Scholarlink

With recent advancements in AI and computation tools, intelligent paradigms have emerged to empower different fields such as shared autonomy and human-machine teaming in healthcare with new capabilities. Advanced AI algorithms (e.g., reinforcement learning) can be trained and developed to autonomously make individual decisions to achieve desired plan and motion goals. However, such independent decisions and goal achievements might not be ideal within healthcare, where human intent plays a pivotal and crucial role in guiding human-machine paradigms. This chapter presents a comprehensive review of human-centered shared autonomy AI frameworks, particularly by focusing on upper limb biosignal-based machine interfaces and their associated end-effector based motor control systems, including computer cursors, robotic arms, and planar robotic platforms. Our primary focus is delving into motor planning, learning (rehabilitation), and controls, specifically covering conceptual foundations of human-machine teaming in reach-and-grasp tasks, analyzing both the theoretical principles and practical implementations from both human and machine perspectives. We extended the discussion in each section to elaborate on how human and machine inputs can be blended as shared autonomy paradigms, with the healthcare applications. The chapter examines topics on human factors, biosignal processing for intent detection, shared autonomy approaches in brain-computer interfaces (BCI), rehabilitation, robots, assistive robotics, and finally, Large Language Models (LLM) as the next frontier. With a foundation based on human-centered factors, we also proposed adaptive shared autonomy AI as a potential high-performance paradigm for the two interactive human and AI agents. We identified current challenges in human-centered shared autonomy implementation and proposed future directions, particularly examining the roles of AI reasoning agents in advancing these systems. Through this analysis, we bridge neuroscientific understanding with robotics approaches to develop more intuitive, effective, and ethical human-machine teaming frameworks.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Human-Centered Shared Autonomy for Motor Planning, Learning, and Control Applications

  • 章节

  • 发表日期：

    2026年

查看全文
  • M. H. Farhadi,
  • Ali Rabiee,
  • Sima Ghafoori,
  • Anna Cetera,
  • Wei Xu,
  • Reza Abiri

摘要

With recent advancements in AI and computation tools, intelligent paradigms have emerged to empower different fields such as shared autonomy and human-machine teaming in healthcare with new capabilities. Advanced AI algorithms (e.g., reinforcement learning) can be trained and developed to autonomously make individual decisions to achieve desired plan and motion goals. However, such independent decisions and goal achievements might not be ideal within healthcare, where human intent plays a pivotal and crucial role in guiding human-machine paradigms. This chapter presents a comprehensive review of human-centered shared autonomy AI frameworks, particularly by focusing on upper limb biosignal-based machine interfaces and their associated end-effector based motor control systems, including computer cursors, robotic arms, and planar robotic platforms. Our primary focus is delving into motor planning, learning (rehabilitation), and controls, specifically covering conceptual foundations of human-machine teaming in reach-and-grasp tasks, analyzing both the theoretical principles and practical implementations from both human and machine perspectives. We extended the discussion in each section to elaborate on how human and machine inputs can be blended as shared autonomy paradigms, with the healthcare applications. The chapter examines topics on human factors, biosignal processing for intent detection, shared autonomy approaches in brain-computer interfaces (BCI), rehabilitation, robots, assistive robotics, and finally, Large Language Models (LLM) as the next frontier. With a foundation based on human-centered factors, we also proposed adaptive shared autonomy AI as a potential high-performance paradigm for the two interactive human and AI agents. We identified current challenges in human-centered shared autonomy implementation and proposed future directions, particularly examining the roles of AI reasoning agents in advancing these systems. Through this analysis, we bridge neuroscientific understanding with robotics approaches to develop more intuitive, effective, and ethical human-machine teaming frameworks.