Zero-Shot Learning to Enable Error Awareness in Data-Driven HRI
Pages 592 - 601
Abstract
Data-driven social imitation learning is a minimally-supervised approach to generating robot behaviors for human-robot interaction (HRI). However, this type of learning-based approach is error-prone. Existing error detection methods for HRI rely on data labeling, rendering them inappropriate for the data-driven paradigm. We present a zero-shot error detection strategy that requires no labeled data. We use human interaction data to learn models of normal human behavior, then use these models to extract features that help discriminate abnormal human reactions to robot errors. In this feature space, we frame error detection as a novelty detection task, utilizing human interaction data to learn a model of non-erroneous interactions in an unsupervised fashion. Then, we apply the fitted novelty detector to HRI data to identify erroneous robot behavior. We show that our method obtains an average precision of 0.497 on errors, outperforming unsupervised baselines and supervised approaches with limited training data.
References
[1]
Henny Admoni and Brian Scassellati. 2014. Data-Driven Model of Nonverbal Behavior for Socially Assistive Human-Robot Interactions. In Proceedings of the 16th International Conference on Multimodal Interaction (Istanbul, Turkey) (ICMI '14). Association for Computing Machinery, New York, NY, USA, 196--199. https://doi.org/10.1145/2663204.2663263
[2]
Riccardo Bovo, Nicola Binetti, Duncan P. Brumby, and Simon Julier. 2020. Detecting Errors in Pick and Place Procedures: Detecting Errors in Multi-Stage and Sequence-Constrained Manual Retrieve-Assembly Procedures. In Proceedings of the 25th International Conference on Intelligent User Interfaces (Cagliari, Italy) (IUI '20). Association for Computing Machinery, New York, NY, USA, 536--545. https://doi.org/10.1145/3377325.3377497
[3]
Cynthia Breazeal, Nick DePalma, Jeff Orkin, Sonia Chernova, and Malte Jung. 2013. Crowdsourcing Human-Robot Interaction: New Methods and System Evaluation in a Public Environment. J. Hum.-Robot Interact., Vol. 2, 1 (feb 2013), 82--111. https://doi.org/10.5898/JHRI.2.1.Breazeal
[4]
Rakesh Chada, Pradeep Natarajan, Darshan Fofadiya, and Prathap Ramachandra. 2021. Error Detection in Large-Scale Natural Language Understanding Systems Using Transformer Models. CoRR, Vol. abs/2109.01754 (2021). showeprint[arXiv]2109.01754 https://arxiv.org/abs/2109.01754
[5]
N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer. 2002. SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research, Vol. 16 (jun 2002), 321--357. https://doi.org/10.1613/jair.953
[6]
Jessie Y. C. Chen, Michael J. Barnes, and Michelle Harper-Sciarini. 2011. Supervisory Control of Multiple Robots: Human-Performance Issues and User-Interface Design. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), Vol. 41, 4 (2011), 435--454. https://doi.org/10.1109/TSMCC.2010.2056682
[7]
Piotr Chynal and Janusz Sobecki. 2016. Application of thermal imaging camera in eye tracking evaluation. In 2016 9th International Conference on Human System Interactions (HSI). 451--457. https://doi.org/10.1109/HSI.2016.7529673
[8]
Jesse Davis and Mark Goadrich. 2006. The Relationship between Precision-Recall and ROC Curves. In Proceedings of the 23rd International Conference on Machine Learning (Pittsburgh, Pennsylvania, USA) (ICML '06). Association for Computing Machinery, New York, NY, USA, 233--240. https://doi.org/10.1145/1143844.1143874
[9]
Malcolm Doering, Dravzen Brvsvcić, and Takayuki Kanda. 2021. Data-Driven Imitation Learning for a Shopkeeper Robot with Periodically Changing Product Information. J. Hum.-Robot Interact., Vol. 10, 4, Article 31 (jul 2021), bibinfonumpages20 pages. https://doi.org/10.1145/3451883
[10]
Malcolm Doering, Phoebe Liu, Dylan F. Glas, Takayuki Kanda, Dana Kulić, and Hiroshi Ishiguro. 2019. Curiosity Did Not Kill the Robot: A Curiosity-Based Learning System for a Shopkeeper Robot. J. Hum.-Robot Interact., Vol. 8, 3, Article 15 (jul 2019), bibinfonumpages24 pages. https://doi.org/10.1145/3326462
[11]
Peter Flach and Meelis Kull. 2015. Precision-Recall-Gain Curves: PR Analysis Done Right. In Advances in Neural Information Processing Systems, C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett (Eds.), Vol. 28. Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2015/file/33e8075e9970de0cfea955afd4644bb2-Paper.pdf
[12]
Tianxing He and James Glass. 2020. Negative Training for Neural Dialogue Response Generation. arxiv: 1903.02134 [cs.CL]
[13]
Emiel Krahmer, Marc Swerts, Mariet Theune, and Mieke Weegels. 2001. Error Detection in Spoken Human-Machine Interaction. International Journal of Speech Technology, Vol. 4 (03 2001), 19--30. https://doi.org/10.1023/A:1009648614566
[14]
Thomas K. Landauer, Peter W. Foltz, and Darrell Laham. 1998. An Introduction to Latent Semantic Analysis. Discourse Processes, Vol. 25, 2--3 (1998), 259--284.
