A Multifaceted User Study for the Teaching-Learning-Prediction-Collaboration Framework in Human-Robot Collaborative Tasks
Presentation Type
Poster
Faculty Advisor
Weitian Wang
Access Type
Event
Start Date
26-4-2024 2:15 PM
End Date
26-4-2024 3:15 PM
Description
As the implementation of robotic systems in modern industries becomes more commonplace, the desire to streamline and simplify interaction with them does as well. Human-robot collaboration (HRC) frameworks have made strides towards these goals in recent years to facilitate shared tasks in human-robot teams. Proposed methods such as learning from demonstration (LfD) show great potential in enhancing collaborative tasks. To boost the capacity of LfD, in our previous study, we developed a novel teaching-learning-prediction- collaboration (TLPC) framework for the robot to learn from human demonstrations, customize its task strategies according to human’s personalized working preference, predict human intentions, and assist the human in collaborative tasks. In this work, we conduct a multifaceted user study to evaluate the TLPC framework in real-world human-robot collaborative tasks. Participants of this user study are from diverse age groups, educational backgrounds, and genders, and this study seeks to observe and analyze the subjective feelings and feedback of the participants using the TLPC framework during collaborative tasks with the robot via periodic surveys given throughout the experiment. Seven assessment metrics are developed during the human-robot collaborative process to comprehensively evaluate the performance of the TLPC framework. A controlled human-robot collaborative experiment without the TLPC framework is also conducted. The user study results and evaluation analysis will contribute to gathering insights into and creating catalysts for the construction and optimization of human-robot interactive systems in advanced manufacturing contexts to improve collaboration quality, manufacturing productivity, human safety, and ergonomics. The future work of this study is also discussed.
A Multifaceted User Study for the Teaching-Learning-Prediction-Collaboration Framework in Human-Robot Collaborative Tasks
As the implementation of robotic systems in modern industries becomes more commonplace, the desire to streamline and simplify interaction with them does as well. Human-robot collaboration (HRC) frameworks have made strides towards these goals in recent years to facilitate shared tasks in human-robot teams. Proposed methods such as learning from demonstration (LfD) show great potential in enhancing collaborative tasks. To boost the capacity of LfD, in our previous study, we developed a novel teaching-learning-prediction- collaboration (TLPC) framework for the robot to learn from human demonstrations, customize its task strategies according to human’s personalized working preference, predict human intentions, and assist the human in collaborative tasks. In this work, we conduct a multifaceted user study to evaluate the TLPC framework in real-world human-robot collaborative tasks. Participants of this user study are from diverse age groups, educational backgrounds, and genders, and this study seeks to observe and analyze the subjective feelings and feedback of the participants using the TLPC framework during collaborative tasks with the robot via periodic surveys given throughout the experiment. Seven assessment metrics are developed during the human-robot collaborative process to comprehensively evaluate the performance of the TLPC framework. A controlled human-robot collaborative experiment without the TLPC framework is also conducted. The user study results and evaluation analysis will contribute to gathering insights into and creating catalysts for the construction and optimization of human-robot interactive systems in advanced manufacturing contexts to improve collaboration quality, manufacturing productivity, human safety, and ergonomics. The future work of this study is also discussed.