Simulation-Based Testing for Human-Robot Collaboration
The evolution towards the Industry 4.0 paradigm aims to increase flexibility and robustness by maintaining the level of productivity. To meet these requirements, collaboration between humans and robots is considered a basic mode of operation within the future intelligent manufacturing cells. However, this interaction between humans and robots is a complex process that raises challenges around compatibility and operational safety. Test-based simulation for human-robot collaboration provides the opportunity to evaluate the feasibility and performance of the system, particularly the layout or workplace planning, production reliability and, especially, the safety and efficiency of human-robot collaboration.
Validating the safety of an HRI (Human Robot Interaction) application is not a trivial task. The simulation is key to the validation in this type of systems [SBT1, SBT5, SBT6]. Through simulation, a high percentage of the safety requirements can be validated without putting any human at risk. In the domain of HRI applications, the relevant value space of input variables in tests and simulations can approach infinity (ill-defined domains), even more when dealing with humans with different impairments [SBT4].
This method explores procedural-task evaluation approaches for testing simulation-based human-robot collaboration. These approaches usually receive as input (i) models required to generate a diagnosis and (ii) data streams from the simulated system to be evaluated (aka, simulation stream). After performing the evaluation, the result of the activity diagnosis is provided as output. Some approaches have focussed on constraint-based modelling to implement the evaluation [SBT2, SBT3]. Whereas other approaches have focussed on the implementation based on Model Tracing [SBT7].
Method artefacts:
- Inputs:
- Diagnosis models
- Simulation stream
- Outputs:
- Activity diagnosis results
- In simulation-based testing, verification activities can be done for different robots without changing other models or tools. Also, system-testing can be done without producing any physical item and adding risk to environment.
- Constraint-based modelling of oracles can provide powerful asserts in complex simulation testing.
- The generation of Constraint-based knowledge models can be a complex and time-consuming task.
- Model Tracing based approaches are not able to explain the root causes of the failures.
References
- [SBT1] Koenig, N., & Howard, A. (2004, September). Design and use paradigms for gazebo, an open-source multi-robot simulator. In 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No. 04CH37566) (Vol. 3, pp. 2149-2154). IEEE. DOI: 10.1109/IROS.2004.1389727
- [SBT2] Aguirre, A., Lozano-Rodero, A., Matey, L. M., Villamañe, M., & Ferrero, B. (2014). A novel approach to diagnosing motor skills. IEEE Transactions on Learning Technologies, 7(4), 304-318. DOI: 10.1109/TLT.2014.2340878
- [SBT3] Aguirre, A., Lozano-Rodero, A., Villamañe, M., Ferrero, B., & Matey, L. M. (2012). OLYMPUS: An Intelligent Interactive Learning Platform for Procedural Tasks. In GRAPP/IVAPP (pp. 543-550). ISBN: 978-989856502-0
- [SBT4] Ostiategui, F., Amundarain, A., Lozano, A., & Matey, L. (2010). Gardening Work Simulation Tool in Virtual Reality for Disabled People Tutorial. Proceedings of Integrated Design and Manufacturing-Virtual Concept (IDMME’10).
- [SBT5] Webster, M., Western, D., Araiza-Illan, D., Dixon, C., Eder, K., Fisher, M., & Pipe, A. G. (2020). A corroborative approach to verification and validation of human–robot teams. The International Journal of Robotics Research, 39(1), 73-99. DOI:10.1177/0278364919883338
- [SBT6] Takaya, K., Asai, T., Kroumov, V., & Smarandache, F. (2016, October). Simulation environment for mobile robots testing using ROS and Gazebo. In 2016 20th International Conference on System Theory, Control and Computing (ICSTCC) (pp. 96-101). IEEE. DOI: 10.1109/ICSTCC.2016.7790647
- [SBT7] Kodaganallur, V., Weitz, R. R., & Rosenthal, D. (2005). A comparison of model-tracing and constraint-based intelligent tutoring paradigms. International Journal of Artificial Intelligence in Education, 15(2), 117-144.