<p>&nbsp;In order to execute non-repetitive tasks, robots need to learn on the tasks to improve task performance. The performance model that maps process parameters to task performance cannot be built in advance for such non-repetitive tasks. The robot can execute a small portion of the task with certain set of process parameters and attractively update the process parameters based on the observations of the task performance. In order to make the learning process efficient, the trade-off between exploration and exploitation should be explicitly considered . Too much exploration may lead to the waste of time without significant improvement on task performance. On the other hand, stopping exploration prematurely leads to high suboptimal task performance. This paper describes a sequential decision making approach to select the set of parameters to improve the task performance during non-repetitive tasks. The robot learns to improve process parameters while meeting an objective function and satisfying given task performance constraints. &nbsp;We&nbsp;are mainly focused on tasks where minimization of task completion time is the main objective. The overall learning approach uses &nbsp;feasibility biased sampling, surrogate model construction and greedy optimization. We validate our approach by implementing the decision making approach in simulation of robotic sanding application.</p>

Learning to Improve Performance During Non-Repetitive Tasks Performed by Robots

Paper Proceedings: https://asmedigitalcollection.asme.org/IDETC-CIE/IDETC-CIE2021/volume/85369

ASME 2021 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.