An adversarial explainable artificial intelligence (XAI) based approach for action forecasting

• Autorzy: Dutta Vibekananda , Zielińska Teresa

Identyfikatory

DOI

10.14313/JAMRIS/4‐2020/38

• Języki publikacji: EN

Abstrakty

EN

Despite the growing popularity of machine learning technology, vision‐based action recognition/forecasting systems are seen as black‐boxes by the user. The effecti‐ veness of such systems depends on the machine learning algorithms, it is difficult (or impossible) to explain the de‐ cisions making processes to the users. In this context, an approach that offers the user understanding of these re‐ asoning models is significant. To do this, we present an Explainable Artificial Intelligence (XAI) based approach to action forecasting using structured database and object affordances definition. The structured database is sup‐ porting the prediction process. The method allows to vi‐ sualize the components of the structured database. Later, the components of the base are used for forecasting the nominally possible motion goals. The object affordance explicated by the probability functions supports the se‐ lection of possible motion goals. The presented methodo‐ logy allows satisfactory explanations of the reasoning be‐ hind the inference mechanism. Experimental evaluation was conducted using the WUT‐18 dataset, the efficiency of the presented solution was compared to the other ba‐ seline algorithms.

Słowa kluczowe

EN

action prediction; explainable artificial intelligence; object affordances; structured database; motion trajectories

• Wydawca: Łukasiewicz Industrial Research Institute for Automation and Measurements PIAP
• Czasopismo: Journal of Automation Mobile Robotics and Intelligent Systems
• Rocznik: 2020
• Tom: Vol. 14, No. 4
• Strony: 3--10
• Opis fizyczny: Bibliogr. 19 poz., rys.

Twórcy

autor

Dutta Vibekananda

• Institute of Micromechanics and Photonics, Faculty of Mechatronics, Warsaw University of Technology, ul. Św. Andrzeja Boboli 8, 02‑525 Warsaw, Poland, www: https://ztmir.meil.pw.edu.pl/web/Pracownicy/dr‑ Vibekananda‑Dutta

autor

Zielińska Teresa

• Institute of Aeronautics and Applied Mechanics, Faculty of Power and Aeronautical Engineering, Warsaw University of Technology, ul.Nowowiejska 24, 00‑665 Warsaw, Polandwww: https://ztmir.meil.pw.edu.pl/web/Pracownicy/prof.‑ Teresa‑Zielinska

Bibliografia

• [1] S. Anjomshoae, A. Najjar, D. Calvaresi, and K. Främling, “Explainable Agents and Robots: Results from a Systematic Literature Review”. In: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, Richland, SC, 2019, 1078–1088, Montreal QC, Canada.
• [2] F. Chollet, Deep Learning mit Python und Keras: Das Praxis‑Handbuch vom Entwickler der KerasBibliothek, MITP Verlags GmbH: Frechen, 2018.
• [3] M. G. Core, H. C. Lane, M. van Lent, D. Gomboc,S. Solomon, and M. Rosenberg, “Building explainable artificial intelligence systems”. In: Proceedings of the 21st National Conference on Artiifcial Intelligence and the 18th Innovative Applications of Artificial Intelligence Conference/ AAAI‑06/IAAI‑06, 2006, 1766–1773.
• [4] V. Dutta and T. Zielinska, “Action prediction based on physically grounded object affordances in human‑object interactions”. In: 2017 11th International Workshop on Robot Motion and Control (RoMoCo), 2017, 47–52, 10.1109/RoMoCo.2017.8003891.
• [5] V. Dutta and T. Zielinska, “Action based activities prediction by considering human‑object relation”, Prace Naukowe Politechniki Warszawskiej. Elektronika, vol. 196, 2018.
• [6] V. Dutta and T. Zielinska, “Activities Prediction Using Structured Data Base”. In: 2019 12th International Workshop on Robot Motion and Control (RoMoCo), 2019, 80–85, 10.1109/RoMoCo.2019.8787354.
• [7] V. Dutta and T. Zielinska, “Prognosing Human ctivity Using Actions Forecast and Structured Database”, IEEE Access, vol. 8, 2020, 6098–6116, 10.1109/ACCESS.2020.2963933.
• [8] V. Dutta, M. Choraś, M. Pawlicki, and R. Kozik, “A Deep Learning Ensemble for Network Anomaly and Cyber‑Attack Detection”, Sensors, vol. 20, no. 16, 2020, 4583, 10.3390/s20164583.
• [9] V. Dutta and T. Zielinska. “Predicting the Intention of Human Activities for Real‑Time Human Robot Interaction (HRI)”. In: A. Agah, J.‑J. Cabibihan, A. M. Howard, M. A. Salichs, and H. He, eds., Social Robotics, vol. 9979, 723–734. Springer,Cham, 2016, 10.1007/978‑3‑319‑47437‑3_71.
• [10] V. Dutta and T. Zielinska, “Predicting Human ctions Taking into Account Object Affordances”, Journal of Intelligent & Robotic Systems, vol. 93, no. 3‑4, 2019, 745–761, 10.1007/s10846‑018‑0815‑7.
• [11] R. Goebel, A. Chander, K. Holzinger, F. Lecue, Z. Akata, S. Stumpf, P. Kieseberg, and A. Holzinger. “Explainable AI: The New 42?”. In: A. Holzinger, P. Kieseberg, A. M. Tjoa, and E. Weippl, eds., Machine Learning and Knowledge Extraction, volume 11015, 295–303. Springer, Cham, 2018.
• [12] D. Gunning, “Explainable artificial intelligence (XAI)”, Defense Advanced Research Projects Agency (DARPA), nd Web, vol. 2, 2017.
• [13] M. T. Hagan, H. B. Demuth, and M. Beale, Neural Network Design, PWS Publishing Co.: USA, 1997.
• [14] M. Harbers, J. Broekens, K. van den Bosch, and J.‑J. Meyer, “Guidelines for Developing Explainable Cognitive Models”. In: Proceedings of the 10th International Conference on Cognitive Modeling (ICCM 2010), 2010, 85–90.
• [15] T. Lan, T.‑C. Chen, and S. Savarese. “A Hierarchical epresentation for Future Action Prediction”. In: D. Fleet, T. Pajdla, B. Schiele, and T. Tuytelaars, eds., Computer Vision – ECCV 2014, volume 8691, 689–704. Springer, Cham, 2014, 10.1007/978‑3‑319‑10578‑9_45.
• [16] Z. C. Lipton, “The mythos of model interpretability”, Queue, vol. 16, no. 3, 2018, 31–57.
• [17] W. Liu, Z. Wang, X. Liu, N. Zeng, Y. Liu, and F. E. Alsaadi, “A survey of deep neural network architectures and their applications”, Neurocomputing, vol. 234, 2017, 11 – 26, https://doi.org/10.1016/j.neucom.2016.12.038.
• [18] T. Miller, “Explanation in artificial intelligence: Insights from the social sciences”, Artificial Intelligence, vol. 267, 2019, 1–38,10.1016/j.artint.2018.07.007.
• [19] M. T. Ribeiro, S. Singh, and C. Guestrin, “”Why Should I Trust You?”: Explaining the Predictions of Any Classifier”. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA,2016, 1135–1144, 10.1145/2939672.2939778.