immonews","category-proptech-en","tag-feedback-en","tag-flexibilitaet-en","tag-greiftechnik-en","tag-ki-algorythmen-en","tag-technik-en","pmpro-has-access"],"acf":{"bild_mit_ki_erstellt_worden":[],"lead":"Researchers at EPFL have developed a robotic hand that can grasp 24 different objects with human-like precision without complex programming - simply through the strategic use of flexibility in materials and mechanics. The ADAPT project marks a paradigm shift in robotics: away from centralised control and towards distributed intelligence in skin, joints and materials.","autor":"Quelle: EPFL, Bild: CREATE Lab EPFL","ort":"","bildunterschrift":"","zusammenfassung":"","bild_im_grid":false,"gallerie":"","newsim":""},"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t
<\/strong>The hand uses silicone straps, mechanical springs and a foldable robotic joint, supplemented by just 12 motors instead of the usual 20. Thanks to this reduced but optimally distributed control, ADAPT achieved a gripping success rate of 93% in tests with 24 objects, with a similarity of 68% to human movements. The interaction between material, mould and environment partially replaces classic programming, a form of mechanical intelligence.<\/p>\n\n\n\n\n\n
<\/strong>Instead of controlling each joint separately, the robot hand follows only four main points of movement. Everything else is determined by physical interactions with the object. This not only reduces computational effort, but also creates robust systems that can deal with uncertainties and unknown shapes. In future, this flexibility will be supplemented by sensory feedback and AI algorithms. A hybrid approach that combines precision and adaptability.<\/p>\n\n\n\n\n\n
<\/strong>The findings of the EPFL researchers are not only important for research, but also for industrial applications in unstructured environments – such as logistics, care, agriculture or urban service systems. Robots that act flexibly without permanent reprogramming open up new possibilities for automation and relieve the burden on skilled workers in specific areas where conventional systems reach their limits.<\/p>\n\n\n\n\n\n