Holistic Assembly Planning Framework for Dynamic Human-Robot Collaboration

The combination of humans' cognitive skills and dexterity with the endurance and repeatability of robots is a promising approach to modern assembly. However, creating an assembly sequence plan and the appropriate division of the workload between humans and robots is a manual and time-consuming job. This work presents a novel framework named "Extract-Enrich-Plan-Review" that facilitates holistic planning of human-robot assembly processes. The framework uses information from CAD files to feed a planning algorithm that generates assembly sequences according to various boundary conditions such as resource capability, part dependencies, timing, and adaptability to human behavior. An expert is kept in the loop to enrich the data and to review and modify the automatically generated sequences. Preliminary results show assembly sequence plans for human-robot collaboration (HRC) as an output with less cycle times compared to human-only assembly.