Plan execution monitoring through detection of unmet expectations about action outcomes
The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Modeling the effects of actions based on the state of the world enables robots to make intelligent decisions in different situations. However, it is often infeasible to have globally accurate models. Task performance is often hindered by discrepancies between models and the real world, since the true outcome of executing a plan may be significantly worse than the expected outcome used during planning. Furthermore, expectations about the world are often stochastic in robotics, making the discovery of model-world discrepancies non-trivial. We present an execution monitoring framework capable of finding statistically significant discrepancies, determining the situations in which they occur, and making simple corrections to the world model to improve performance. In our approach, plans are initially based on a model of the world that is only as faithful as computational and algorithmic limitations allow. Through experience, the monitor discovers previously unmodeled modes of the world, defined as regions of a feature space in which the experienced outcome of a plan deviates significantly from the predicted outcome. The monitor may then make suggestions to change the model to match the real world more accurately. We demonstrate this approach on the adversarial domain of robot soccer: we monitor pass interception performance of potentially unknown opponents to try to find unforeseen modes of behavior that affect their interception performance.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“If the failure is technical, there are several automatic methods that can be used to detect the error (e.g., Murphy and Hershberger, 1999; Canham et al., 2003) and automatically determine the appropriate recovery method, without involving human assistance (e.g., Murphy and Hershberger, 1999; Mendoza et al., 2015).”
From Understanding and Resolving Failures in Human-Robot Interaction: Literature Review and Model Development (2018) · cites this paper as Mendoza et al., 2015
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687 · cited 1×
“At the core of our algorithm is the detection of unmodeled modes of behavior through anomaly detection techniques, many of which have been applied in robotics and other fields [10].”
Reinforcement Learning: A Survey
Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996) · Journal of Artificial Intelligence Research · doi:10.1613/jair.301 · Cited by 8,972 · cited 1×
“Model-based RL approaches learn, along with optimal policies, a transition model for the MDP that describes their world [9].”
Background(1999) · Cited by 5,147
Kulldorff, M. (1997) · Communications in Statistics - Theory and Methods · doi:10.1080/03610929708831995 · Cited by 3,939 · cited 1×
“(4) The value of the threshold value amax (line 8) used to detect anomalies is obtained through Monte Carlo sampling [14] to”
MethodThe Cross-Entropy Method for Combinatorial and Continuous Optimization
Rubinstein, R. (1999) · Methodology And Computing In Applied Probability · doi:10.1023/a:1010091220143 · Cited by 903 · cited 1×
“As an optimization algorithm, FARO uses the cross-entropy method [13], although other optimization methods could be used instead.”
MethodHOT SAX: Efficiently Finding the Most Unusual Time Series Subsequence
Keogh, E., Lin, J., & Fu, A. (2006) · Fifth IEEE International Conference on Data Mining (ICDM'05) · doi:10.1109/icdm.2005.79 · Cited by 696 · cited 1×
“In this aspect, our work is related to timeseries analysis [11], although we are more interested in data that is spatially related in some space of features of stateaction space, rather than in purely temporal relationships.”
BackgroundA comparison of direct and model-based reinforcement learning
Atkeson, C. G., & Santamaria, J. C. (2002) · Proceedings of International Conference on Robotics and Automation · doi:10.1109/robot.1997.606886 · Cited by 239 · cited 1×
“in situations where modeling is impractical, learning tends to be less data-efficient and is not generalizable to different tasks within the same environment [8].”
BackgroundExecution monitoring in robotics: A survey
Pettersson, O. (2005) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2005.09.004 · Cited by 194 · cited 1×
“The problem of execution monitoring, well established in fields like industrial control, has gained increased interest in the robotics community [3], since robots need to be robust to failure in uncertain domains.”
BackgroundQ-Learning in Continuous State and Action Spaces
Gaskett, C., Wettergreen, D. S., & Zelinsky, A. (1999) · Lecture notes in computer science · doi:10.1007/3-540-46695-9_35 · Cited by 171 · cited 1×
“Model-free RL approaches, such as Q-Learning [6] and policy gradient descent [7], are capable of improving robot performance without explicitly modeling the world.”
MethodExecution Monitoring of High-Level Robot Programs.
Giacomo, G. D., Reiter, R., & Mikhail Soutchanski, B. (1998) · Cited by 100
Research works printed but not linked: 1
- 0, Small Size Robot League
Cited by
Honig, S., & Oron-Gilad, T. (2018) · Frontiers in Psychology · doi:10.3389/fpsyg.2018.00861 · Cited by 338
“…technical, there are several automatic methods that can be used to detect the error (e.g., Murphy and Hershberger, 1999; Canham et al., 2003) and automatically determine the appropriate recovery method, without involving human assistance (e.g., Murphy and Hershberger, 1999; Mendoza et al., 2015).”
MethodComputer Vision – ECCV 2018 Workshops: Munich, Germany, September 8-14, 2018, Proceedings, Part VI
Mauro, L., Alati, E., Sanzari, M., Ntouskos, V., Massimiani, G., & Pirri, F. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11024-6 · Cited by 59
FINO-Net: A Deep Multimodal Sensor Fusion Framework for Manipulation Failure Detection
İnceoğlu, A., Aksoy, E. E., Ak, A. C., & Sarıel, S. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636455 · Cited by 59
“Execution models [15] and stochastic action models [16] are used to detect and correct [17] execution anomalies.”
MethodSaha, O., Dasgupta, P., & Woosley, B. (2019) · Autonomous Robots · doi:10.1007/s10514-019-09852-5 · Cited by 24
“…trajectory (Bowen et al. 2015), updating the regions in the MDP policy where there is a larger deviation between demonstration and execution (Mendoza et al. 2015), and inverse reinforcement learning to determine the reward function in RL more accurately using reward shaping (Brys et al.…”
MethodFailure Detection Using Proprioceptive, Auditory and Visual Modalities
İnceoğlu, A., İnce, G., Yaslan, Y., & Sarıel, S. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594169 · Cited by 17
“[14] generates stochastic expectations of actions for the given task.”
Background
Metadata
- Authors
- Mendoza, J. P., Veloso, M., & Simmons, R.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- 2015 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2015-05
- Pages
- 3247-3252
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W1528650983
- Cited by
- 18
- References
- 14
- Citations by year
- 2026: 1 · 2025: 1 · 2023: 1 · 2022: 2 · 2021: 4 · 2019: 4 · 2018: 2 · 2017: 1 · 2016: 1 · 2015: 1
- FWCI
- 0.94
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
- KiltHub Repository (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Keywords
- plan execution monitoring, unmet expectations, robot soccer, model-based planning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Plan execution monitoring through detection of unmet expectations about action outcomes. https://app.cochat.ai/papers/10.1109/icra.2015.7139646
- The paper
- Mendoza, J. P., Veloso, M., & Simmons, R. (2015). Plan execution monitoring through detection of unmet expectations about action outcomes. 2015 IEEE International Conference on Robotics and Automation (ICRA). https://doi.org/10.1109/icra.2015.7139646
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.