{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T07:08:59Z","timestamp":1773385739746,"version":"3.50.1"},"reference-count":125,"publisher":"Association for Computing Machinery (ACM)","issue":"4","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["J. Hum.-Robot Interact."],"published-print":{"date-parts":[[2025,12,31]]},"abstract":"<jats:p>How can intelligent machines assess their competency to complete a task? This question has come into focus for autonomous systems that algorithmically make decisions under uncertainty. We argue that machine self-confidence\u2014a form of meta-reasoning based on self-assessments of system knowledge about the state of the world, itself, and ability to reason about and execute tasks\u2014leads to many computable and useful competency indicators for such agents. This article presents our body of work, so far, on this concept in the form of the Factorized Machine Self-Confidence (FaMSeC) framework, which holistically considers several major factors driving competency in algorithmic decision-making: outcome assessment, solver quality, model quality, alignment quality, and past experience. In FaMSeC, self-confidence indicators are derived via \u201cproblem-solving statistics\u201d embedded in Markov Decision Process solvers and related approaches. These statistics come from evaluating probabilistic exceedance margins in relation to certain outcomes and associated competency standards specified by an evaluator. Once designed, and evaluated, the statistics can be easily incorporated into autonomous agents and serve as indicators of competency. We include detailed descriptions and examples for Markov Decision Process agents and show how outcome assessment and solver quality factors can be found for a range of tasking contexts through novel use of meta-utility functions, behavior simulations, and surrogate prediction models. Numerical evaluations are performed to demonstrate that FaMSeC indicators perform as desired (references to human subject studies beyond the scope of this article are provided).<\/jats:p>","DOI":"10.1145\/3732794","type":"journal-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T10:59:18Z","timestamp":1745837958000},"page":"1-63","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["\u201cA Good Bot Always Knows Its Limitations\u201d: Assessing Autonomous System Decision-Making Competencies through Factorized Machine Self-Confidence"],"prefix":"10.1145","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1602-1685","authenticated-orcid":false,"given":"Brett","family":"Israelsen","sequence":"first","affiliation":[{"name":"RTX Technology Research Center, Hartford, Connecticut, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7555-5671","authenticated-orcid":false,"given":"Nisar R.","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Smead Aerospace Engineering Sciences, University of Colorado Boulder, Boulder, Colorado, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2208-3977","authenticated-orcid":false,"given":"Matthew","family":"Aitken","sequence":"additional","affiliation":[{"name":"Allen Institute for Brain Science, Seattle, Washington, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3686-089X","authenticated-orcid":false,"given":"Eric W.","family":"Frew","sequence":"additional","affiliation":[{"name":"Smead Aerospace Engineering Sciences, University of Colorado Boulder, Boulder, Colorado, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3355-5056","authenticated-orcid":false,"given":"Dale A.","family":"Lawrence","sequence":"additional","affiliation":[{"name":"Smead Aerospace Engineering Sciences, University of Colorado Boulder, Boulder, Colorado, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8400-943X","authenticated-orcid":false,"given":"Brian M.","family":"Argrow","sequence":"additional","affiliation":[{"name":"Smead Aerospace Engineering Sciences, University of Colorado Boulder, Boulder, Colorado, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,22]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981991"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160766"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2017.05.004"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.3390\/s21041210"},{"key":"e_1_3_3_6_2","volume-title":"Master\u2019s thesis","author":"Aitken Matthew","year":"2016","unstructured":"Matthew Aitken. 