[15]
Iolanda Leite, André Pereira, Allison Funkhouser, Boyang Li, and Jill Lehman. 2016. Semi-situated learning of verbal and nonverbal content for repeated human-robot interaction. 13--20. https://doi.org/10.1145/2993148.2993190
[16]
Zongyu Li, Kay Hutchinson, and Homa Alemzadeh. 2022. Runtime Detection of Executional Errors in Robot-Assisted Surgery. arxiv: 2203.00737 [cs.CV]
[17]
Phoebe Liu, Dylan F. Glas, Takayuki Kanda, and Hiroshi Ishiguro. 2016. Data-Driven HRI: Learning Social Behaviors by Example From Human--Human Interaction. IEEE Transactions on Robotics, Vol. 32, 4 (2016), 988--1008. https://doi.org/10.1109/TRO.2016.2588880
[18]
Phoebe Liu, Dylan F. Glas, Takayuki Kanda, and Hiroshi Ishiguro. 2019. Two Demonstrators Are Better Than One-A Social Robot That Learns to Imitate People With Different Interaction Styles. IEEE Transactions on Cognitive and Developmental Systems, Vol. 11, 3 (2019), 319--333. https://doi.org/10.1109/TCDS.2017.2787062
[19]
Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schütze. 2008. Introduction to Information Retrieval. Cambridge University Press, Cambridge, UK. http://nlp.stanford.edu/IR-book/information-retrieval-book.html
[20]
Raveesh Meena, José Lopes, Gabriel Skantze, and Joakim Gustafson. 2015. Automatic Detection of Miscommunication in Spoken Dialogue Systems. In Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue. Association for Computational Linguistics, Prague, Czech Republic, 354--363. https://doi.org/10.18653/v1/W15--4647
[21]
Teruhiro Mizumoto, Alberto Fornaser, Hirohiko Suwa, Keiichi Yasumoto, and Mariolino Cecco. 2018. Kinect-Based Micro-Behavior Sensing System for Learning the Smart Assistance with Human Subjects Inside Their Homes. 1--6. https://doi.org/10.1109/METROI4.2018.8428345
[22]
F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, Vol. 12 (2011), 2825--2830.
[23]
Ronald Petrick and Mary Ellen Foster. 2012. What Would You Like to Drink? Recognising and Planning with Social States in a Robot Bartender Domain. AAAI Workshop - Technical Report.
[24]
John Platt. 2000. Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods. Adv. Large Margin Classif., Vol. 10 (06 2000).
[25]
Foster Provost, Tom Fawcett, and Ron Kohavi. 2001. The Case Against Accuracy Estimation for Comparing Induction Algorithms. Proceedings of the Fifteenth International Conference on Machine Learning (04 2001).
[26]
Joshua Ravishankar, Malcolm Doering, and Takayuki Kanda. 2022. Analysis of Robot Errors in Social Imitation Learning. (2022). Extended Abstract presented at Intellect4HRI Workshop, IROS2022.
[27]
Takaya Saito and Marc Rehmsmeier. 2015. The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. PLoS ONE, Vol. 10 (2015). https://api.semanticscholar.org/CorpusID:14081058
[28]
Kristin Schaefer, Jessie Chen, James Szalma, and Peter Hancock. 2016. A Meta-Analysis of Factors Influencing the Development of Trust in Automation: Implications for Understanding Autonomy in Future Systems. Human Factors: The Journal of the Human Factors and Ergonomics Society, Vol. 58 (03 2016). https://doi.org/10.1177/0018720816634228
[29]
Bernhard Schölkopf, Robert C Williamson, Alex Smola, John Shawe-Taylor, and John Platt. 1999. Support Vector Method for Novelty Detection. In Advances in Neural Information Processing Systems, S. Solla, T. Leen, and K. Müller (Eds.), Vol. 12. MIT Press. https://proceedings.neurips.cc/paper_files/paper/1999/file/8725fb777f25776ffa9076e44fcfd776-Paper.pdf
[30]
Abigail See and Christopher Manning. 2021. Understanding and predicting user dissatisfaction in a neural generative chatbot. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue. Association for Computational Linguistics, Singapore and Online, 1--12. https://aclanthology.org/2021.sigdial-1.1
[31]
Alexander J. Smola and Bernhard Schölkopf. 2001. A Tutorial on Support Vector Regression. Statistics and Computing, Vol. 14, 3 (2001), 199--222. https://doi.org/10.1023/A:1006727118198
[32]
Marina Sokolova and Guy Lapalme. 2009. A systematic analysis of performance measures for classification tasks. Information Processing & Management, Vol. 45 (07 2009), 427--437. https://doi.org/10.1016/j.ipm.2009.03.002
[33]
Thorsten P. Spexard, Marc Hanheide, Shuyin Li, and Britta Wrede. 2008. Oops, something is wrong - error detection and recovery for advanced human-robot-interaction. In IEEE International Conference on Robotics and Automation. https://api.semanticscholar.org/CorpusID:59733667
