國立中興大學科研產業化平台

上一頁
  • 專利名稱(中文) / 應用於智慧機器人與智慧機械的深度與寬度學習
  • 專利名稱(英文) / Deep Learning and Broad Learning with Applications to Smart Robots and Machinery
  • 所屬單位(一級單位) / 電機資訊學院
  • 所屬單位(二級單位) / 電機工程學系
  • 發明人(中文) / 蔡清池
  • 發明人(英文) / Ching-Chih Tsai
  • 申請國家 /
  • 專利類型 /
  • 專利證書號 /
  • 技術成熟度 /

深度學習已被廣泛地探討且被應用於智慧機器人與智慧機械之前沿科技。寬度學習自2017年被證實為可在沒有深度學習架構下達成同等效能的一種有功效與效率的學習演算法。藉由加入深度學習,寬度學習以及智慧運動控制法則,本演講針對智慧機器人與智慧機械之應用課題,提出多種以深度學習以及寬度學習為基礎的人工智慧新典範與學習架構。該報告首先回顧深度學習以及寬度學習的近期進展,然後分別就智慧移動單機器人,多單機器人以及陸空合作多機器人系統等案例,說明四種深寬度學習演算法的應用。最後,推薦未來可能的研究議題。

Deep learning (DL) has been widely investigated and applied for frontier mobile robotics and smart machinery. Broad learning system (BLS) has been shown to work as an effective and efficient incremental learning without the need for deep architecture, thus giving a new paradigm and learning system for AI systems. By incorporating the merits of DL, BLS and intelligent motion control methods, this talk will present you DL-based or BLS-based novel control frameworks or paradigms for a class of mobile robots, multirobots and smart machinery, in order to achieve desired control. In the short talk, some literature reviews about DLs and BLs are first mentioned, and then four novel DL-based or BL-based control methods are briefly highlighted and demonstrated for their applications to intelligent mobile robots, multirobots and collaborative air-ground robotic systems. Last but not least, some perspective topics are recommended for future research.

自主導航,深度學習,寬度學習,智慧機器人,智慧機器

Autonomous Navigation, Deep Learning, Broad Learning System, Intelligent Robots, Intelligent Machinery


與我聯絡