2016. Assured Human-Autonomy Interaction through Machine Self-Confidence. Master\u2019s thesis. Aerospace Engineering Sciences Department, University of Colorado at Boulder."},{"key":"e_1_3_3_7_2","unstructured":"Matthew Aitken Nisar Ahmed Dale Lawrence Brian Argrow and Eric Frew. 2016. Assurances and machine self-confidence for enhanced trust in autonomous systems. In Proceedings of the RSS 2016 Workshop on Social Trust in Autonomous Robots. Robotics Foundation. Retrieved from http:\/\/qav.comlab.ox.ac.uk\/trust_in_autonomy\/"},{"key":"e_1_3_3_8_2","unstructured":"Prithvi Akella Wyatt Ubellacker and Aaron D. Ames. 2022. Test and evaluation of quadrupedal walking gaits through Sim2Real gap quantification. arXiv:2201.01323. Retrieved from https:\/\/arxiv.org\/abs\/2201.01323"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101805"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-017-0064"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.5555\/3398761.3398781"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2022.103844"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.4204\/eptcs.319.4"},{"key":"e_1_3_3_14_2","first-page":"796","volume-title":"Proceedings of the Conference on Robot Learning","author":"Bobu Andreea","year":"2018","unstructured":"Andreea Bobu, Andrea Bajcsy, Jaime F. Fisac, and Anca D. Dragan. 2018. Learning under misspecified objective spaces. In Proceedings of the Conference on Robot Learning. PMLR, 796\u2013805."},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3610977.3634987"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3618532"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2013.70"},{"key":"e_1_3_3_18_2","first-page":"365","volume-title":"Proceedings of the 10th International Command and Control Research Technology Symposium","author":"Berndt Brehmer","year":"2005","unstructured":"Berndt Brehmer. 2005. The dynamic OODA loop: Amalgamating Boyd\u2019s OODA loop and the cybernetic approach to command and control. In Proceedings of the 10th International Command and Control Research Technology Symposium, 365\u2013368."},{"key":"e_1_3_3_19_2","unstructured":"Eric Brochu Vlad M. Cora and Nando De Freitas. 2010. A tutorial on Bayesian optimization of expensive cost functions with application to active user modeling and hierarchical reinforcement learning. arXiv:1012.2599. Retrieved from https:\/\/arxiv.org\/abs\/1012.2599"},{"key":"e_1_3_3_20_2","first-page":"1105","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Brown Daniel S.","year":"2021","unstructured":"Daniel S. Brown, Jordan Schneider, Anca Dragan, and Scott Niekum. 2021. Value alignment verification. In Proceedings of the International Conference on Machine Learning. PMLR, 1105\u20131115."},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3262187"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2014.00505"},{"issue":"3","key":"e_1_3_3_23_2","first-page":"56","article-title":"Random graph models: An overview of modeling approaches","volume":"156","author":"Channarond Antoine","year":"2015","unstructured":"Antoine Channarond. 2015. Random graph models: An overview of modeling approaches. Journal de la Soci\u00e9t\u00e9 Fran\u00e7aise de Statistique 156, 3 (2015), 56\u201394.","journal-title":"Journal de la Soci\u00e9t\u00e9 Fran\u00e7aise de Statistique"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1088\/1751-8113\/40\/29\/003"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-98464-9_7"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340755"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/PL00012580"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(89)90335-1"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.2202\/1941-6008.1126"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.2514\/6.2022-2496"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2023.1294533"},{"key":"e_1_3_3_32_2","doi-asserted-by":"crossref","unstructured":"Nicholas Conlon Nisar R. Ahmed and Daniel Szafir. 