The DOI matches its Crossref record; 56 of the 57 references it cites were found in a registry or an index.
A policy-blending formalism for shared control
Abstract
In shared control teleoperation, the robot assists the user in accomplishing the desired task, making teleoperation easier and more seamless. Rather than simply executing the user’s input, which is hindered by the inadequacies of the interface, the robot attempts to predict the user’s intent, and assists in accomplishing it. In this work, we are interested in the scientific underpinnings of assistance: we propose an intuitive formalism that captures assistance as policy blending, illustrate how some of the existing techniques for shared control instantiate it, and provide a principled analysis of its main components: prediction of user intent and its arbitration with the user input. We define the prediction problem, with foundations in inverse reinforcement learning, discuss simplifying assumptions that make it tractable, and test these on data from users teleoperating a robotic manipulator. We define the arbitration problem from a control-theoretic perspective, and turn our attention to what users consider good arbitration. We conduct a user study that analyzes the effect of different factors on the performance of assistance, indicating that arbitration should be contextual: it should depend on the robot’s confidence in itself and in the user, and even the particulars of the user. Based on the study, we discuss challenges and opportunities that a robot sharing the control with the user might face: adaptation to the context and the user, legibility of behavior, and the closed loop between prediction and user behavior.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“This transition can be cognitively demanding, particularly for individuals with motor or cognitive impairments.”
In the citing paper
“the study by Dragan and Srinivasa (2013) [19] highlighted that users frequently experience difficulty when required to switch interaction modalities, such as from speech to touch.”
Citations
Cites
Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods
Platt, J. C. (1999) · Cited by 6,385
Apprenticeship learning via inverse reinforcement learning
Abbeel, P., & Ng, A. Y. (2004) · Twenty-first international conference on Machine learning - ICML '04 · doi:10.1145/1015330.1015430 · Cited by 2,769 · cited 3×
“Email: adragan@cs.cmu.edu In our work, we stray away from predefined paths, and instead formulate the prediction problem based on inverse reinforcement learning (Abbeel and Ng, 2004; Ratliff et al., 2006; Ziebart et al., 2008).”
BackgroundMethodAdvances in Large-Margin Classifiers
(2000) · The MIT Press eBooks · doi:10.7551/mitpress/1113.001.0001 · Cited by 1,869
Maximum Entropy Inverse Reinforcement Learning
Ziebart, B. D., Maas, A. L., Bagnell, J. A., & Dey, A. K. (2018) · doi:10.1184/r1/6555512 · Cited by 1,869
CHOMP: Gradient optimization techniques for efficient motion planning
Ratliff, N., Zucker, M., Bagnell, J. A., & Srinivasa, S. (2009) · 2009 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2009.5152817 · Cited by 992 · cited 1×
“Given such a cost, the robot would use a trajectory optimizer (Todorov and Li, 2005; Ratliff et al., 2009; Toussaint, 2009; Dragan et al., 2011b; Kalakrishnan et al., 2011) to acquire the intended trajectory (Figure 4).”
MethodSelf-citationSTOMP: Stochastic trajectory optimization for motion planning
Kalakrishnan, M., Chitta, S., Theodorou, E., Pastor, P., & Schaal, S. (2011) · 2011 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2011.5980280 · Cited by 876 · cited 1×
“Given such a cost, the robot would use a trajectory optimizer (Todorov and Li, 2005; Ratliff et al., 2009; Toussaint, 2009; Dragan et al., 2011b; Kalakrishnan et al., 2011) to acquire the intended trajectory (Figure 4).”
MethodImitation in Animals and Artifacts
(2002) · The MIT Press eBooks · doi:10.7551/mitpress/3676.001.0001 · Cited by 708
Todorov, E., & Li, W. (2005) · Proceedings of the 2005, American Control Conference, 2005. · doi:10.1109/acc.2005.1469949 · Cited by 611 · cited 1×
“Given such a cost, the robot would use a trajectory optimizer (Todorov and Li, 2005; Ratliff et al., 2009; Toussaint, 2009; Dragan et al., 2011b; Kalakrishnan et al., 2011) to acquire the intended trajectory (Figure 4).”
MethodRatliff, N. D., Bagnell, J. A., & Zinkevich, M. A. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143936 · Cited by 606 · cited 4×
“We can formalize this adaptation as an online update to the cost function C that we assume the user is optimizing (Ratliff et al., 2006), made challenging by the high-dimensionality of the space.”
