Great advances have been made in the area of assistive robots - robots that can do tasks when requested. For example, a robot might be told to “pick up a box.” This action, however, presupposes that the robot knows what a “box” is. Robots can be programmed to recognize a variety of objects, but to make them most useful, they should be able to adjust to a situation where they encounter an unrecognized object.
A project by Computer Science and Engineering PhD student Yang Yang seeks to address this problem. Yang is developing a grasping system whereby a robot will understand a command by the user and ask questions to confirm the attributes of the object if it is unknown. A system such as this would have huge benefits for assistive robots.
Some funding for this project was provided by a 2021 University of Minnesota Informatics Institute MnDRIVE PhD Graduate Assistantship. The UMII MnDRIVE Graduate Assistantship program supports UMN PhD candidates pursuing research at the intersection of informatics and any of the five MnDRIVE areas:
- Robotics, Sensors and Advanced Manufacturing
- Global Food Ventures
- Advancing Industry, Conserving Our Environment
- Discoveries and Treatments for Brain Conditions
- Cancer Clinical Trials
This project is part of the Robotics, Sensors, and Advanced Manufacturing MnDRIVE area.
Research Computing partners:
- University of Minnesota Informatics Institute (funding)
Image description: A robot arm reaches for and grasps an apple.