2024. A survey of algorithmic methods for competency self-assessments in human-autonomy teaming. ACM Computing Surveys 56 7 (April 2024) 1\u201331.","DOI":"10.1145\/3616010"},{"key":"e_1_3_3_33_2","first-page":"2127","volume-title":"Proceedings of the 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Conlon Nicholas","year":"2022","unstructured":"Nicholas Conlon, Daniel Szafir, and Nisar Ahmed. 2022. \u201cI\u2019m confident this will end poorly\u201d: Robot proficiency self-assessment in human-robot teaming. In Proceedings of the 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2127\u20132134."},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconbus.2013.08.001"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759279"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.4230\/DagRep.12.7.62"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682730"},{"key":"e_1_3_3_38_2","first-page":"247","volume-title":"Advances in Experimental Social Psychology","author":"Dunning David","year":"2011","unstructured":"David Dunning. 2011. The Dunning\u2013Kruger effect: On being ignorant of one\u2019s own ignorance. In Advances in Experimental Social Psychology. Mark P. Zanna and James M. Olson (Eds.), Vol. 44. Elsevier, 247\u2013296."},{"key":"e_1_3_3_39_2","doi-asserted-by":"crossref","unstructured":"Rudresh Dwivedi Devam Dave Het Naik Smiti Singhal Rana Omer Pankesh Patel Bin Qian Zhenyu Wen Tejal Shah Graham Morgan et al. 2023. Explainable AI (XAI): Core ideas techniques and solutions. ACM Computing Surveys 55 9 (2023) 1\u201333.","DOI":"10.1145\/3561048"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1017\/dsj.2019.7"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2014-34275"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-05258-3_5"},{"key":"e_1_3_3_43_2","first-page":"423","article-title":"Self-confidence and sports performance","volume":"16","author":"Feltz Deborah L.","year":"1988","unstructured":"Deborah L. Feltz. 1988. Self-confidence and sports performance. Exercise and Sports Reviews 16 (1988), 423\u2013457.","journal-title":"Exercise and Sports Reviews"},{"key":"e_1_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1175\/WAF1034.1"},{"key":"e_1_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-psych-022423-032425"},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1037\/rev0000045"},{"key":"e_1_3_3_47_2","unstructured":"Tyler Frasca Evan Krause Ravenna Thielstrom and Matthias Scheutz. 2020. \u201cCan you do this?\u201d Self-assessment dialogues with autonomous robots before during and after a mission. arXiv:2005.01544. Retrieved from https:\/\/arxiv.org\/abs\/2005.01544"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3219024"},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812030"},{"key":"e_1_3_3_50_2","first-page":"2170","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Gelada Carles","year":"2019","unstructured":"Carles Gelada, Saurabh Kumar, Jacob Buckman, Ofir Nachum, and Marc G. Bellemare. 2019. DeepMDP: Learning continuous latent space models for representation learning. In Proceedings of the 36th International Conference on Machine Learning. Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.), Vol. 97, PMLR, 2170\u20132179. Retrieved from https:\/\/proceedings.mlr.press\/v97\/gelada19a.html"},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2014.2331034"},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2970339"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426721"},{"key":"e_1_3_3_54_2","unstructured":"Erin Grant Chelsea Finn Sergey Levine Trevor Darrell and Thomas Griffiths. 2018. Recasting gradient-based meta-learning as hierarchical bayes. arXiv:1801.08930. Retrieved from https:\/\/arxiv.org\/abs\/1801.08930"},{"key":"e_1_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2015.04.006"},{"key":"e_1_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915587924"},{"key":"e_1_3_3_57_2","unstructured":"Alexander Guyer and Thomas G. Dietterich. 2024. Will my robot achieve my goals? Predicting the probability that an MDP policy reaches a user-specified behavior target. arXiv: 2211.16462. Retrieved from https:\/\/arxiv.org\/abs\/2211.16462"},{"key":"e_1_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-32237-2"},{"key":"e_1_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593649"},{"key":"e_1_3_3_60_2","first-page":"279","volume-title":"Proceedings of the Human Factors and Ergonomics Society Annual Meeting","author":"Hutchins Andrew R.","year":"2015","unstructured":"Andrew R. Hutchins, Mary L. Cummings, Mark Draper, and Thomas Hughes. 