Abstract
Service robots entailing a tight collaboration with humans are increasingly widespread in critical domains, such as healthcare and domestic assistance. However, the so-called Human-Machine-Teaming paradigm can be hindered by the black-box nature of service robots, whose autonomous decisions may be confusing or even dangerous for humans. Thus, the explainability for these systems emerges as a crucial property for their acceptance in our society. This paper introduces the concept of explainable service robots and proposes a software architecture to support the engineering of the self-explainability requirements in these collaborating systems by combining formal analysis and interpretable machine learning. We evaluate the proposed architecture using an illustrative example in healthcare. Results show that our proposal supports the explainability of multi-agent Human-Machine-Teaming missions featuring an infinite (dense) space of human-machine uncertain factors, such as diverse physical and physiological characteristics of the agents involved in the teamwork.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We let the reader refer to [22] for a comprehensive treatment of the model and its accuracy w.r.t. a real-world deployment.
- 2.
A package with full mission specification, data and sources to replicate our results is available at https://doi.org/10.5281/zenodo.8110691.
- 3.
Our current implementation relies on uniform random sampling.
- 4.
Mission success occurs if \(P(\psi )\) is greater than a user-defined probability threshold.
- 5.
References
Angelov, P.P., Soares, E.A., Jiang, R., Arnold, N.I., Atkinson, P.M.: Explainable artificial intelligence: an analytical review. WIREs Data Min. Knowl. Discov. 11(5), e1424 (2021)
Bersani, M.M., Camilli, M., Lestingi, L., Mirandola, R., Rossi, M.: Explainable human-machine teaming using model checking and interpretable machine learning. In: International Conference on Formal Methods in Software Engineering, pp. 18–28. IEEE (2023)
Bersani, M.M., Camilli, M., Lestingi, L., Mirandola, R., Rossi, M., Scandurra, P.: Towards better trust in human-machine teaming through explainable dependability. In: ICSA Companion, pp. 86–90. IEEE (2023)
Cámara, J., Silva, M., Garlan, D., Schmerl, B.: Explaining architectural design tradeoff spaces: a machine learning approach. In: Biffl, S., Navarro, E., Löwe, W., Sirjani, M., Mirandola, R., Weyns, D. (eds.) ECSA 2021. LNCS, vol. 12857, pp. 49–65. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86044-8_4
Camilli, M., Mirandola, R., Scandurra, P.: XSA: Explainable self-adaptation. In: International Conference on Automated Software Engineering. ASE’22. ACM (2023)
Cleland-Huang, J., Agrawal, A., Vierhauser, M., Murphy, M., Prieto, M.: Extending MAPE-K to support human-machine teaming. In: SEAMS, pp. 120–131. ACM (2022)
David, A., Larsen, K.G., Legay, A., Mikučionis, M., Poulsen, D.B.: UPPAAL SMC tutorial. STTT 17(4), 397–415 (2015)
David, A., et al.: Statistical model checking for networks of priced timed automata. In: Fahrenberg, U., Tripakis, S. (eds.) FORMATS 2011. LNCS, vol. 6919, pp. 80–96. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-24310-3_7
EU: Robotics 2020 Multi-Annual Roadmap For Robotic in Europe (2016). https://www.eu-robotics.net/sparc/upload/about/files/H2020-Robotics-Multi-Annual-Roadmap-ICT-2016.pdf
García, S., Strüber, D., Brugali, D., Berger, T., Pelliccione, P.: Robotics software engineering: a perspective from the service robotics domain, pp. 593–604. ESEC/FSE 2020. ACM (2020)
Hanley, J.A., McNeil, B.J.: The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143(1), 29–36 (1982)
