{"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/self-organized-control-for-musculoskeletal","title":"Self-organized control for musculoskeletal robots","arxiv_id":"1602.02990","date":"2016-02-09","proceeding":null,"authors":["Ralf Der","Georg Martius"],"abstract":"With the accelerated development of robot technologies, optimal control\nbecomes one of the central themes of research. In traditional approaches, the\ncontroller, by its internal functionality, finds appropriate actions on the\nbasis of the history of sensor values, guided by the goals, intentions,\nobjectives, learning schemes, and so on planted into it. The idea is that the\ncontroller controls the world---the body plus its environment---as reliably as\npossible. However, in elastically actuated robots this approach faces severe\ndifficulties. This paper advocates for a new paradigm of self-organized\ncontrol. The paper presents a solution with a controller that is devoid of any\nfunctionalities of its own, given by a fixed, explicit and context-free\nfunction of the recent history of the sensor values. When applying this\ncontroller to a muscle-tendon driven arm-shoulder system from the Myorobotics\ntoolkit, we observe a vast variety of self-organized behavior patterns: when\nleft alone, the arm realizes pseudo-random sequences of different poses but one\ncan also manipulate the system into definite motion patterns. But most\ninterestingly, after attaching an object, the controller gets in a functional\nresonance with the object's internal dynamics: when given a half-filled bottle,\nthe system spontaneously starts shaking the bottle so that maximum response\nfrom the dynamics of the water is being generated. After attaching a pendulum\nto the arm, the controller drives the pendulum into a circular mode. In this\nway, the robot discovers dynamical affordances of objects its body is\ninteracting with. We also discuss perspectives for using this controller\nparadigm for intention driven behavior generation.","url_abs":"http://arxiv.org/abs/1602.02990v2","url_pdf":"http://arxiv.org/pdf/1602.02990v2.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":"self-organized-control-for-musculoskeletal","repo_url":"https://github.com/HBPNeurorobotics/Demonstrator7-UnsupervisedHebbianLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}