34
I. Chatzikonstantinou et al.
roach, which is an indication that narrowing down the search space through hierarchical consideration of topology and task assignment, and then task scheduling
presents a measurable merit. A single instance of a schedule generated through
the proposed approach is demonstrated in Fig. 4.
6 Conclusion
This paper presented a new approach for orchestrating large teams of agents
consisting of collaborating humans and robots in achieving optimal process efficiency while ensuring that humans are involved in minimally laborious tasks. We
specifically focus on the distribution of human agents within factory floors consisting of many workstations, in an efficient manner that promotes supervisory
roles in place of copious labor. We propose a multi-stage optimization approach
for tackling the large-scale HRC orchestration problem, where the first stage
solves an approximate task and topological agent distribution problem, which
is introduced as a set of constraints for the second stage of the problem, which
solves a fully detailed scheduling problem formulated as MILP. Initial experimental validation yields encouraging results that demonstrate a clear advantage
of the proposed approach. The next steps involve further development of heuristics in order to improve efficiency of the scheduling algorithm, as well as further
validation in more diverse sets of tasks and topological organizations.
References
1. Blankemeyer, S., et al.: A method to distinguish potential workplaces for humanrobot collaboration. Proc. CIRP 76, 171–176 (2018)
2. Fechter, M., Seeber, C., Chen, S.: Integrated process planning and resource allocation for collaborative robot workplace design. Proc. CIRP 1(72), 39–44 (2018)
3. Johannsmeier, L., Haddadin, S.: A hierarchical human-robot interaction-planning
framework for task allocation in collaborative industrial assembly processes. IEEE
Robot. Autom. Lett. 2(1), 41–48 (2017)
4. Chen, F., Sekiyama, K., Cannella, F., Fukuda, T.: Optimal subtask allocation
for human and robot collaboration within hybrid assembly system. IEEE Trans.
Autom. Sci. Eng. 11(4), 1065–1075 (2014)
5. Roncone, A., Mangin, O., Scassellati, B.: Transparent role assignment and task
allocation in human robot collaboration. In: 2017 IEEE International Conference
on Robotics and Automation (ICRA), pp. 1014–1021. IEEE (2017)
6. Bogner, K., Pferschy, U., Unterberger, R., Zeiner, H.: Optimised scheduling in
humanrobot collaboration a use case in the assembly of printed circuit boards. Int.
J. Prod. Res. 56(16), 5522–5540 (2018)
7. Zhang, C., Shah, J.A.: Co-optimizating multi-agent placement with task assignment and scheduling. In: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, p. 7 (2016)
8. Weckenborg, C., Kieckh¨ afer, K., M¨ uller, C., Grunewald, M., Spengler, T.S.: Balancing of assembly lines with collaborative robots. Bus. Res. 13(1), 93–132 (2019).
https://doi.org/10.1007/s40685-019-0101-y
I. Chatzikonstantinou et al.
roach, which is an indication that narrowing down the search space through hierarchical consideration of topology and task assignment, and then task scheduling
presents a measurable merit. A single instance of a schedule generated through
the proposed approach is demonstrated in Fig. 4.
6 Conclusion
This paper presented a new approach for orchestrating large teams of agents
consisting of collaborating humans and robots in achieving optimal process efficiency while ensuring that humans are involved in minimally laborious tasks. We
specifically focus on the distribution of human agents within factory floors consisting of many workstations, in an efficient manner that promotes supervisory
roles in place of copious labor. We propose a multi-stage optimization approach
for tackling the large-scale HRC orchestration problem, where the first stage
solves an approximate task and topological agent distribution problem, which
is introduced as a set of constraints for the second stage of the problem, which
solves a fully detailed scheduling problem formulated as MILP. Initial experimental validation yields encouraging results that demonstrate a clear advantage
of the proposed approach. The next steps involve further development of heuristics in order to improve efficiency of the scheduling algorithm, as well as further
validation in more diverse sets of tasks and topological organizations.
References
1. Blankemeyer, S., et al.: A method to distinguish potential workplaces for humanrobot collaboration. Proc. CIRP 76, 171–176 (2018)
2. Fechter, M., Seeber, C., Chen, S.: Integrated process planning and resource allocation for collaborative robot workplace design. Proc. CIRP 1(72), 39–44 (2018)
3. Johannsmeier, L., Haddadin, S.: A hierarchical human-robot interaction-planning
framework for task allocation in collaborative industrial assembly processes. IEEE
Robot. Autom. Lett. 2(1), 41–48 (2017)
4. Chen, F., Sekiyama, K., Cannella, F., Fukuda, T.: Optimal subtask allocation
for human and robot collaboration within hybrid assembly system. IEEE Trans.
Autom. Sci. Eng. 11(4), 1065–1075 (2014)
5. Roncone, A., Mangin, O., Scassellati, B.: Transparent role assignment and task
allocation in human robot collaboration. In: 2017 IEEE International Conference
on Robotics and Automation (ICRA), pp. 1014–1021. IEEE (2017)
6. Bogner, K., Pferschy, U., Unterberger, R., Zeiner, H.: Optimised scheduling in
humanrobot collaboration a use case in the assembly of printed circuit boards. Int.
J. Prod. Res. 56(16), 5522–5540 (2018)
7. Zhang, C., Shah, J.A.: Co-optimizating multi-agent placement with task assignment and scheduling. In: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, p. 7 (2016)
8. Weckenborg, C., Kieckh¨ afer, K., M¨ uller, C., Grunewald, M., Spengler, T.S.: Balancing of assembly lines with collaborative robots. Bus. Res. 13(1), 93–132 (2019).
https://doi.org/10.1007/s40685-019-0101-y