BackgroundMethodInfluentialVirtual fixtures: Perceptual tools for telerobotic manipulation
Rosenberg, L. B. (1993) · Proceedings of IEEE Virtual Reality Annual International Symposium · doi:10.1109/vrais.1993.380795 · Cited by 578 · cited 3×
“…this topic has proposed a great variety of methods for assistance, ranging from the robot having full control over all or some aspect of the motion (Rosenberg, 1993; Debus et al., 2000; Demiris and Hayes, 2002; Marayong et al., 2002, 2003; Fagg et al., 2004; Kim et al., 2011; You and Hauser,…”
BackgroundMethod
Research works printed but not linked: 8
- Anderson SJ, 2010, Proceedings of the 27th army science conference
- Bruemmer DJ, 2002, 2002 AAAI mobile robot workshop
- Dragan A, 2011, Proceedings of the international symposium on robotics research
- Li M, 2003, Proceedings of haptic interfaces for virtual environment and teleoperator systems conference
- Schmidt CF, 1973, Proceedings of the 3rd international joint conference on artificial intelligence
- You E, 2011, Proceedings of robotics: Science and systems
- Yu W, 2005, IEEE international conference on robotics and automation
- Ziebart BD, 2008, Proceedings of the Association for the Advancement of Artificial Intelligence
Cited by
Losey, D. P., McDonald, C. G., Battaglia, E., & O'Malley, M. K. (2018) · Applied Mechanics Reviews · doi:10.1115/1.4039145 · Cited by 392
“[67] and Dragan and Srinivasa [66] combine aspects of co-activity with collaborative arbitration.”
BackgroundInfluentialTeleoperation of Humanoid Robots: A Survey
Darvish, K., Penco, L., Ramos, J., Cisneros, R., Pratt, J., Yoshida, E., Ivaldi, S., & Pucci, D. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3236952 · Cited by 278
“Generally, the operator’s input is modified according to specific metrics by sharing the control authority between the robot and the operator to enhance performance or safety [101].”
BackgroundSimões, A. C., Pinto, A., Santos, J., Pinheiro, S., & Romero, D. (2022) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2021.11.007 · Cited by 233
“Some technical proposals were found in the literature to accomplish this objective: intuitive formalism that captures assistance as policy blending in order [56]; control strategies using a novel asymmetric semiautonomous teleoperation control design framework for teleoperation of mobile twin-arm robotic manipulators…”
BackgroundShared autonomy via hindsight optimization for teleoperation and teaming
Javdani, S., Admoni, H., Pellegrinelli, S., Srinivasa, S. S., & Bagnell, J. A. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364918776060 · Cited by 223
“Blending methods (Dragan and Srinivasa, 2013b) attempt to bridge the gap between highly assistive methods with little user control, and minimal assistance with higher user burden.”
BackgroundMethodResultInfluentialSelf-citationAutonomy in Physical Human-Robot Interaction: A Brief Survey
Selvaggio, M., Cognetti, M., Nikolaidis, S., Ivaldi, S., & Siciliano, B. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3100603 · Cited by 208
“On the same line, a framework based on policy blending is presented in [61]: the robot assistance, during a teleoperated reach-to-grasp task execution, is provided as arbitration of two policies, namely, user’s input and the robot’s prediction of the user’s intent.”
Metadata
- Authors
- Dragan, A. D., & Srinivasa, S. S.
- Affiliations
- Carnegie Mellon University (US)
- Venue
- The International Journal of Robotics Research
- Publisher
- SAGE Publications
- Published
- 2013-06
- Volume
- 32
- Issue
- 7
- Pages
- 790-805
- ISSN
- 0278-3649 (ISSN-L)
- 1741-3176
- OpenAlex
- W2105925198
- Semantic Scholar
- c57571598a964fd49436bf98094697dec17e8d3e
- Cited by
- 387
- References
- 57
- Citations by year
- 2026: 32 · 2025: 31 · 2024: 43 · 2023: 43 · 2022: 31 · 2021: 46 · 2020: 36 · 2019: 21 · 2018: 31 · 2017: 38 · 2016: 17 · 2015: 14 · 2014: 4
- FWCI
- 15.46
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- journals.sagepub.com/page/policies/text-and-data-mining-license (tdm)
- Locations
- The International Journal of Robotics Research (publishedVersion)
- Topics
- Physical Sciences › Engineering › Mechanical Engineering › Teleoperation and Haptic Systems
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Keywords
- shared control, teleoperation, user intention recognition, inverse reinforcement learning, robot manipulators, user study, human-robot interaction
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: A policy-blending formalism for shared control. https://app.cochat.ai/papers/10.1177/0278364913490324
- The paper
- Dragan, A. D., & Srinivasa, S. S. (2013). A policy-blending formalism for shared control. The International Journal of Robotics Research. https://doi.org/10.1177/0278364913490324
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.