2015. Representing autonomous systems\u2019 self-confidence through competency boundaries. In Proceedings of the Human Factors and Ergonomics Society Annual Meeting, Vol. 59. Sage Publications, Los Angeles, CA, 279\u2013283."},{"key":"e_1_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2013.10.003"},{"key":"e_1_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.5772\/55919"},{"key":"e_1_3_3_63_2","first-page":"213","volume-title":"Advances in Artificial Intelligence, Software and Systems Engineering: Proceedings of the AHFE 2019 International Conference on Human Factors, Software, Service and Systems Engineering","author":"Israelsen Brett","year":"2020","unstructured":"Brett Israelsen, Nisar Ahmed, Eric Frew, Dale Lawrence, and Brian Argrow. 2020. Machine self-confidence in autonomous systems via meta-analysis of decision processes. In Advances in Artificial Intelligence, Software and Systems Engineering: Proceedings of the AHFE 2019 International Conference on Human Factors, Software, Service and Systems Engineering. Springer, 213\u2013223."},{"key":"e_1_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-44-315991-6.00016-9"},{"key":"e_1_3_3_65_2","volume-title":"Ph.D. Dissertation","author":"Israelsen Brett Wayne","year":"2019","unstructured":"Brett Wayne Israelsen. 2019. Algorithmic Assurances and Self-Assessment of Competency Boundaries in Autonomous Systems. Ph.D. Dissertation. University of Colorado at Boulder, Ann Arbor, United States."},{"key":"e_1_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3267338"},{"key":"e_1_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogpsych.2020.101334"},{"issue":"1","key":"e_1_3_3_68_2","article-title":"Artificial intelligence\u2014The revolution hasn\u2019t happened Yet","volume":"1","author":"Jordan Michael I.","year":"2019","unstructured":"Michael I. Jordan. 2019. Artificial intelligence\u2014The revolution hasn\u2019t happened Yet. Harvard Data Science Review 1, 1 (1 July 2019), 1\u20139. Retrieved from https:\/\/hdsr.mitpress.mit.edu\/pub\/wot7mkc1","journal-title":"Harvard Data Science Review"},{"key":"e_1_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2022.3155327"},{"key":"e_1_3_3_70_2","first-page":"4","volume-title":"Proceedings of the 2015 AAAI Fall Symposium","author":"Kaipa Krishnanand N.","year":"2015","unstructured":"Krishnanand N. Kaipa, Akshaya S. Kankanhalli-Nagendra, and Satyandra K. Gupta. 2015. Toward estimating task execution confidence for robotic bin-picking applications. In Proceedings of the 2015 AAAI Fall Symposium. AAAI Press, 4\u20139. Retrieved from http:\/\/www.aaai.org\/ocs\/index.php\/FSS\/FSS15\/paper\/view\/11723"},{"key":"e_1_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.21314\/JCF.2014.283"},{"key":"e_1_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491209"},{"key":"e_1_3_3_73_2","first-page":"362","volume-title":"Proceedings of the 11th Conference on Uncertainty in Artificial Intelligence (UAI\u201995)","author":"Kim Young-Gyun","year":"1995","unstructured":"Young-Gyun Kim and Marco Valtorta. 1995. On the detection of conflicts in diagnostic Bayesian networks using abstraction. In Proceedings of the 11th Conference on Uncertainty in Artificial Intelligence (UAI\u201995). Morgan Kaufmann Publishers Inc., San Francisco, CA, 362\u2013367."},{"key":"e_1_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/10187.001.0001"},{"key":"e_1_3_3_75_2","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"key":"e_1_3_3_76_2","first-page":"2469","volume-title":"Proceedings of the 39th Annual Meeting of the Cognitive Science Society: Computational Foundations of Cognition (CogSci \u201917)","author":"Krueger Paul M.","year":"2017","unstructured":"Paul M. Krueger, Falk Lieder, and Thomas L. Griffiths. 2017. Enhancing metacognitive reinforcement learning using reward structures and feedback. In Proceedings of the 39th Annual Meeting of the Cognitive Science Society: Computational Foundations of Cognition (CogSci \u201917). The Cognitive Science Society, 2469\u20132474."