[34]
Maia Stiber, Russell Taylor, and Chien-Ming Huang. 2022. Modeling Human Response to Robot Errors for Timely Error Detection. arxiv: 2208.00565 [cs.RO]
[35]
Maia Stiber, Russell H. Taylor, and Chien-Ming Huang. 2023. On Using Social Signals to Enable Flexible Error-Aware HRI. In Proceedings of the 2023 ACM/IEEE International Conference on Human-Robot Interaction (Stockholm, Sweden) (HRI '23). Association for Computing Machinery, New York, NY, USA, 222--230. https://doi.org/10.1145/3568162.3576990
[36]
Leimin Tian and Sharon Oviatt. 2021. A Taxonomy of Social Errors in Human-Robot Interaction. J. Hum.-Robot Interact., Vol. 10, 2, Article 13 (feb 2021), bibinfonumpages32 pages. https://doi.org/10.1145/3439720
[37]
Suzanne Tolmeijer, Astrid Weiss, Marc Hanheide, Felix Lindner, Thomas M. Powers, Clare Dixon, and Myrthe L. Tielman. 2020. Taxonomy of Trust-Relevant Failures and Mitigation Strategies. In Proceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction (Cambridge, United Kingdom) (HRI '20). Association for Computing Machinery, New York, NY, USA, 3--12. https://doi.org/10.1145/3319502.3374793
[38]
Pauline Trung, Manuel Giuliani, Michael Miksch, Gerald Stollnberger, Susanne Stadler, Nicole Mirnig, and Manfred Tscheligi. 2017. Head and Shoulders: Automatic Error Detection in Human-Robot Interaction. In Proceedings of the 19th ACM International Conference on Multimodal Interaction (Glasgow, UK) (ICMI '17). Association for Computing Machinery, New York, NY, USA, 181--188. https://doi.org/10.1145/3136755.3136785
[39]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. CoRR, Vol. abs/1706.03762 (2017). showeprint[arXiv]1706.03762 http://arxiv.org/abs/1706.03762
[40]
Qiuping Wang. 2007. Probability distribution and entropy as a measure of uncertainty. Journal of Physics A Mathematical and Theoretical, Vol. 41 (01 2007). https://doi.org/10.1088/1751--8113/41/6/065004
[41]
Chuang Yu and Adriana Tapus. 2019. Interactive Robot Learning for Multimodal Emotion Recognition. In The Eleventh International Conference on Social Robotics. Madrid, Spain. https://hal.science/hal-02371856
[42]
Kuanhao Zheng, Dylan F Glas, Takayuki Kanda, Hiroshi Ishiguro, and Norihiro Hagita. 2014. Supervisory control of multiple social robots for conversation and navigation. Transaction on Control and Mechanical Systems, Vol. 3, 2 (2014). io
Index Terms
- Zero-Shot Learning to Enable Error Awareness in Data-Driven HRI
Recommendations
Flexible Robot Error Detection Using Natural Human Responses for Effective HRI
HRI '24: Companion of the 2024 ACM/IEEE International Conference on Human-Robot InteractionRobot errors during human-robot interaction are inescapable; they can occur during any task and do not necessarily fit human expectations. When left unmanaged, robot errors harm task performance and user trust, resulting in user unwillingness to work ...
Adaptive Label Cleaning for Error Detection on Tabular Data
Web and Big DataAbstractExisting supervised methods for error detection require access to clean labels to train the classification model. While the majority of error detection algorithms ignore the harm of noisy labels to detection models. In this paper, we design an ...
Ordinal zero-shot learning
IJCAI'17: Proceedings of the 26th International Joint Conference on Artificial IntelligenceZero-shot learning predicts new class even if no training data is available for that class. The solution to conventional zero-shot learning usually depends on side information such as attribute or text corpora. But these side information is not easy to ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
March 2024
982 pages
ISBN:9798400703225
DOI:10.1145/3610977
- General Chairs:
- Dan Grollman,
- Elizabeth Broadbent,
- Program Chairs:
- Wendy Ju,
- Harold Soh,
- Tom Williams
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 11 March 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- JST, AIP Trilateral AI Research
Conference
HRI '24: ACM/IEEE International Conference on Human-Robot Interaction
March 11 - 15, 2024
CO, Boulder, USA
Acceptance Rates
Overall Acceptance Rate 268 of 1,124 submissions, 24%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 133Total Downloads
- Downloads (Last 12 months)133
- Downloads (Last 6 weeks)13
Reflects downloads up to 19 Nov 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in