Development of the AI-based autonomous task planning and robot teaching solution for highly complex manufacturing assembly process

1. Funding Agency

MOTIE

2. Motivation

Mobile manipulators have shown effective autonomy in daily tasks with ㎝-level precision, but manufacturing assemblies require much finer accuracy, often at the ㎜ or µm scale. As these tasks remain mostly manual, there is a growing need for intuitive teaching and autonomous planning solutions to enable robots to perform complex tasks in unstructured environments.

3. Objectives

The project develops demonstration-based teaching technologies, AI foundation models for autonomous complex assembly, and an integrated solution combining virtual environments, teaching systems, task AI, and robotic platforms.

4. Results

• Simulation-based teaching interface (especially for force involved manipulation tasks)
• Autonomous task segmentation using force and motion data

5. Related Publications

• Is a Simulation better than Teleoperation for Acquiring Human Manipulation Skill Data?

6. Contact

• Kwang-Hyun Lee
• Donghyeon Kim
• Seong-Su Park