},{"key":"e_1_3_3_77_2","first-page":"18","volume-title":"Proceedings of the 2015 AAAI Fall Symposium","author":"Kuter Ugur","year":"2015","unstructured":"Ugur Kuter and Chris Miller. 2015. Computational mechanisms to support reporting of self-confidence of automated\/autonomous systems. In Proceedings of the 2015 AAAI Fall Symposium. AAAI Press, 18\u201321. Retrieved from http:\/\/www.aaai.org\/ocs\/index.php\/FSS\/FSS15\/paper\/view\/11682"},{"key":"e_1_3_3_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3319502.3374832"},{"key":"e_1_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/2594413.2594424"},{"key":"e_1_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.1080\/15427951.2005.10129111"},{"key":"e_1_3_3_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342355"},{"key":"e_1_3_3_82_2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-819472-0.00001-0"},{"key":"e_1_3_3_83_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.concog.2011.09.021"},{"key":"e_1_3_3_84_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolmodel.2012.01.013"},{"key":"e_1_3_3_85_2","volume-title":"Master\u2019s thesis","year":"2022","unstructured":"Jamison McGinley. 2022. Approaches for the Computation of Generalized Self-Confidence Statements for Autonomous Vehicles. Master\u2019s thesis. University of Colorado at Boulder, Aerospace Engineering Sciences Department."},{"key":"e_1_3_3_86_2","doi-asserted-by":"publisher","DOI":"10.2514\/6.2020-1378"},{"key":"e_1_3_3_87_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10088-y"},{"key":"e_1_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160828"},{"key":"e_1_3_3_89_2","doi-asserted-by":"crossref","unstructured":"Cyrus Neary Christian Ellis Aryaman Singh Samyal Craig Lennon and Ufuk Topcu. 2023. A multifidelity sim-to-real pipeline for verifiable and compositional reinforcement learning. arXiv:231201249. Retrieved from https:\/\/arxiv.org\/abs\/2312.01249","DOI":"10.1109\/ICRA57147.2024.10610735"},{"key":"e_1_3_3_90_2","doi-asserted-by":"publisher","DOI":"10.1145\/3522579"},{"key":"e_1_3_3_91_2","doi-asserted-by":"publisher","DOI":"10.1518\/001872097778543886"},{"key":"e_1_3_3_92_2","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4240"},{"key":"e_1_3_3_93_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103999"},{"key":"e_1_3_3_94_2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2012.2214558"},{"key":"e_1_3_3_95_2","first-page":"1","volume-title":"Robotics: Science and Systems","volume":"9","author":"Raman Vasumathi","year":"2013","unstructured":"Vasumathi Raman, Constantine Lignos, Cameron Finucane, Kenton C. T. Lee, Mitchell, P. Marcus, and Hadas Kress-Gazit. 2013. Sorry Dave, I\u2019m afraid I can\u2019t do that: Explaining unachievable robot tasks using natural language. In Robotics: Science and Systems. Paul Newman, Dieter Fox, and David Hsu (Eds.), Vol. 9. Citeseer, 1\u20138."},{"key":"e_1_3_3_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3434074.3447181"},{"key":"e_1_3_3_97_2","unstructured":"[96] Goldman Sachs Research. 2024. Gen AI: Too Much Spend Too Little Benefit? Retrieved July 5 2024 from https:\/\/www.goldmansachs.com\/intelligence\/pages\/gen-ai-too-much-spend-too-little-benefit.html"},{"key":"e_1_3_3_98_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS54341.2022.00007"},{"key":"e_1_3_3_99_2","unstructured":"Rebecca Russell. 2023. ALPACA: Autonomous Learning with Probability & Abstraction for Competency Awareness. Technical Report 398339. DTIC. Retrieved from https:\/\/apps.dtic.mil\/sti\/citations\/trecms\/AD1192115"},{"key":"e_1_3_3_100_2","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(91)90015-C"},{"key":"e_1_3_3_101_2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.053"},{"key":"e_1_3_3_102_2","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-1239(199702)7:2<97::AID-RNC298>3.0.CO;2-F"},{"key":"e_1_3_3_103_2","doi-asserted-by":"publisher","DOI":"10.1145\/3568294.3580147"},{"key":"e_1_3_3_104_2","doi-asserted-by":"publisher","DOI":"10.1115\/1.4044598"},{"key":"e_1_3_3_105_2","article-title":"Are emergent abilities of large language models a mirage","volume":"36","author":"Schaeffer Rylan","year":"2024","unstructured":"Rylan Schaeffer, Brando Miranda, and Sanmi Koyejo. 