Task-centric optimization for assistive mobile manipulators

Assistive-robotics;Mobile manipulation

Kapusta, Ariel S. ; Mechanical Engineering Hammond, Frank M. Liu, C. K. Ting, Lena Turk, Greg

University:Georgia Institute of Technology

Department:Mechanical Engineering

关键词: Assistive-robotics;    Mobile manipulation;   

Others  :  https://smartech.gatech.edu/bitstream/1853/60306/1/KAPUSTA-DISSERTATION-2018.pdf

美国|英语

来源: SMARTech Repository

【 摘 要 】

Assistive mobile manipulators could enable people with disabilities to perform tasks for themselves which would otherwise be difficult or impossible. The robot’s assistance has the potential to increase independence and quality of life. Through this dissertation we have explored methods to realize that assistance. Although many groups have looked at how a robot could execute some specific tasks, few have considered where to place the robot to better provide assistance. We have observed that this problem arises frequently in real-world settings and solving the problem can be challenging, even for an expert user. We first present an answer to the question, “How should a robot choose a configuration of its base to be better able to provide assistance?” In answering this question we expand the problem to better match common scenarios in assistive robotics, where the task may be complicated and may take place in a bed or wheelchair. We present task-centric optimization of robot configurations (TOC), a method for addressing this question. We demonstrate how TOC can select one or more robot configurations for many assistive tasks that involve the robot moving a tool around a persons body. We additionally provide evidence that TOC outperforms baseline methods from literature. We present an assistive robotic system consisting of a robotic bed and a mobile manipulator that uses TOC to allow the two robots to autonomously collaborate to better provide assistance. We tested this system with a person with severe quadriplegia in his home, providing evidence of the feasibility of TOC and the robotic system for providing assistance to real people. Through our work on assistive robotics, we recognized that an important activity of daily living (ADL), dressing, contains special challenges not fully addressed by TOC. We present task optimization of robot assisted dressing (TOORAD), a method for selecting actions for both the robot and the person that will result in successful dressing. We demonstrate the efficacy of TOORAD in a study with participants with disabilities receiving dressing xix assistance from a mobile manipulator. In that study, we also administered surveys on habits, needs, capabilities, and views on robot-assisted dressing that we expect will provide guidance for future research.