{"id":416,"date":"2010-12-17T13:42:01","date_gmt":"2010-12-17T13:42:01","guid":{"rendered":"http:\/\/fs-s-wpmu-02.facsci.ualberta.ca\/rlai\/?page_id=416"},"modified":"2020-01-06T19:11:02","modified_gmt":"2020-01-06T19:11:02","slug":"reinforcement-learning-for-adaptive-prosthetics","status":"publish","type":"page","link":"https:\/\/spaces.facsci.ualberta.ca\/rlai\/projects\/reinforcement-learning-for-adaptive-prosthetics\/","title":{"rendered":"Reinforcement Learning for Adaptive Prosthetics"},"content":{"rendered":"

The Reinforcement Learning for Adaptive Prosthetics project is a\u00a0collaboration with the AICML, the Glenrose Rehabilitation Hospital,\u00a0and the Composite & Biomedical Materials Research Group (MechanicalEngineering, U of A). Its goal is to develop reinforcement learning\u00a0(RL) algorithms that can help increase limb-deficient patients\u2019\u00a0ability to customize and control their new prosthetic devices, while\u00a0at the same time removing the need for frequent manual adjustments by\u00a0patients and physiotherapists. Specifically, the project addresses the\u00a0following open research questions:<\/p>\n

    \n
  1. How best to translate muscle\u00a0signals into control commands for a multi-function mechanical limb<\/li>\n
  2. How to automatically adapt control systems to the needs of individual\u00a0patients<\/li>\n
  3. How to improve limb control based on patient\u00a0feedback<\/li>\n<\/ol>\n

    When complete, the developed methods will increase the speed\u00a0and success with which new amputees can adapt to their powered\u00a0prosthetics, directly improving the quality of life for limb-deficient\u00a0patients.<\/p>\n

    Since its inception in 2010, the project has demonstrated a successful\u00a0first application of new actor-critic RL techniques to the domain of\u00a0upper-arm myoelectric prostheses. This is an important incremental\u00a0step toward the goal of fully adaptable intelligent prosthetic\u00a0devices. Current work is focused on the application of new RL\u00a0prediction and knowledge representation techniques to further increase\u00a0the adaptability and learning potential of intelligent prostheses.<\/p>\n","protected":false},"excerpt":{"rendered":"

    The Reinforcement Learning for Adaptive Prosthetics project is a\u00a0collaboration with the AICML, the Glenrose Rehabilitation Hospital,\u00a0and the Composite & Biomedical Materials Research Group (MechanicalEngineering, U of A). Its goal is to develop reinforcement learning\u00a0(RL) algorithms that can help increase limb-deficient patients\u2019\u00a0ability to customize and control their new prosthetic devices, while\u00a0at the same time removing the<\/p>\n

    Read More<\/a><\/p>\n","protected":false},"author":5,"featured_media":0,"parent":34,"menu_order":9,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-416","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/spaces.facsci.ualberta.ca\/rlai\/wp-json\/wp\/v2\/pages\/416","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/spaces.facsci.ualberta.ca\/rlai\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/spaces.facsci.ualberta.ca\/rlai\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/spaces.facsci.ualberta.ca\/rlai\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/spaces.facsci.ualberta.ca\/rlai\/wp-json\/wp\/v2\/comments?post=416"}],"version-history":[{"count":1,"href":"https:\/\/spaces.facsci.ualberta.ca\/rlai\/wp-json\/wp\/v2\/pages\/416\/revisions"}],"predecessor-version":[{"id":1141,"href":"https:\/\/spaces.facsci.ualberta.ca\/rlai\/wp-json\/wp\/v2\/pages\/416\/revisions\/1141"}],"up":[{"embeddable":true,"href":"https:\/\/spaces.facsci.ualberta.ca\/rlai\/wp-json\/wp\/v2\/pages\/34"}],"wp:attachment":[{"href":"https:\/\/spaces.facsci.ualberta.ca\/rlai\/wp-json\/wp\/v2\/media?parent=416"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}