2024. Are emergent abilities of large language models a mirage? In Proceedings of the Advances in Neural Information Processing Systems, Vol. 36.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_106_2","article-title":"Monte-Carlo planning in large POMDPs","volume":"23","author":"Silver David","year":"2010","unstructured":"David Silver and Joel Veness. 2010. 2010. Monte-Carlo planning in large POMDPs. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 23.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_107_2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.ps.41.020190.000245"},{"key":"e_1_3_3_108_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF02512227"},{"key":"e_1_3_3_109_2","doi-asserted-by":"publisher","DOI":"10.1177\/1534484312456690"},{"key":"e_1_3_3_110_2","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton Richard S.","year":"2018","unstructured":"Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. MIT Press."},{"key":"e_1_3_3_111_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967676"},{"key":"e_1_3_3_112_2","doi-asserted-by":"publisher","DOI":"10.2514\/6.2016-1651"},{"key":"e_1_3_3_113_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981105"},{"key":"e_1_3_3_114_2","volume-title":"Probabilistic Robotics","author":"Thrun Sebastian","year":"2005","unstructured":"Sebastian Thrun, Wolfram Burgard, and Dieter Fox. 2005. Probabilistic Robotics. MIT Press."},{"key":"e_1_3_3_115_2","doi-asserted-by":"publisher","DOI":"10.1002\/sim.3033"},{"key":"e_1_3_3_116_2","doi-asserted-by":"publisher","DOI":"10.1177\/0962280209105541"},{"key":"e_1_3_3_117_2","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-023-00284-7"},{"key":"e_1_3_3_118_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00122574"},{"key":"e_1_3_3_119_2","doi-asserted-by":"publisher","DOI":"10.3233\/978-1-58603-969-1-i"},{"key":"e_1_3_3_120_2","doi-asserted-by":"publisher","DOI":"10.4236\/jmf.2016.65060"},{"key":"e_1_3_3_121_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00184-018-0674-z"},{"key":"e_1_3_3_122_2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10384158"},{"key":"e_1_3_3_123_2","volume-title":"Proceedings of the 7th Annual Conference on Robot Learning","author":"Yu Wenhao","year":"2023","unstructured":"Wenhao Yu, Nimrod Gileadi, Chuyuan Fu, Sean Kirmani, Kuang-Huei Lee, Montserrat Gonzalez Arenas, Hao-Tien Lewis Chiang, Tom Erez, Leonard Hasenclever, Jan Humplik, et al. 2023. Language to rewards for robotic skill synthesis. In Proceedings of the 7th Annual Conference on Robot Learning."},{"key":"e_1_3_3_124_2","first-page":"39","volume-title":"Proceedings of the 2015 AAAI Fall Symposium","author":"Zagorecki Adam","year":"2015","unstructured":"Adam Zagorecki, Marcin Kozniewski, and Marek J. Druzdzel. 2015. An approximation of surprise index as a measure of confidence. In Proceedings of the 2015 AAAI Fall Symposium. AAAI Press, 39. Retrieved from http:\/\/www.aaai.org\/ocs\/index.php\/FSS\/FSS15\/paper\/view\/11711"},{"key":"e_1_3_3_125_2","first-page":"1433","volume-title":"Proceedings of the 23rd AAAI Conference on Artificial Intelligence","volume":"8","author":"Ziebart Brian D.","year":"2008","unstructured":"Brian D. Ziebart, Andrew L. Maas, J. Andrew Bagnell, and Anind K. Dey. 2008. Maximum entropy inverse reinforcement learning. In Proceedings of the 23rd AAAI Conference on Artificial Intelligence, Vol. 8, 1433\u20131438."},{"key":"e_1_3_3_126_2","unstructured":"G. Zorpette. 2023. Just calm down about GPT-4 already. IEEE Spectrum. Retrieved May 2023 from https:\/\/spectrum.ieee.org\/gpt-4-calm-down"}],"container-title":["ACM Transactions on Human-Robot Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3732794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T19:26:29Z","timestamp":1753212389000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3732794"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,22]]},"references-count":125,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12,31]]}},"alternative-id":["10.1145\/3732794"],"URL":"https:\/\/doi.org\/10.1145\/3732794","relation":{},"ISSN":["2573-9522"],"issn-type":[{"value":"2573-9522","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,22]]},"assertion":[{"value":"2024-08-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}