Hayes, B., Shah, J.A.: Improving robot controller transparency through autonomous policy explanation. In: HRI, pp. 303–312. IEEE (2017)
Jovanović, M., Schmitz, M.: Explainability as a user requirement for artificial intelligence systems. Computer 55(2), 90–94 (2022)
Kaleeswaran, A.P., Nordmann, A., Vogel, T., Grunske, L.: A systematic literature review on counterexample explanation. Inf. Softw. Technol. 145, 106800 (2022)
Kang, H.G., Dingwell, J.B.: Differential changes with age in multiscale entropy of electromyography signals from leg muscles during treadmill walking. PLoS ONE 11(8), e0162034 (2016)
Khalid, N., Qureshi, N.A.: Towards self-explainable adaptive systems (SEAS): a requirements driven approach. In: Joint Proceedings of REFSQ. CEUR Workshop Proceedings, vol. 2857. CEUR-WS.org (2021)
Kordts, B., Kopetz, J.P., Schrader, A.: A framework for self-explaining systems in the context of intensive care. In: ACSOS, pp. 138–144. IEEE (2021)
Köhl, M.A., Baum, K., Langer, M., Oster, D., Speith, T., Bohlender, D.: Explainability as a non-functional requirement. In: RE, pp. 363–368. IEEE (2019)
de Lemos, R.: Human in the loop: what is the point of no return? In: SEAMS, pp. 165–166. ACM (2020)
Lessmann, S., Baesens, B., Mues, C., Pietsch, S.: Benchmarking classification models for software defect prediction: a proposed framework and novel findings. IEEE Trans. Softw. Eng. 34(4), 485–496 (2008)
Lestingi, L., Askarpour, M., Bersani, M.M., Rossi, M.: A deployment framework for formally verified human-robot interactions. IEEE Access 9, 136616–136635 (2021)
Lestingi, L., Zerla, D., Bersani, M.M., Rossi, M.: Specification, stochastic modeling and analysis of interactive service robotic applications. Robot. Autonom. Syst. 163 (2023)
Li, N., Cámara, J., Garlan, D., Schmerl, B.R., Jin, Z.: Hey! Preparing humans to do tasks in self-adaptive systems. In: SEAMS, pp. 48–58. IEEE (2021)
Madni, A.M., Madni, C.C.: Architectural framework for exploring adaptive human-machine teaming options in simulated dynamic environments. Systems 6(4) (2018)
Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2019)
Mitchell, T.M.: Machine Learning, 1st edn. McGraw-Hill Inc., New York (1997)
Molnar, C.: Interpretable Machine Learning. 2 edn (2022). https://christophm.github.io/interpretable-ml-book
Ozkaya, I.: The behavioral science of software engineering and human-machine teaming. IEEE Softw. 37(6), 3–6 (2020)
Paleja, R., Ghuy, M., Ranawaka Arachchige, N., Jensen, R., Gombolay, M.: The utility of explainable AI in ad hoc human-machine teaming. In: NEURIPS, vol. 34, pp. 610–623. Curran Associates, Inc. (2021)
Scott, A.J., Knott, M.: A cluster analysis method for grouping means in the analysis of variance. Biometrics 30(3), 507–512 (1974)
Stone, M.: Cross-validatory choice and assessment of statistical predictions. J. Roy. Stat. Soc.: Ser. B (Methodol.) 36(2), 111–133 (1974)
Tantithamthavorn, C.K., Jiarpakdee, J.: Explainable AI for software engineering. In: ASE, pp. 1–2. ACM (2021)
Tjoa, E., Guan, C.: A survey on explainable artificial intelligence (XAI): toward medical XAI. IEEE Trans. Neural Netw. Learn. Syst. 32(11), 4793–4813 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bersani, M.M., Camilli, M., Lestingi, L., Mirandola, R., Rossi, M., Scandurra, P. (2023). Architecting Explainable Service Robots. In: Tekinerdogan, B., Trubiani, C., Tibermacine, C., Scandurra, P., Cuesta, C.E. (eds) Software Architecture. ECSA 2023. Lecture Notes in Computer Science, vol 14212. Springer, Cham. https://doi.org/10.1007/978-3-031-42592-9_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-42592-9_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42591-2
Online ISBN: 978-3-031-42592-9
eBook Packages: Computer ScienceComputer Science (R0)